Showing 1–50 of 66 results for author: Chai, W

AuroraLong: Bringing RNNs Back to Efficient Open-Ended Video Understanding

Authors: Weili Xu, Enxin Song, Wenhao Chai, Xuexiang Wen, Tian Ye, Gaoang Wang

Abstract: The challenge of long video understanding lies in its high computational complexity and prohibitive memory cost, since the memory and computation required by transformer-based LLMs scale quadratically with input sequence length. We propose AuroraLong to address this challenge by replacing the LLM component in MLLMs with a linear RNN language model that handles input sequence of arbitrary length wi… ▽ More The challenge of long video understanding lies in its high computational complexity and prohibitive memory cost, since the memory and computation required by transformer-based LLMs scale quadratically with input sequence length. We propose AuroraLong to address this challenge by replacing the LLM component in MLLMs with a linear RNN language model that handles input sequence of arbitrary length with constant-size hidden states. To further increase throughput and efficiency, we combine visual token merge with linear RNN models by reordering the visual tokens by their sizes in ascending order. Despite having only 2B parameters and being trained exclusively on public data, AuroraLong achieves performance comparable to Transformer-based models of similar size trained on private datasets across multiple video benchmarks. This demonstrates the potential of efficient, linear RNNs to democratize long video understanding by lowering its computational entry barrier. To our best knowledge, we are the first to use a linear RNN based LLM backbone in a LLaVA-like model for open-ended video understanding. △ Less

Submitted 23 July, 2025; v1 submitted 3 July, 2025; originally announced July 2025.

Comments: ICCV 2025 Camera Ready

ToSA: Token Merging with Spatial Awareness

Authors: Hsiang-Wei Huang, Wenhao Chai, Kuang-Ming Chen, Cheng-Yen Yang, Jenq-Neng Hwang

Abstract: Token merging has emerged as an effective strategy to accelerate Vision Transformers (ViT) by reducing computational costs. However, existing methods primarily rely on the visual token's feature similarity for token merging, overlooking the potential of integrating spatial information, which can serve as a reliable criterion for token merging in the early layers of ViT, where the visual tokens onl… ▽ More Token merging has emerged as an effective strategy to accelerate Vision Transformers (ViT) by reducing computational costs. However, existing methods primarily rely on the visual token's feature similarity for token merging, overlooking the potential of integrating spatial information, which can serve as a reliable criterion for token merging in the early layers of ViT, where the visual tokens only possess weak visual information. In this paper, we propose ToSA, a novel token merging method that combines both semantic and spatial awareness to guide the token merging process. ToSA leverages the depth image as input to generate pseudo spatial tokens, which serve as auxiliary spatial information for the visual token merging process. With the introduced spatial awareness, ToSA achieves a more informed merging strategy that better preserves critical scene structure. Experimental results demonstrate that ToSA outperforms previous token merging methods across multiple benchmarks on visual and embodied question answering while largely reducing the runtime of the ViT, making it an efficient solution for ViT acceleration. The code will be available at: https://github.com/hsiangwei0903/ToSA △ Less

Submitted 24 June, 2025; originally announced June 2025.

Comments: Accepted by IROS 2025

VideoMAR: Autoregressive Video Generatio with Continuous Tokens

Authors: Hu Yu, Biao Gong, Hangjie Yuan, DanDan Zheng, Weilong Chai, Jingdong Chen, Kecheng Zheng, Feng Zhao

Abstract: Masked-based autoregressive models have demonstrated promising image generation capability in continuous space. However, their potential for video generation remains under-explored. In this paper, we propose \textbf{VideoMAR}, a concise and efficient decoder-only autoregressive image-to-video model with continuous tokens, composing temporal frame-by-frame and spatial masked generation. We first id… ▽ More Masked-based autoregressive models have demonstrated promising image generation capability in continuous space. However, their potential for video generation remains under-explored. In this paper, we propose \textbf{VideoMAR}, a concise and efficient decoder-only autoregressive image-to-video model with continuous tokens, composing temporal frame-by-frame and spatial masked generation. We first identify temporal causality and spatial bi-directionality as the first principle of video AR models, and propose the next-frame diffusion loss for the integration of mask and video generation. Besides, the huge cost and difficulty of long sequence autoregressive modeling is a basic but crucial issue. To this end, we propose the temporal short-to-long curriculum learning and spatial progressive resolution training, and employ progressive temperature strategy at inference time to mitigate the accumulation error. Furthermore, VideoMAR replicates several unique capacities of language models to video generation. It inherently bears high efficiency due to simultaneous temporal-wise KV cache and spatial-wise parallel generation, and presents the capacity of spatial and temporal extrapolation via 3D rotary embeddings. On the VBench-I2V benchmark, VideoMAR surpasses the previous state-of-the-art (Cosmos I2V) while requiring significantly fewer parameters ($9.3\%$), training data ($0.5\%$), and GPU resources ($0.2\%$). △ Less

Submitted 18 June, 2025; v1 submitted 17 June, 2025; originally announced June 2025.

LiveCodeBench Pro: How Do Olympiad Medalists Judge LLMs in Competitive Programming?

Authors: Zihan Zheng, Zerui Cheng, Zeyu Shen, Shang Zhou, Kaiyuan Liu, Hansen He, Dongruixuan Li, Stanley Wei, Hangyi Hao, Jianzhu Yao, Peiyao Sheng, Zixuan Wang, Wenhao Chai, Aleksandra Korolova, Peter Henderson, Sanjeev Arora, Pramod Viswanath, Jingbo Shang, Saining Xie

Abstract: Recent reports claim that large language models (LLMs) now outperform elite humans in competitive programming. Drawing on knowledge from a group of medalists in international algorithmic contests, we revisit this claim, examining how LLMs differ from human experts and where limitations still remain. We introduce LiveCodeBench Pro, a benchmark composed of problems from Codeforces, ICPC, and IOI tha… ▽ More Recent reports claim that large language models (LLMs) now outperform elite humans in competitive programming. Drawing on knowledge from a group of medalists in international algorithmic contests, we revisit this claim, examining how LLMs differ from human experts and where limitations still remain. We introduce LiveCodeBench Pro, a benchmark composed of problems from Codeforces, ICPC, and IOI that are continuously updated to reduce the likelihood of data contamination. A team of Olympiad medalists annotates every problem for algorithmic categories and conducts a line-by-line analysis of failed model-generated submissions. Using this new data and benchmark, we find that frontier models still have significant limitations: without external tools, the best model achieves only 53% pass@1 on medium-difficulty problems and 0% on hard problems, domains where expert humans still excel. We also find that LLMs succeed at implementation-heavy problems but struggle with nuanced algorithmic reasoning and complex case analysis, often generating confidently incorrect justifications. High performance appears largely driven by implementation precision and tool augmentation, not superior reasoning. LiveCodeBench Pro thus highlights the significant gap to human grandmaster levels, while offering fine-grained diagnostics to steer future improvements in code-centric LLM reasoning. △ Less

Submitted 13 June, 2025; originally announced June 2025.

Comments: Project Page at https://livecodebenchpro.com/

Ming-Omni: A Unified Multimodal Model for Perception and Generation

Authors: Inclusion AI, Biao Gong, Cheng Zou, Chuanyang Zheng, Chunluan Zhou, Canxiang Yan, Chunxiang Jin, Chunjie Shen, Dandan Zheng, Fudong Wang, Furong Xu, GuangMing Yao, Jun Zhou, Jingdong Chen, Jianxin Sun, Jiajia Liu, Jianjiang Zhu, Jun Peng, Kaixiang Ji, Kaiyou Song, Kaimeng Ren, Libin Wang, Lixiang Ru, Lele Xie, Longhua Tan , et al. (33 additional authors not shown)

Abstract: We propose Ming-Omni, a unified multimodal model capable of processing images, text, audio, and video, while demonstrating strong proficiency in both speech and image generation. Ming-Omni employs dedicated encoders to extract tokens from different modalities, which are then processed by Ling, an MoE architecture equipped with newly proposed modality-specific routers. This design enables a single… ▽ More We propose Ming-Omni, a unified multimodal model capable of processing images, text, audio, and video, while demonstrating strong proficiency in both speech and image generation. Ming-Omni employs dedicated encoders to extract tokens from different modalities, which are then processed by Ling, an MoE architecture equipped with newly proposed modality-specific routers. This design enables a single model to efficiently process and fuse multimodal inputs within a unified framework, thereby facilitating diverse tasks without requiring separate models, task-specific fine-tuning, or structural redesign. Importantly, Ming-Omni extends beyond conventional multimodal models by supporting audio and image generation. This is achieved through the integration of an advanced audio decoder for natural-sounding speech and Ming-Lite-Uni for high-quality image generation, which also allow the model to engage in context-aware chatting, perform text-to-speech conversion, and conduct versatile image editing. Our experimental results showcase Ming-Omni offers a powerful solution for unified perception and generation across all modalities. Notably, our proposed Ming-Omni is the first open-source model we are aware of to match GPT-4o in modality support, and we release all code and model weights to encourage further research and development in the community. △ Less

Submitted 10 June, 2025; originally announced June 2025.

Comments: 18 pages,8 figures

Muddit: Liberating Generation Beyond Text-to-Image with a Unified Discrete Diffusion Model

Authors: Qingyu Shi, Jinbin Bai, Zhuoran Zhao, Wenhao Chai, Kaidong Yu, Jianzong Wu, Shuangyong Song, Yunhai Tong, Xiangtai Li, Xuelong Li, Shuicheng Yan

Abstract: Unified generation models aim to handle diverse tasks across modalities -- such as text generation, image generation, and vision-language reasoning -- within a single architecture and decoding paradigm. Autoregressive unified models suffer from slow inference due to sequential decoding, and non-autoregressive unified models suffer from weak generalization due to limited pretrained backbones. We in… ▽ More Unified generation models aim to handle diverse tasks across modalities -- such as text generation, image generation, and vision-language reasoning -- within a single architecture and decoding paradigm. Autoregressive unified models suffer from slow inference due to sequential decoding, and non-autoregressive unified models suffer from weak generalization due to limited pretrained backbones. We introduce Muddit, a unified discrete diffusion transformer that enables fast and parallel generation across both text and image modalities. Unlike prior unified diffusion models trained from scratch, Muddit integrates strong visual priors from a pretrained text-to-image backbone with a lightweight text decoder, enabling flexible and high-quality multimodal generation under a unified architecture. Empirical results show that Muddit achieves competitive or superior performance compared to significantly larger autoregressive models in both quality and efficiency. The work highlights the potential of purely discrete diffusion, when equipped with strong visual priors, as a scalable and effective backbone for unified generation. △ Less

Submitted 29 May, 2025; originally announced May 2025.

Comments: The code and model are available at https://github.com/M-E-AGI-Lab/Muddit

GAM-Agent: Game-Theoretic and Uncertainty-Aware Collaboration for Complex Visual Reasoning

Authors: Jusheng Zhang, Yijia Fan, Wenjun Lin, Ruiqi Chen, Haoyi Jiang, Wenhao Chai, Jian Wang, Keze Wang

Abstract: We propose GAM-Agent, a game-theoretic multi-agent framework for enhancing vision-language reasoning. Unlike prior single-agent or monolithic models, GAM-Agent formulates the reasoning process as a non-zero-sum game between base agents--each specializing in visual perception subtasks--and a critical agent that verifies logic consistency and factual correctness. Agents communicate via structured cl… ▽ More We propose GAM-Agent, a game-theoretic multi-agent framework for enhancing vision-language reasoning. Unlike prior single-agent or monolithic models, GAM-Agent formulates the reasoning process as a non-zero-sum game between base agents--each specializing in visual perception subtasks--and a critical agent that verifies logic consistency and factual correctness. Agents communicate via structured claims, evidence, and uncertainty estimates. The framework introduces an uncertainty-aware controller to dynamically adjust agent collaboration, triggering multi-round debates when disagreement or ambiguity is detected. This process yields more robust and interpretable predictions. Experiments on four challenging benchmarks--MMMU, MMBench, MVBench, and V*Bench--demonstrate that GAM-Agent significantly improves performance across various VLM backbones. Notably, GAM-Agent boosts the accuracy of small-to-mid scale models (e.g., Qwen2.5-VL-7B, InternVL3-14B) by 5--6\%, and still enhances strong models like GPT-4o by up to 2--3\%. Our approach is modular, scalable, and generalizable, offering a path toward reliable and explainable multi-agent multimodal reasoning. △ Less

Submitted 29 May, 2025; originally announced May 2025.

Ming-Lite-Uni: Advancements in Unified Architecture for Natural Multimodal Interaction

Authors: Inclusion AI, Biao Gong, Cheng Zou, Dandan Zheng, Hu Yu, Jingdong Chen, Jianxin Sun, Junbo Zhao, Jun Zhou, Kaixiang Ji, Lixiang Ru, Libin Wang, Qingpei Guo, Rui Liu, Weilong Chai, Xinyu Xiao, Ziyuan Huang

Abstract: We introduce Ming-Lite-Uni, an open-source multimodal framework featuring a newly designed unified visual generator and a native multimodal autoregressive model tailored for unifying vision and language. Specifically, this project provides an open-source implementation of the integrated MetaQueries and M2-omni framework, while introducing the novel multi-scale learnable tokens and multi-scale repr… ▽ More We introduce Ming-Lite-Uni, an open-source multimodal framework featuring a newly designed unified visual generator and a native multimodal autoregressive model tailored for unifying vision and language. Specifically, this project provides an open-source implementation of the integrated MetaQueries and M2-omni framework, while introducing the novel multi-scale learnable tokens and multi-scale representation alignment strategy. By leveraging a fixed MLLM and a learnable diffusion model, Ming-Lite-Uni enables native multimodal AR models to perform both text-to-image generation and instruction based image editing tasks, expanding their capabilities beyond pure visual understanding. Our experimental results demonstrate the strong performance of Ming-Lite-Uni and illustrate the impressive fluid nature of its interactive process. All code and model weights are open-sourced to foster further exploration within the community. Notably, this work aligns with concurrent multimodal AI milestones - such as ChatGPT-4o with native image generation updated in March 25, 2025 - underscoring the broader significance of unified models like Ming-Lite-Uni on the path toward AGI. Ming-Lite-Uni is in alpha stage and will soon be further refined. △ Less

Submitted 12 June, 2025; v1 submitted 5 May, 2025; originally announced May 2025.

Comments: https://github.com/inclusionAI/Ming/tree/Ming-Lite-Omni-Preview/Ming-unify

TEMPURA: Temporal Event Masked Prediction and Understanding for Reasoning in Action

Authors: Jen-Hao Cheng, Vivian Wang, Huayu Wang, Huapeng Zhou, Yi-Hao Peng, Hou-I Liu, Hsiang-Wei Huang, Kuang-Ming Chen, Cheng-Yen Yang, Wenhao Chai, Yi-Ling Chen, Vibhav Vineet, Qin Cai, Jenq-Neng Hwang

Abstract: Understanding causal event relationships and achieving fine-grained temporal grounding in videos remain challenging for vision-language models. Existing methods either compress video tokens to reduce temporal resolution, or treat videos as unsegmented streams, which obscures fine-grained event boundaries and limits the modeling of causal dependencies. We propose TEMPURA (Temporal Event Masked Pred… ▽ More Understanding causal event relationships and achieving fine-grained temporal grounding in videos remain challenging for vision-language models. Existing methods either compress video tokens to reduce temporal resolution, or treat videos as unsegmented streams, which obscures fine-grained event boundaries and limits the modeling of causal dependencies. We propose TEMPURA (Temporal Event Masked Prediction and Understanding for Reasoning in Action), a two-stage training framework that enhances video temporal understanding. TEMPURA first applies masked event prediction reasoning to reconstruct missing events and generate step-by-step causal explanations from dense event annotations, drawing inspiration from effective infilling techniques. TEMPURA then learns to perform video segmentation and dense captioning to decompose videos into non-overlapping events with detailed, timestamp-aligned descriptions. We train TEMPURA on VER, a large-scale dataset curated by us that comprises 1M training instances and 500K videos with temporally aligned event descriptions and structured reasoning steps. Experiments on temporal grounding and highlight detection benchmarks demonstrate that TEMPURA outperforms strong baseline models, confirming that integrating causal reasoning with fine-grained temporal segmentation leads to improved video understanding. △ Less

Submitted 2 May, 2025; originally announced May 2025.

Video-MMLU: A Massive Multi-Discipline Lecture Understanding Benchmark

Authors: Enxin Song, Wenhao Chai, Weili Xu, Jianwen Xie, Yuxuan Liu, Gaoang Wang

Abstract: Recent advancements in language multimodal models (LMMs) for video have demonstrated their potential for understanding video content, yet the task of comprehending multi-discipline lectures remains largely unexplored. We introduce Video-MMLU, a massive benchmark designed to evaluate the capabilities of LMMs in understanding Multi-Discipline Lectures. We evaluate over 90 open-source and proprietary… ▽ More Recent advancements in language multimodal models (LMMs) for video have demonstrated their potential for understanding video content, yet the task of comprehending multi-discipline lectures remains largely unexplored. We introduce Video-MMLU, a massive benchmark designed to evaluate the capabilities of LMMs in understanding Multi-Discipline Lectures. We evaluate over 90 open-source and proprietary models, ranging from 0.5B to 40B parameters. Our results highlight the limitations of current models in addressing the cognitive challenges presented by these lectures, especially in tasks requiring both perception and reasoning. Additionally, we explore how the number of visual tokens and the large language models influence performance, offering insights into the interplay between multimodal perception and reasoning in lecture comprehension. △ Less

Submitted 2 May, 2025; v1 submitted 20 April, 2025; originally announced April 2025.

Comments: Code, docs, and benchmark are all avaliable at https://enxinsong.com/Video-MMLU-web/

Science-T2I: Addressing Scientific Illusions in Image Synthesis

Authors: Jialuo Li, Wenhao Chai, Xingyu Fu, Haiyang Xu, Saining Xie

Abstract: We present a novel approach to integrating scientific knowledge into generative models, enhancing their realism and consistency in image synthesis. First, we introduce Science-T2I, an expert-annotated adversarial dataset comprising adversarial 20k image pairs with 9k prompts, covering wide distinct scientific knowledge categories. Leveraging Science-T2I, we present SciScore, an end-to-end reward m… ▽ More We present a novel approach to integrating scientific knowledge into generative models, enhancing their realism and consistency in image synthesis. First, we introduce Science-T2I, an expert-annotated adversarial dataset comprising adversarial 20k image pairs with 9k prompts, covering wide distinct scientific knowledge categories. Leveraging Science-T2I, we present SciScore, an end-to-end reward model that refines the assessment of generated images based on scientific knowledge, which is achieved by augmenting both the scientific comprehension and visual capabilities of pre-trained CLIP model. Additionally, based on SciScore, we propose a two-stage training framework, comprising a supervised fine-tuning phase and a masked online fine-tuning phase, to incorporate scientific knowledge into existing generative models. Through comprehensive experiments, we demonstrate the effectiveness of our framework in establishing new standards for evaluating the scientific realism of generated content. Specifically, SciScore attains performance comparable to human-level, demonstrating a 5% improvement similar to evaluations conducted by experienced human evaluators. Furthermore, by applying our proposed fine-tuning method to FLUX, we achieve a performance enhancement exceeding 50% on SciScore. △ Less

Submitted 17 April, 2025; originally announced April 2025.

Comments: Accepted to CVPR 2025. Code, docs, weight, benchmark and training data are all avaliable at https://jialuo-li.github.io/Science-T2I-Web

An Empirical Study of GPT-4o Image Generation Capabilities

Authors: Sixiang Chen, Jinbin Bai, Zhuoran Zhao, Tian Ye, Qingyu Shi, Donghao Zhou, Wenhao Chai, Xin Lin, Jianzong Wu, Chao Tang, Shilin Xu, Tao Zhang, Haobo Yuan, Yikang Zhou, Wei Chow, Linfeng Li, Xiangtai Li, Lei Zhu, Lu Qi

Abstract: The landscape of image generation has rapidly evolved, from early GAN-based approaches to diffusion models and, most recently, to unified generative architectures that seek to bridge understanding and generation tasks. Recent advances, especially the GPT-4o, have demonstrated the feasibility of high-fidelity multimodal generation, their architectural design remains mysterious and unpublished. This… ▽ More The landscape of image generation has rapidly evolved, from early GAN-based approaches to diffusion models and, most recently, to unified generative architectures that seek to bridge understanding and generation tasks. Recent advances, especially the GPT-4o, have demonstrated the feasibility of high-fidelity multimodal generation, their architectural design remains mysterious and unpublished. This prompts the question of whether image and text generation have already been successfully integrated into a unified framework for those methods. In this work, we conduct an empirical study of GPT-4o's image generation capabilities, benchmarking it against leading open-source and commercial models. Our evaluation covers four main categories, including text-to-image, image-to-image, image-to-3D, and image-to-X generation, with more than 20 tasks. Our analysis highlights the strengths and limitations of GPT-4o under various settings, and situates it within the broader evolution of generative modeling. Through this investigation, we identify promising directions for future unified generative models, emphasizing the role of architectural design and data scaling. For a high-definition version of the PDF, please refer to the link on GitHub: \href{https://github.com/Ephemeral182/Empirical-Study-of-GPT-4o-Image-Gen}{https://github.com/Ephemeral182/Empirical-Study-of-GPT-4o-Image-Gen}. △ Less

Submitted 10 April, 2025; v1 submitted 8 April, 2025; originally announced April 2025.

Envisioning Beyond the Pixels: Benchmarking Reasoning-Informed Visual Editing

Authors: Xiangyu Zhao, Peiyuan Zhang, Kexian Tang, Xiaorong Zhu, Hao Li, Wenhao Chai, Zicheng Zhang, Renqiu Xia, Guangtao Zhai, Junchi Yan, Hua Yang, Xue Yang, Haodong Duan

Abstract: Large Multi-modality Models (LMMs) have made significant progress in visual understanding and generation, but they still face challenges in General Visual Editing, particularly in following complex instructions, preserving appearance consistency, and supporting flexible input formats. To study this gap, we introduce RISEBench, the first benchmark for evaluating Reasoning-Informed viSual Editing (R… ▽ More Large Multi-modality Models (LMMs) have made significant progress in visual understanding and generation, but they still face challenges in General Visual Editing, particularly in following complex instructions, preserving appearance consistency, and supporting flexible input formats. To study this gap, we introduce RISEBench, the first benchmark for evaluating Reasoning-Informed viSual Editing (RISE). RISEBench focuses on four key reasoning categories: Temporal, Causal, Spatial, and Logical Reasoning. We curate high-quality test cases for each category and propose an robust evaluation framework that assesses Instruction Reasoning, Appearance Consistency, and Visual Plausibility with both human judges and the LMM-as-a-judge approach. We conducted experiments evaluating nine prominent visual editing models, comprising both open-source and proprietary models. The evaluation results demonstrate that current models face significant challenges in reasoning-based editing tasks. Even the most powerful model evaluated, GPT-4o-Image, achieves an accuracy of merely 28.8%. RISEBench effectively highlights the limitations of contemporary editing models, provides valuable insights, and indicates potential future directions for the field of reasoning-aware visual editing. Our code and data have been released at https://github.com/PhoenixZ810/RISEBench. △ Less

Submitted 27 May, 2025; v1 submitted 3 April, 2025; originally announced April 2025.

EMMOE: A Comprehensive Benchmark for Embodied Mobile Manipulation in Open Environments

Authors: Dongping Li, Tielong Cai, Tianci Tang, Wenhao Chai, Katherine Rose Driggs-Campbell, Gaoang Wang

Abstract: Developing autonomous home robots controlled by natural language has long been a pursuit of humanity. While advancements in large language models (LLMs) and embodied intelligence make this goal closer, several challenges persist: the lack of a unified benchmark for more complex robot tasks, limited evaluation methods and metrics, data incompatibility between LLMs and mobile manipulation trajectori… ▽ More Developing autonomous home robots controlled by natural language has long been a pursuit of humanity. While advancements in large language models (LLMs) and embodied intelligence make this goal closer, several challenges persist: the lack of a unified benchmark for more complex robot tasks, limited evaluation methods and metrics, data incompatibility between LLMs and mobile manipulation trajectories. To address these issues, we propose Embodied Mobile Manipulation in Open Environments (EMMOE), a benchmark that requires agents to interpret user instructions and execute long-horizon everyday tasks in continuous space. EMMOE seamlessly integrates high-level and low-level embodied tasks into a unified framework, along with three new metrics for more diverse assessment. Additionally, we collect~\dataset, which features in various task attributes, detailed process annotations, re-plans after failures, and two sub-datasets for LLM training. Furthermore, we design~\model, a sophisticated agent system consists of LLM with Direct Preference Optimization (DPO), light weighted navigation and manipulation models, and multiple error detection mechanisms. Finally, we demonstrate~\model's performance and evaluations of different models and policies. △ Less

Submitted 14 May, 2025; v1 submitted 11 March, 2025; originally announced March 2025.

DiffPO: Diffusion-styled Preference Optimization for Efficient Inference-Time Alignment of Large Language Models

Authors: Ruizhe Chen, Wenhao Chai, Zhifei Yang, Xiaotian Zhang, Joey Tianyi Zhou, Tony Quek, Soujanya Poria, Zuozhu Liu

Abstract: Inference-time alignment provides an efficient alternative for aligning LLMs with humans. However, these approaches still face challenges, such as limited scalability due to policy-specific value functions and latency during the inference phase. In this paper, we propose a novel approach, Diffusion-styled Preference Optimization (\model), which provides an efficient and policy-agnostic solution fo… ▽ More Inference-time alignment provides an efficient alternative for aligning LLMs with humans. However, these approaches still face challenges, such as limited scalability due to policy-specific value functions and latency during the inference phase. In this paper, we propose a novel approach, Diffusion-styled Preference Optimization (\model), which provides an efficient and policy-agnostic solution for aligning LLMs with humans. By directly performing alignment at sentence level, \model~avoids the time latency associated with token-level generation. Designed as a plug-and-play module, \model~can be seamlessly integrated with various base models to enhance their alignment. Extensive experiments on AlpacaEval 2, MT-bench, and HH-RLHF demonstrate that \model~achieves superior alignment performance across various settings, achieving a favorable trade-off between alignment quality and inference-time latency. Furthermore, \model~demonstrates model-agnostic scalability, significantly improving the performance of large models such as Llama-3-70B. △ Less

Submitted 25 May, 2025; v1 submitted 6 March, 2025; originally announced March 2025.

Comments: ACL 2025

Multimodal Representation Alignment for Image Generation: Text-Image Interleaved Control Is Easier Than You Think

Authors: Liang Chen, Shuai Bai, Wenhao Chai, Weichu Xie, Haozhe Zhao, Leon Vinci, Junyang Lin, Baobao Chang

Abstract: The field of advanced text-to-image generation is witnessing the emergence of unified frameworks that integrate powerful text encoders, such as CLIP and T5, with Diffusion Transformer backbones. Although there have been efforts to control output images with additional conditions, like canny and depth map, a comprehensive framework for arbitrary text-image interleaved control is still lacking. This… ▽ More The field of advanced text-to-image generation is witnessing the emergence of unified frameworks that integrate powerful text encoders, such as CLIP and T5, with Diffusion Transformer backbones. Although there have been efforts to control output images with additional conditions, like canny and depth map, a comprehensive framework for arbitrary text-image interleaved control is still lacking. This gap is especially evident when attempting to merge concepts or visual elements from multiple images in the generation process. To mitigate the gap, we conducted preliminary experiments showing that large multimodal models (LMMs) offer an effective shared representation space, where image and text can be well-aligned to serve as a condition for external diffusion models. Based on this discovery, we propose Dream Engine, an efficient and unified framework designed for arbitrary text-image interleaved control in image generation models. Building on powerful text-to-image models like SD3.5, we replace the original text-only encoders by incorporating versatile multimodal information encoders such as QwenVL. Our approach utilizes a two-stage training paradigm, consisting of joint text-image alignment and multimodal interleaved instruction tuning. Our experiments demonstrate that this training method is effective, achieving a 0.69 overall score on the GenEval benchmark, and matching the performance of state-of-the-art text-to-image models like SD3.5 and FLUX. △ Less

Submitted 27 February, 2025; originally announced February 2025.

Comments: 13 pages, 9 figures, codebase in https://github.com/chenllliang/DreamEngine

Pointmap Association and Piecewise-Plane Constraint for Consistent and Compact 3D Gaussian Segmentation Field

Authors: Wenhao Hu, Wenhao Chai, Shengyu Hao, Xiaotong Cui, Xuexiang Wen, Jenq-Neng Hwang, Gaoang Wang

Abstract: Achieving a consistent and compact 3D segmentation field is crucial for maintaining semantic coherence across views and accurately representing scene structures. Previous 3D scene segmentation methods rely on video segmentation models to address inconsistencies across views, but the absence of spatial information often leads to object misassociation when object temporarily disappear and reappear.… ▽ More Achieving a consistent and compact 3D segmentation field is crucial for maintaining semantic coherence across views and accurately representing scene structures. Previous 3D scene segmentation methods rely on video segmentation models to address inconsistencies across views, but the absence of spatial information often leads to object misassociation when object temporarily disappear and reappear. Furthermore, in the process of 3D scene reconstruction, segmentation and optimization are often treated as separate tasks. As a result, optimization typically lacks awareness of semantic category information, which can result in floaters with ambiguous segmentation. To address these challenges, we introduce CCGS, a method designed to achieve both view consistent 2D segmentation and a compact 3D Gaussian segmentation field. CCGS incorporates pointmap association and a piecewise-plane constraint. First, we establish pixel correspondence between adjacent images by minimizing the Euclidean distance between their pointmaps. We then redefine object mask overlap accordingly. The Hungarian algorithm is employed to optimize mask association by minimizing the total matching cost, while allowing for partial matches. To further enhance compactness, the piecewise-plane constraint restricts point displacement within local planes during optimization, thereby preserving structural integrity. Experimental results on ScanNet and Replica datasets demonstrate that CCGS outperforms existing methods in both 2D panoptic segmentation and 3D Gaussian segmentation. △ Less

Submitted 22 February, 2025; originally announced February 2025.

PackDiT: Joint Human Motion and Text Generation via Mutual Prompting

Authors: Zhongyu Jiang, Wenhao Chai, Zhuoran Zhou, Cheng-Yen Yang, Hsiang-Wei Huang, Jenq-Neng Hwang

Abstract: Human motion generation has advanced markedly with the advent of diffusion models. Most recent studies have concentrated on generating motion sequences based on text prompts, commonly referred to as text-to-motion generation. However, the bidirectional generation of motion and text, enabling tasks such as motion-to-text alongside text-to-motion, has been largely unexplored. This capability is esse… ▽ More Human motion generation has advanced markedly with the advent of diffusion models. Most recent studies have concentrated on generating motion sequences based on text prompts, commonly referred to as text-to-motion generation. However, the bidirectional generation of motion and text, enabling tasks such as motion-to-text alongside text-to-motion, has been largely unexplored. This capability is essential for aligning diverse modalities and supports unconditional generation. In this paper, we introduce PackDiT, the first diffusion-based generative model capable of performing various tasks simultaneously, including motion generation, motion prediction, text generation, text-to-motion, motion-to-text, and joint motion-text generation. Our core innovation leverages mutual blocks to integrate multiple diffusion transformers (DiTs) across different modalities seamlessly. We train PackDiT on the HumanML3D dataset, achieving state-of-the-art text-to-motion performance with an FID score of 0.106, along with superior results in motion prediction and in-between tasks. Our experiments further demonstrate that diffusion models are effective for motion-to-text generation, achieving performance comparable to that of autoregressive models. △ Less

Submitted 27 January, 2025; originally announced January 2025.

SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory

Authors: Cheng-Yen Yang, Hsiang-Wei Huang, Wenhao Chai, Zhongyu Jiang, Jenq-Neng Hwang

Abstract: The Segment Anything Model 2 (SAM 2) has demonstrated strong performance in object segmentation tasks but faces challenges in visual object tracking, particularly when managing crowded scenes with fast-moving or self-occluding objects. Furthermore, the fixed-window memory approach in the original model does not consider the quality of memories selected to condition the image features for the next… ▽ More The Segment Anything Model 2 (SAM 2) has demonstrated strong performance in object segmentation tasks but faces challenges in visual object tracking, particularly when managing crowded scenes with fast-moving or self-occluding objects. Furthermore, the fixed-window memory approach in the original model does not consider the quality of memories selected to condition the image features for the next frame, leading to error propagation in videos. This paper introduces SAMURAI, an enhanced adaptation of SAM 2 specifically designed for visual object tracking. By incorporating temporal motion cues with the proposed motion-aware memory selection mechanism, SAMURAI effectively predicts object motion and refines mask selection, achieving robust, accurate tracking without the need for retraining or fine-tuning. SAMURAI operates in real-time and demonstrates strong zero-shot performance across diverse benchmark datasets, showcasing its ability to generalize without fine-tuning. In evaluations, SAMURAI achieves significant improvements in success rate and precision over existing trackers, with a 7.1% AUC gain on LaSOT$_{\text{ext}}$ and a 3.5% AO gain on GOT-10k. Moreover, it achieves competitive results compared to fully supervised methods on LaSOT, underscoring its robustness in complex tracking scenarios and its potential for real-world applications in dynamic environments. △ Less

Submitted 30 November, 2024; v1 submitted 18 November, 2024; originally announced November 2024.

Comments: Project page is available at https://yangchris11.github.io/samurai/

LLaVA-Ultra: Large Chinese Language and Vision Assistant for Ultrasound

Authors: Xuechen Guo, Wenhao Chai, Shi-Yan Li, Gaoang Wang

Abstract: Multimodal Large Language Model (MLLM) has recently garnered attention as a prominent research focus. By harnessing powerful LLM, it facilitates a transition of conversational generative AI from unimodal text to performing multimodal tasks. This boom begins to significantly impact medical field. However, general visual language model (VLM) lacks sophisticated comprehension for medical visual quest… ▽ More Multimodal Large Language Model (MLLM) has recently garnered attention as a prominent research focus. By harnessing powerful LLM, it facilitates a transition of conversational generative AI from unimodal text to performing multimodal tasks. This boom begins to significantly impact medical field. However, general visual language model (VLM) lacks sophisticated comprehension for medical visual question answering (Med-VQA). Even models specifically tailored for medical domain tend to produce vague answers with weak visual relevance. In this paper, we propose a fine-grained adaptive VLM architecture for Chinese medical visual conversations through parameter-efficient tuning. Specifically, we devise a fusion module with fine-grained vision encoders to achieve enhancement for subtle medical visual semantics. Then we note data redundancy common to medical scenes is ignored in most prior works. In cases of a single text paired with multiple figures, we utilize weighted scoring with knowledge distillation to adaptively screen valid images mirroring text descriptions. For execution, we leverage a large-scale multimodal Chinese ultrasound dataset obtained from the hospital. We create instruction-following data based on text from professional doctors, which ensures effective tuning. With enhanced model and quality data, our Large Chinese Language and Vision Assistant for Ultrasound (LLaVA-Ultra) shows strong capability and robustness to medical scenarios. On three Med-VQA datasets, LLaVA-Ultra surpasses previous state-of-the-art models on various metrics. △ Less

Submitted 19 October, 2024; originally announced October 2024.

Ego3DT: Tracking Every 3D Object in Ego-centric Videos

Authors: Shengyu Hao, Wenhao Chai, Zhonghan Zhao, Meiqi Sun, Wendi Hu, Jieyang Zhou, Yixian Zhao, Qi Li, Yizhou Wang, Xi Li, Gaoang Wang

Abstract: The growing interest in embodied intelligence has brought ego-centric perspectives to contemporary research. One significant challenge within this realm is the accurate localization and tracking of objects in ego-centric videos, primarily due to the substantial variability in viewing angles. Addressing this issue, this paper introduces a novel zero-shot approach for the 3D reconstruction and track… ▽ More The growing interest in embodied intelligence has brought ego-centric perspectives to contemporary research. One significant challenge within this realm is the accurate localization and tracking of objects in ego-centric videos, primarily due to the substantial variability in viewing angles. Addressing this issue, this paper introduces a novel zero-shot approach for the 3D reconstruction and tracking of all objects from the ego-centric video. We present Ego3DT, a novel framework that initially identifies and extracts detection and segmentation information of objects within the ego environment. Utilizing information from adjacent video frames, Ego3DT dynamically constructs a 3D scene of the ego view using a pre-trained 3D scene reconstruction model. Additionally, we have innovated a dynamic hierarchical association mechanism for creating stable 3D tracking trajectories of objects in ego-centric videos. Moreover, the efficacy of our approach is corroborated by extensive experiments on two newly compiled datasets, with 1.04x - 2.90x in HOTA, showcasing the robustness and accuracy of our method in diverse ego-centric scenarios. △ Less

Submitted 11 October, 2024; originally announced October 2024.

Comments: Accepted by ACM Multimedia 2024

PAD: Personalized Alignment of LLMs at Decoding-Time

Authors: Ruizhe Chen, Xiaotian Zhang, Meng Luo, Wenhao Chai, Zuozhu Liu

Abstract: Aligning with personalized preferences, which vary significantly across cultural, educational, and political differences, poses a significant challenge due to the computational costs and data demands of traditional alignment methods. In response, this paper presents Personalized Alignment at Decoding-time (PAD), a novel framework designed to align LLM outputs with diverse personalized preferences… ▽ More Aligning with personalized preferences, which vary significantly across cultural, educational, and political differences, poses a significant challenge due to the computational costs and data demands of traditional alignment methods. In response, this paper presents Personalized Alignment at Decoding-time (PAD), a novel framework designed to align LLM outputs with diverse personalized preferences during the inference phase, eliminating the need for additional training. By introducing a unique personalized reward modeling strategy, this framework decouples the text generation process from personalized preferences, facilitating the generation of generalizable token-level personalized rewards. The PAD algorithm leverages these rewards to guide the decoding process, dynamically tailoring the base model's predictions to personalized preferences. Extensive experimental results demonstrate that PAD not only outperforms existing training-based alignment methods in terms of aligning with diverse preferences but also shows significant generalizability to preferences unseen during training and scalability across different base models. This work advances the capability of LLMs to meet user needs in real-time applications, presenting a substantial step forward in personalized LLM alignment. △ Less

Submitted 13 March, 2025; v1 submitted 5 October, 2024; originally announced October 2024.

Comments: ICLR 2025

AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark

Authors: Wenhao Chai, Enxin Song, Yilun Du, Chenlin Meng, Vashisht Madhavan, Omer Bar-Tal, Jenq-Neng Hwang, Saining Xie, Christopher D. Manning

Abstract: Video detailed captioning is a key task which aims to generate comprehensive and coherent textual descriptions of video content, benefiting both video understanding and generation. In this paper, we propose AuroraCap, a video captioner based on a large multimodal model. We follow the simplest architecture design without additional parameters for temporal modeling. To address the overhead caused by… ▽ More Video detailed captioning is a key task which aims to generate comprehensive and coherent textual descriptions of video content, benefiting both video understanding and generation. In this paper, we propose AuroraCap, a video captioner based on a large multimodal model. We follow the simplest architecture design without additional parameters for temporal modeling. To address the overhead caused by lengthy video sequences, we implement the token merging strategy, reducing the number of input visual tokens. Surprisingly, we found that this strategy results in little performance loss. AuroraCap shows superior performance on various video and image captioning benchmarks, for example, obtaining a CIDEr of 88.9 on Flickr30k, beating GPT-4V (55.3) and Gemini-1.5 Pro (82.2). However, existing video caption benchmarks only include simple descriptions, consisting of a few dozen words, which limits research in this field. Therefore, we develop VDC, a video detailed captioning benchmark with over one thousand carefully annotated structured captions. In addition, we propose a new LLM-assisted metric VDCscore for bettering evaluation, which adopts a divide-and-conquer strategy to transform long caption evaluation into multiple short question-answer pairs. With the help of human Elo ranking, our experiments show that this benchmark better correlates with human judgments of video detailed captioning quality. △ Less

Submitted 9 April, 2025; v1 submitted 3 October, 2024; originally announced October 2024.

Comments: Accepted to ICLR 2025. Code, docs, weight, benchmark and training data are all avaliable at https://rese1f.github.io/aurora-web/

AGLLDiff: Guiding Diffusion Models Towards Unsupervised Training-free Real-world Low-light Image Enhancement

Authors: Yunlong Lin, Tian Ye, Sixiang Chen, Zhenqi Fu, Yingying Wang, Wenhao Chai, Zhaohu Xing, Lei Zhu, Xinghao Ding

Abstract: Existing low-light image enhancement (LIE) methods have achieved noteworthy success in solving synthetic distortions, yet they often fall short in practical applications. The limitations arise from two inherent challenges in real-world LIE: 1) the collection of distorted/clean image pairs is often impractical and sometimes even unavailable, and 2) accurately modeling complex degradations presents… ▽ More Existing low-light image enhancement (LIE) methods have achieved noteworthy success in solving synthetic distortions, yet they often fall short in practical applications. The limitations arise from two inherent challenges in real-world LIE: 1) the collection of distorted/clean image pairs is often impractical and sometimes even unavailable, and 2) accurately modeling complex degradations presents a non-trivial problem. To overcome them, we propose the Attribute Guidance Diffusion framework (AGLLDiff), a training-free method for effective real-world LIE. Instead of specifically defining the degradation process, AGLLDiff shifts the paradigm and models the desired attributes, such as image exposure, structure and color of normal-light images. These attributes are readily available and impose no assumptions about the degradation process, which guides the diffusion sampling process to a reliable high-quality solution space. Extensive experiments demonstrate that our approach outperforms the current leading unsupervised LIE methods across benchmarks in terms of distortion-based and perceptual-based metrics, and it performs well even in sophisticated wild degradation. △ Less

Submitted 23 July, 2024; v1 submitted 20 July, 2024; originally announced July 2024.

Comments: 21 pages, 9 figures

Boosting Online 3D Multi-Object Tracking through Camera-Radar Cross Check

Authors: Sheng-Yao Kuan, Jen-Hao Cheng, Hsiang-Wei Huang, Wenhao Chai, Cheng-Yen Yang, Hugo Latapie, Gaowen Liu, Bing-Fei Wu, Jenq-Neng Hwang

Abstract: In the domain of autonomous driving, the integration of multi-modal perception techniques based on data from diverse sensors has demonstrated substantial progress. Effectively surpassing the capabilities of state-of-the-art single-modality detectors through sensor fusion remains an active challenge. This work leverages the respective advantages of cameras in perspective view and radars in Bird's E… ▽ More In the domain of autonomous driving, the integration of multi-modal perception techniques based on data from diverse sensors has demonstrated substantial progress. Effectively surpassing the capabilities of state-of-the-art single-modality detectors through sensor fusion remains an active challenge. This work leverages the respective advantages of cameras in perspective view and radars in Bird's Eye View (BEV) to greatly enhance overall detection and tracking performance. Our approach, Camera-Radar Associated Fusion Tracking Booster (CRAFTBooster), represents a pioneering effort to enhance radar-camera fusion in the tracking stage, contributing to improved 3D MOT accuracy. The superior experimental results on the K-Radaar dataset, which exhibit 5-6% on IDF1 tracking performance gain, validate the potential of effective sensor fusion in advancing autonomous driving. △ Less

Submitted 18 July, 2024; originally announced July 2024.

Comments: 2024 IEEE Intelligent Vehicles Symposium (IV)

RT-Pose: A 4D Radar Tensor-based 3D Human Pose Estimation and Localization Benchmark

Authors: Yuan-Hao Ho, Jen-Hao Cheng, Sheng Yao Kuan, Zhongyu Jiang, Wenhao Chai, Hsiang-Wei Huang, Chih-Lung Lin, Jenq-Neng Hwang

Abstract: Traditional methods for human localization and pose estimation (HPE), which mainly rely on RGB images as an input modality, confront substantial limitations in real-world applications due to privacy concerns. In contrast, radar-based HPE methods emerge as a promising alternative, characterized by distinctive attributes such as through-wall recognition and privacy-preserving, rendering the method m… ▽ More Traditional methods for human localization and pose estimation (HPE), which mainly rely on RGB images as an input modality, confront substantial limitations in real-world applications due to privacy concerns. In contrast, radar-based HPE methods emerge as a promising alternative, characterized by distinctive attributes such as through-wall recognition and privacy-preserving, rendering the method more conducive to practical deployments. This paper presents a Radar Tensor-based human pose (RT-Pose) dataset and an open-source benchmarking framework. The RT-Pose dataset comprises 4D radar tensors, LiDAR point clouds, and RGB images, and is collected for a total of 72k frames across 240 sequences with six different complexity-level actions. The 4D radar tensor provides raw spatio-temporal information, differentiating it from other radar point cloud-based datasets. We develop an annotation process using RGB images and LiDAR point clouds to accurately label 3D human skeletons. In addition, we propose HRRadarPose, the first single-stage architecture that extracts the high-resolution representation of 4D radar tensors in 3D space to aid human keypoint estimation. HRRadarPose outperforms previous radar-based HPE work on the RT-Pose benchmark. The overall HRRadarPose performance on the RT-Pose dataset, as reflected in a mean per joint position error (MPJPE) of 9.91cm, indicates the persistent challenges in achieving accurate HPE in complex real-world scenarios. RT-Pose is available at https://huggingface.co/datasets/uwipl/RT-Pose. △ Less

Submitted 18 July, 2024; originally announced July 2024.

Comments: ECCV 2024

STEVE Series: Step-by-Step Construction of Agent Systems in Minecraft

Authors: Zhonghan Zhao, Wenhao Chai, Xuan Wang, Ke Ma, Kewei Chen, Dongxu Guo, Tian Ye, Yanting Zhang, Hongwei Wang, Gaoang Wang

Abstract: Building an embodied agent system with a large language model (LLM) as its core is a promising direction. Due to the significant costs and uncontrollable factors associated with deploying and training such agents in the real world, we have decided to begin our exploration within the Minecraft environment. Our STEVE Series agents can complete basic tasks in a virtual environment and more challengin… ▽ More Building an embodied agent system with a large language model (LLM) as its core is a promising direction. Due to the significant costs and uncontrollable factors associated with deploying and training such agents in the real world, we have decided to begin our exploration within the Minecraft environment. Our STEVE Series agents can complete basic tasks in a virtual environment and more challenging tasks such as navigation and even creative tasks, with an efficiency far exceeding previous state-of-the-art methods by a factor of $2.5\times$ to $7.3\times$. We begin our exploration with a vanilla large language model, augmenting it with a vision encoder and an action codebase trained on our collected high-quality dataset STEVE-21K. Subsequently, we enhanced it with a Critic and memory to transform it into a complex system. Finally, we constructed a hierarchical multi-agent system. Our recent work explored how to prune the agent system through knowledge distillation. In the future, we will explore more potential applications of STEVE agents in the real world. △ Less

Submitted 17 June, 2024; originally announced June 2024.

Comments: CVPR 2024 Embodied AI Workshop

CityCraft: A Real Crafter for 3D City Generation

Authors: Jie Deng, Wenhao Chai, Junsheng Huang, Zhonghan Zhao, Qixuan Huang, Mingyan Gao, Jianshu Guo, Shengyu Hao, Wenhao Hu, Jenq-Neng Hwang, Xi Li, Gaoang Wang

Abstract: City scene generation has gained significant attention in autonomous driving, smart city development, and traffic simulation. It helps enhance infrastructure planning and monitoring solutions. Existing methods have employed a two-stage process involving city layout generation, typically using Variational Autoencoders (VAEs), Generative Adversarial Networks (GANs), or Transformers, followed by neur… ▽ More City scene generation has gained significant attention in autonomous driving, smart city development, and traffic simulation. It helps enhance infrastructure planning and monitoring solutions. Existing methods have employed a two-stage process involving city layout generation, typically using Variational Autoencoders (VAEs), Generative Adversarial Networks (GANs), or Transformers, followed by neural rendering. These techniques often exhibit limited diversity and noticeable artifacts in the rendered city scenes. The rendered scenes lack variety, resembling the training images, resulting in monotonous styles. Additionally, these methods lack planning capabilities, leading to less realistic generated scenes. In this paper, we introduce CityCraft, an innovative framework designed to enhance both the diversity and quality of urban scene generation. Our approach integrates three key stages: initially, a diffusion transformer (DiT) model is deployed to generate diverse and controllable 2D city layouts. Subsequently, a Large Language Model(LLM) is utilized to strategically make land-use plans within these layouts based on user prompts and language guidelines. Based on the generated layout and city plan, we utilize the asset retrieval module and Blender for precise asset placement and scene construction. Furthermore, we contribute two new datasets to the field: 1)CityCraft-OSM dataset including 2D semantic layouts of urban areas, corresponding satellite images, and detailed annotations. 2) CityCraft-Buildings dataset, featuring thousands of diverse, high-quality 3D building assets. CityCraft achieves state-of-the-art performance in generating realistic 3D cities. △ Less

Submitted 7 June, 2024; originally announced June 2024.

Comments: 20 pages, 9 figures

MovieChat+: Question-aware Sparse Memory for Long Video Question Answering

Authors: Enxin Song, Wenhao Chai, Tian Ye, Jenq-Neng Hwang, Xi Li, Gaoang Wang

Abstract: Recently, integrating video foundation models and large language models to build a video understanding system can overcome the limitations of specific pre-defined vision tasks. Yet, existing methods either employ complex spatial-temporal modules or rely heavily on additional perception models to extract temporal features for video understanding, and they only perform well on short videos. For long… ▽ More Recently, integrating video foundation models and large language models to build a video understanding system can overcome the limitations of specific pre-defined vision tasks. Yet, existing methods either employ complex spatial-temporal modules or rely heavily on additional perception models to extract temporal features for video understanding, and they only perform well on short videos. For long videos, the computational complexity and memory costs associated with long-term temporal connections are significantly increased, posing additional challenges.Taking advantage of the Atkinson-Shiffrin memory model, with tokens in Transformers being employed as the carriers of memory in combination with our specially designed memory mechanism, we propose MovieChat to overcome these challenges. We lift pre-trained multi-modal large language models for understanding long videos without incorporating additional trainable temporal modules, employing a zero-shot approach. MovieChat achieves state-of-the-art performance in long video understanding, along with the released MovieChat-1K benchmark with 1K long video, 2K temporal grounding labels, and 14K manual annotations for validation of the effectiveness of our method. The code along with the dataset can be accessed via the following https://github.com/rese1f/MovieChat. △ Less

Submitted 26 April, 2024; originally announced April 2024.

Expanding the Katz Index for Link Prediction: A Case Study on a Live Fish Movement Network

Authors: Michael-Sam Vidza, Marcin Budka, Wei Koong Chai, Mark Thrush, Mickael Teixeira Alves

Abstract: In aquaculture, disease spread models often neglect the dynamic interactions between farms, hindering accuracy. This study enhances the Katz index (KI) to incorporate spatial and temporal patterns of fish movement, improving the prediction of farms susceptible to disease via live fish transfers. We modified the Katz index to create models like the Weighted Katz Index (WKI), Edge Weighted Katz Inde… ▽ More In aquaculture, disease spread models often neglect the dynamic interactions between farms, hindering accuracy. This study enhances the Katz index (KI) to incorporate spatial and temporal patterns of fish movement, improving the prediction of farms susceptible to disease via live fish transfers. We modified the Katz index to create models like the Weighted Katz Index (WKI), Edge Weighted Katz Index (EWKI), and combined models (e.g., KIEWKI). These incorporate spatial distances and temporal movement patterns for a comprehensive aquaculture network connection prediction framework. Model performance was evaluated using precision, recall, F1-scores, AUPR, and AUROC. The EWKI model significantly outperformed the traditional KI and other variations. It achieved high precision (0.988), recall (0.712), F1-score (0.827), and AUPR (0.970). Combined models (KIEWKI, WKIEWKI) approached, but couldn't surpass, EWKI performance. This study highlights the value of extending Katz index models to improve disease spread predictions in aquaculture networks. The EWKI model's performance demonstrates an innovative and flexible approach to tackling spatial challenges within network analysis. △ Less

Submitted 19 April, 2024; originally announced April 2024.

Comments: 15 pages, 3 figures, submitted to Expert Systems with Applications

MonoTAKD: Teaching Assistant Knowledge Distillation for Monocular 3D Object Detection

Authors: Hou-I Liu, Christine Wu, Jen-Hao Cheng, Wenhao Chai, Shian-Yun Wang, Gaowen Liu, Hugo Latapie, Jhih-Ciang Wu, Jenq-Neng Hwang, Hong-Han Shuai, Wen-Huang Cheng

Abstract: Monocular 3D object detection (Mono3D) holds noteworthy promise for autonomous driving applications owing to the cost-effectiveness and rich visual context of monocular camera sensors. However, depth ambiguity poses a significant challenge, as it requires extracting precise 3D scene geometry from a single image, resulting in suboptimal performance when transferring knowledge from a LiDAR-based tea… ▽ More Monocular 3D object detection (Mono3D) holds noteworthy promise for autonomous driving applications owing to the cost-effectiveness and rich visual context of monocular camera sensors. However, depth ambiguity poses a significant challenge, as it requires extracting precise 3D scene geometry from a single image, resulting in suboptimal performance when transferring knowledge from a LiDAR-based teacher model to a camera-based student model. To facilitate effective distillation, we introduce Monocular Teaching Assistant Knowledge Distillation (MonoTAKD), which proposes a camera-based teaching assistant (TA) model to transfer robust 3D visual knowledge to the student model, leveraging the smaller feature representation gap. Additionally, we define 3D spatial cues as residual features that capture the differences between the teacher and the TA models. We then leverage these cues to improve the student model's 3D perception capabilities. Experimental results show that our MonoTAKD achieves state-of-the-art performance on the KITTI3D dataset. Furthermore, we evaluate the performance on nuScenes and KITTI raw datasets to demonstrate the generalization of our model to multi-view 3D and unsupervised data settings. Our code is available at https://github.com/hoiliu-0801/MonoTAKD. △ Less

Submitted 26 March, 2025; v1 submitted 7 April, 2024; originally announced April 2024.

Comments: Accepted by CVPR 2025. Our code is available at https://github.com/hoiliu-0801/MonoTAKD

Do We Really Need a Complex Agent System? Distill Embodied Agent into a Single Model

Authors: Zhonghan Zhao, Ke Ma, Wenhao Chai, Xuan Wang, Kewei Chen, Dongxu Guo, Yanting Zhang, Hongwei Wang, Gaoang Wang

Abstract: With the power of large language models (LLMs), open-ended embodied agents can flexibly understand human instructions, generate interpretable guidance strategies, and output executable actions. Nowadays, Multi-modal Language Models~(MLMs) integrate multi-modal signals into LLMs, further bringing richer perception to entity agents and allowing embodied agents to perceive world-understanding tasks m… ▽ More With the power of large language models (LLMs), open-ended embodied agents can flexibly understand human instructions, generate interpretable guidance strategies, and output executable actions. Nowadays, Multi-modal Language Models~(MLMs) integrate multi-modal signals into LLMs, further bringing richer perception to entity agents and allowing embodied agents to perceive world-understanding tasks more delicately. However, existing works: 1) operate independently by agents, each containing multiple LLMs, from perception to action, resulting in gaps between complex tasks and execution; 2) train MLMs on static data, struggling with dynamics in open-ended scenarios; 3) input prior knowledge directly as prompts, suppressing application flexibility. We propose STEVE-2, a hierarchical knowledge distillation framework for open-ended embodied tasks, characterized by 1) a hierarchical system for multi-granular task division, 2) a mirrored distillation method for parallel simulation data, and 3) an extra expert model for bringing additional knowledge into parallel simulation. After distillation, embodied agents can complete complex, open-ended tasks without additional expert guidance, utilizing the performance and knowledge of a versatile MLM. Extensive evaluations on navigation and creation tasks highlight the superior performance of STEVE-2 in open-ended tasks, with $1.4 \times$ - $7.3 \times$ in performance. △ Less

Submitted 6 April, 2024; originally announced April 2024.

Comments: arXiv admin note: text overlap with arXiv:2403.08282

VersaT2I: Improving Text-to-Image Models with Versatile Reward

Authors: Jianshu Guo, Wenhao Chai, Jie Deng, Hsiang-Wei Huang, Tian Ye, Yichen Xu, Jiawei Zhang, Jenq-Neng Hwang, Gaoang Wang

Abstract: Recent text-to-image (T2I) models have benefited from large-scale and high-quality data, demonstrating impressive performance. However, these T2I models still struggle to produce images that are aesthetically pleasing, geometrically accurate, faithful to text, and of good low-level quality. We present VersaT2I, a versatile training framework that can boost the performance with multiple rewards of… ▽ More Recent text-to-image (T2I) models have benefited from large-scale and high-quality data, demonstrating impressive performance. However, these T2I models still struggle to produce images that are aesthetically pleasing, geometrically accurate, faithful to text, and of good low-level quality. We present VersaT2I, a versatile training framework that can boost the performance with multiple rewards of any T2I model. We decompose the quality of the image into several aspects such as aesthetics, text-image alignment, geometry, low-level quality, etc. Then, for every quality aspect, we select high-quality images in this aspect generated by the model as the training set to finetune the T2I model using the Low-Rank Adaptation (LoRA). Furthermore, we introduce a gating function to combine multiple quality aspects, which can avoid conflicts between different quality aspects. Our method is easy to extend and does not require any manual annotation, reinforcement learning, or model architecture changes. Extensive experiments demonstrate that VersaT2I outperforms the baseline methods across various quality criteria. △ Less

Submitted 27 March, 2024; originally announced March 2024.

MambaMOT: State-Space Model as Motion Predictor for Multi-Object Tracking

Authors: Hsiang-Wei Huang, Cheng-Yen Yang, Wenhao Chai, Zhongyu Jiang, Jenq-Neng Hwang

Abstract: In the field of multi-object tracking (MOT), traditional methods often rely on the Kalman filter for motion prediction, leveraging its strengths in linear motion scenarios. However, the inherent limitations of these methods become evident when confronted with complex, nonlinear motions and occlusions prevalent in dynamic environments like sports and dance. This paper explores the possibilities of… ▽ More In the field of multi-object tracking (MOT), traditional methods often rely on the Kalman filter for motion prediction, leveraging its strengths in linear motion scenarios. However, the inherent limitations of these methods become evident when confronted with complex, nonlinear motions and occlusions prevalent in dynamic environments like sports and dance. This paper explores the possibilities of replacing the Kalman filter with a learning-based motion model that effectively enhances tracking accuracy and adaptability beyond the constraints of Kalman filter-based tracker. In this paper, our proposed method MambaMOT and MambaMOT+, demonstrate advanced performance on challenging MOT datasets such as DanceTrack and SportsMOT, showcasing their ability to handle intricate, non-linear motion patterns and frequent occlusions more effectively than traditional methods. △ Less

Submitted 20 January, 2025; v1 submitted 16 March, 2024; originally announced March 2024.

Comments: Accepted by ICASSP 2025. Previous version paper title: Exploring Learning-based Motion Models in Multi-Object Tracking

Hierarchical Auto-Organizing System for Open-Ended Multi-Agent Navigation

Authors: Zhonghan Zhao, Kewei Chen, Dongxu Guo, Wenhao Chai, Tian Ye, Yanting Zhang, Gaoang Wang

Abstract: Due to the dynamic and unpredictable open-world setting, navigating complex environments in Minecraft poses significant challenges for multi-agent systems. Agents must interact with the environment and coordinate their actions with other agents to achieve common objectives. However, traditional approaches often struggle to efficiently manage inter-agent communication and task distribution, crucial… ▽ More Due to the dynamic and unpredictable open-world setting, navigating complex environments in Minecraft poses significant challenges for multi-agent systems. Agents must interact with the environment and coordinate their actions with other agents to achieve common objectives. However, traditional approaches often struggle to efficiently manage inter-agent communication and task distribution, crucial for effective multi-agent navigation. Furthermore, processing and integrating multi-modal information (such as visual, textual, and auditory data) is essential for agents to comprehend their goals and navigate the environment successfully and fully. To address this issue, we design the HAS framework to auto-organize groups of LLM-based agents to complete navigation tasks. In our approach, we devise a hierarchical auto-organizing navigation system, which is characterized by 1) a hierarchical system for multi-agent organization, ensuring centralized planning and decentralized execution; 2) an auto-organizing and intra-communication mechanism, enabling dynamic group adjustment under subtasks; 3) a multi-modal information platform, facilitating multi-modal perception to perform the three navigation tasks with one system. To assess organizational behavior, we design a series of navigation tasks in the Minecraft environment, which includes searching and exploring. We aim to develop embodied organizations that push the boundaries of embodied AI, moving it towards a more human-like organizational structure. △ Less

Submitted 18 March, 2024; v1 submitted 13 March, 2024; originally announced March 2024.

Comments: ICLR 2024 Workshop on LLM Agents

Only My Model On My Data: A Privacy Preserving Approach Protecting one Model and Deceiving Unauthorized Black-Box Models

Authors: Weiheng Chai, Brian Testa, Huantao Ren, Asif Salekin, Senem Velipasalar

Abstract: Deep neural networks are extensively applied to real-world tasks, such as face recognition and medical image classification, where privacy and data protection are critical. Image data, if not protected, can be exploited to infer personal or contextual information. Existing privacy preservation methods, like encryption, generate perturbed images that are unrecognizable to even humans. Adversarial a… ▽ More Deep neural networks are extensively applied to real-world tasks, such as face recognition and medical image classification, where privacy and data protection are critical. Image data, if not protected, can be exploited to infer personal or contextual information. Existing privacy preservation methods, like encryption, generate perturbed images that are unrecognizable to even humans. Adversarial attack approaches prohibit automated inference even for authorized stakeholders, limiting practical incentives for commercial and widespread adaptation. This pioneering study tackles an unexplored practical privacy preservation use case by generating human-perceivable images that maintain accurate inference by an authorized model while evading other unauthorized black-box models of similar or dissimilar objectives, and addresses the previous research gaps. The datasets employed are ImageNet, for image classification, Celeba-HQ dataset, for identity classification, and AffectNet, for emotion classification. Our results show that the generated images can successfully maintain the accuracy of a protected model and degrade the average accuracy of the unauthorized black-box models to 11.97%, 6.63%, and 55.51% on ImageNet, Celeba-HQ, and AffectNet datasets, respectively. △ Less

Submitted 14 February, 2024; originally announced February 2024.

SpeedUpNet: A Plug-and-Play Adapter Network for Accelerating Text-to-Image Diffusion Models

Authors: Weilong Chai, DanDan Zheng, Jiajiong Cao, Zhiquan Chen, Changbao Wang, Chenguang Ma

Abstract: Text-to-image diffusion models (SD) exhibit significant advancements while requiring extensive computational resources. Existing acceleration methods usually require extensive training and are not universally applicable. LCM-LoRA, trainable once for diverse models, offers universality but rarely considers ensuring the consistency of generated content before and after acceleration. This paper propo… ▽ More Text-to-image diffusion models (SD) exhibit significant advancements while requiring extensive computational resources. Existing acceleration methods usually require extensive training and are not universally applicable. LCM-LoRA, trainable once for diverse models, offers universality but rarely considers ensuring the consistency of generated content before and after acceleration. This paper proposes SpeedUpNet (SUN), an innovative acceleration module, to address the challenges of universality and consistency. Exploiting the role of cross-attention layers in U-Net for SD models, we introduce an adapter specifically designed for these layers, quantifying the offset in image generation caused by negative prompts relative to positive prompts. This learned offset demonstrates stability across a range of models, enhancing SUN's universality. To improve output consistency, we propose a Multi-Step Consistency (MSC) loss, which stabilizes the offset and ensures fidelity in accelerated content. Experiments on SD v1.5 show that SUN leads to an overall speedup of more than 10 times compared to the baseline 25-step DPM-solver++, and offers two extra advantages: (1) training-free integration into various fine-tuned Stable-Diffusion models and (2) state-of-the-art FIDs of the generated data set before and after acceleration guided by random combinations of positive and negative prompts. Code is available: https://williechai.github.io/speedup-plugin-for-stable-diffusions.github.io. △ Less

Submitted 1 October, 2024; v1 submitted 13 December, 2023; originally announced December 2023.

Comments: Accepted to ECCV 2024

User-Aware Prefix-Tuning is a Good Learner for Personalized Image Captioning

Authors: Xuan Wang, Guanhong Wang, Wenhao Chai, Jiayu Zhou, Gaoang Wang

Abstract: Image captioning bridges the gap between vision and language by automatically generating natural language descriptions for images. Traditional image captioning methods often overlook the preferences and characteristics of users. Personalized image captioning solves this problem by incorporating user prior knowledge into the model, such as writing styles and preferred vocabularies. Most existing me… ▽ More Image captioning bridges the gap between vision and language by automatically generating natural language descriptions for images. Traditional image captioning methods often overlook the preferences and characteristics of users. Personalized image captioning solves this problem by incorporating user prior knowledge into the model, such as writing styles and preferred vocabularies. Most existing methods emphasize the user context fusion process by memory networks or transformers. However, these methods ignore the distinct domains of each dataset. Therefore, they need to update the entire caption model parameters when meeting new samples, which is time-consuming and calculation-intensive. To address this challenge, we propose a novel personalized image captioning framework that leverages user context to consider personality factors. Additionally, our framework utilizes the prefix-tuning paradigm to extract knowledge from a frozen large language model, reducing the gap between different language domains. Specifically, we employ CLIP to extract the visual features of an image and align the semantic space using a query-guided mapping network. By incorporating the transformer layer, we merge the visual features with the user's contextual prior knowledge to generate informative prefixes. Moreover, we employ GPT-2 as the frozen large language model. With a small number of parameters to be trained, our model performs efficiently and effectively. Our model outperforms existing baseline models on Instagram and YFCC100M datasets across five evaluation metrics, demonstrating its superiority, including twofold improvements in metrics such as BLEU-4 and CIDEr. △ Less

Submitted 20 December, 2024; v1 submitted 7 December, 2023; originally announced December 2023.

CityGen: Infinite and Controllable City Layout Generation

Authors: Jie Deng, Wenhao Chai, Jianshu Guo, Qixuan Huang, Junsheng Huang, Wenhao Hu, Shengyu Hao, Jenq-Neng Hwang, Gaoang Wang

Abstract: The recent surge in interest in city layout generation underscores its significance in urban planning and smart city development. The task involves procedurally or automatically generating spatial arrangements for urban elements such as roads, buildings, water, and vegetation. Previous methods, whether procedural modeling or deep learning-based approaches like VAEs and GANs, rely on complex priors… ▽ More The recent surge in interest in city layout generation underscores its significance in urban planning and smart city development. The task involves procedurally or automatically generating spatial arrangements for urban elements such as roads, buildings, water, and vegetation. Previous methods, whether procedural modeling or deep learning-based approaches like VAEs and GANs, rely on complex priors, expert guidance, or initial layouts, and often lack diversity and interactivity. In this paper, we present CityGen, an end-to-end framework for infinite, diverse, and controllable city layout generation. Our framework introduces an infinite expansion module to extend local layouts to city-scale layouts and a multi-scale refinement module to upsample and refine them. We also designed a user-friendly control scheme, allowing users to guide generation through simple sketching. Additionally, we convert the 2D layout to 3D by synthesizing a height field, facilitating downstream applications. Extensive experiments demonstrate CityGen's state-of-the-art performance across various metrics, making it suitable for a wide range of downstream applications. △ Less

Submitted 11 April, 2025; v1 submitted 3 December, 2023; originally announced December 2023.

Comments: Accepted to CVPR 2025 USM3D Workshop

UniHPE: Towards Unified Human Pose Estimation via Contrastive Learning

Authors: Zhongyu Jiang, Wenhao Chai, Lei Li, Zhuoran Zhou, Cheng-Yen Yang, Jenq-Neng Hwang

Abstract: In recent times, there has been a growing interest in developing effective perception techniques for combining information from multiple modalities. This involves aligning features obtained from diverse sources to enable more efficient training with larger datasets and constraints, as well as leveraging the wealth of information contained in each modality. 2D and 3D Human Pose Estimation (HPE) are… ▽ More In recent times, there has been a growing interest in developing effective perception techniques for combining information from multiple modalities. This involves aligning features obtained from diverse sources to enable more efficient training with larger datasets and constraints, as well as leveraging the wealth of information contained in each modality. 2D and 3D Human Pose Estimation (HPE) are two critical perceptual tasks in computer vision, which have numerous downstream applications, such as Action Recognition, Human-Computer Interaction, Object tracking, etc. Yet, there are limited instances where the correlation between Image and 2D/3D human pose has been clearly researched using a contrastive paradigm. In this paper, we propose UniHPE, a unified Human Pose Estimation pipeline, which aligns features from all three modalities, i.e., 2D human pose estimation, lifting-based and image-based 3D human pose estimation, in the same pipeline. To align more than two modalities at the same time, we propose a novel singular value based contrastive learning loss, which better aligns different modalities and further boosts the performance. In our evaluation, UniHPE achieves remarkable performance metrics: MPJPE $50.5$mm on the Human3.6M dataset and PAMPJPE $51.6$mm on the 3DPW dataset. Our proposed method holds immense potential to advance the field of computer vision and contribute to various applications. △ Less

Submitted 24 November, 2023; originally announced November 2023.

See and Think: Embodied Agent in Virtual Environment

Authors: Zhonghan Zhao, Wenhao Chai, Xuan Wang, Li Boyi, Shengyu Hao, Shidong Cao, Tian Ye, Gaoang Wang

Abstract: Large language models (LLMs) have achieved impressive pro-gress on several open-world tasks. Recently, using LLMs to build embodied agents has been a hotspot. This paper proposes STEVE, a comprehensive and visionary embodied agent in the Minecraft virtual environment. STEVE comprises three key components: vision perception, language instruction, and code action. Vision perception involves interpre… ▽ More Large language models (LLMs) have achieved impressive pro-gress on several open-world tasks. Recently, using LLMs to build embodied agents has been a hotspot. This paper proposes STEVE, a comprehensive and visionary embodied agent in the Minecraft virtual environment. STEVE comprises three key components: vision perception, language instruction, and code action. Vision perception involves interpreting visual information in the environment, which is then integrated into the LLMs component with agent state and task instruction. Language instruction is responsible for iterative reasoning and decomposing complex tasks into manageable guidelines. Code action generates executable skill actions based on retrieval in skill database, enabling the agent to interact effectively within the Minecraft environment. We also collect STEVE-21K dataset, which includes 600+ vision-environment pairs, 20K knowledge question-answering pairs, and 200+ skill-code pairs. We conduct continuous block search, knowledge question and answering, and tech tree mastery to evaluate the performance. Extensive experiments show that STEVE achieves at most 1.5x faster unlocking key tech trees and 2.5x quicker in block search tasks. △ Less

Submitted 9 July, 2024; v1 submitted 26 November, 2023; originally announced November 2023.

Comments: ECCV 2024. First three authors contribute equally to this work. Project Website https://rese1f.github.io/STEVE/

Efficient Domain Adaptation via Generative Prior for 3D Infant Pose Estimation

Authors: Zhuoran Zhou, Zhongyu Jiang, Wenhao Chai, Cheng-Yen Yang, Lei Li, Jenq-Neng Hwang

Abstract: Although 3D human pose estimation has gained impressive development in recent years, only a few works focus on infants, that have different bone lengths and also have limited data. Directly applying adult pose estimation models typically achieves low performance in the infant domain and suffers from out-of-distribution issues. Moreover, the limitation of infant pose data collection also heavily co… ▽ More Although 3D human pose estimation has gained impressive development in recent years, only a few works focus on infants, that have different bone lengths and also have limited data. Directly applying adult pose estimation models typically achieves low performance in the infant domain and suffers from out-of-distribution issues. Moreover, the limitation of infant pose data collection also heavily constrains the efficiency of learning-based models to lift 2D poses to 3D. To deal with the issues of small datasets, domain adaptation and data augmentation are commonly used techniques. Following this paradigm, we take advantage of an optimization-based method that utilizes generative priors to predict 3D infant keypoints from 2D keypoints without the need of large training data. We further apply a guided diffusion model to domain adapt 3D adult pose to infant pose to supplement small datasets. Besides, we also prove that our method, ZeDO-i, could attain efficient domain adaptation, even if only a small number of data is given. Quantitatively, we claim that our model attains state-of-the-art MPJPE performance of 43.6 mm on the SyRIP dataset and 21.2 mm on the MINI-RGBD dataset. △ Less

Submitted 17 November, 2023; originally announced November 2023.

Comments: WACVW 2024

Devil in the Number: Towards Robust Multi-modality Data Filter

Authors: Yichen Xu, Zihan Xu, Wenhao Chai, Zhonghan Zhao, Enxin Song, Gaoang Wang

Abstract: In order to appropriately filter multi-modality data sets on a web-scale, it becomes crucial to employ suitable filtering methods to boost performance and reduce training costs. For instance, LAION papers employs the CLIP score filter to select data with CLIP scores surpassing a certain threshold. On the other hand, T-MARS achieves high-quality data filtering by detecting and masking text within i… ▽ More In order to appropriately filter multi-modality data sets on a web-scale, it becomes crucial to employ suitable filtering methods to boost performance and reduce training costs. For instance, LAION papers employs the CLIP score filter to select data with CLIP scores surpassing a certain threshold. On the other hand, T-MARS achieves high-quality data filtering by detecting and masking text within images and then filtering by CLIP score. Through analyzing the dataset, we observe a significant proportion of redundant information, such as numbers, present in the textual content. Our experiments on a subset of the data unveil the profound impact of these redundant elements on the CLIP scores. A logical approach would involve reevaluating the CLIP scores after eliminating these influences. Experimentally, our text-based CLIP filter outperforms the top-ranked method on the ``small scale" of DataComp (a data filtering benchmark) on ImageNet distribution shifts, achieving a 3.6% performance improvement. The results also demonstrate that our proposed text-masked filter outperforms the original CLIP score filter when selecting the top 40% of the data. The impact of numbers on CLIP and their handling provide valuable insights for improving the effectiveness of CLIP training, including language rewrite techniques. △ Less

Submitted 24 September, 2023; originally announced September 2023.

Comments: ICCV 2023 Workshop: TNGCV-DataComp

Chasing Consistency in Text-to-3D Generation from a Single Image

Authors: Yichen Ouyang, Wenhao Chai, Jiayi Ye, Dapeng Tao, Yibing Zhan, Gaoang Wang

Abstract: Text-to-3D generation from a single-view image is a popular but challenging task in 3D vision. Although numerous methods have been proposed, existing works still suffer from the inconsistency issues, including 1) semantic inconsistency, 2) geometric inconsistency, and 3) saturation inconsistency, resulting in distorted, overfitted, and over-saturated generations. In light of the above issues, we p… ▽ More Text-to-3D generation from a single-view image is a popular but challenging task in 3D vision. Although numerous methods have been proposed, existing works still suffer from the inconsistency issues, including 1) semantic inconsistency, 2) geometric inconsistency, and 3) saturation inconsistency, resulting in distorted, overfitted, and over-saturated generations. In light of the above issues, we present Consist3D, a three-stage framework Chasing for semantic-, geometric-, and saturation-Consistent Text-to-3D generation from a single image, in which the first two stages aim to learn parameterized consistency tokens, and the last stage is for optimization. Specifically, the semantic encoding stage learns a token independent of views and estimations, promoting semantic consistency and robustness. Meanwhile, the geometric encoding stage learns another token with comprehensive geometry and reconstruction constraints under novel-view estimations, reducing overfitting and encouraging geometric consistency. Finally, the optimization stage benefits from the semantic and geometric tokens, allowing a low classifier-free guidance scale and therefore preventing oversaturation. Experimental results demonstrate that Consist3D produces more consistent, faithful, and photo-realistic 3D assets compared to previous state-of-the-art methods. Furthermore, Consist3D also allows background and object editing through text prompts. △ Less

Submitted 7 September, 2023; originally announced September 2023.

Comments: 9 pages, 11 figures

UniAP: Towards Universal Animal Perception in Vision via Few-shot Learning

Authors: Meiqi Sun, Zhonghan Zhao, Wenhao Chai, Hanjun Luo, Shidong Cao, Yanting Zhang, Jenq-Neng Hwang, Gaoang Wang

Abstract: Animal visual perception is an important technique for automatically monitoring animal health, understanding animal behaviors, and assisting animal-related research. However, it is challenging to design a deep learning-based perception model that can freely adapt to different animals across various perception tasks, due to the varying poses of a large diversity of animals, lacking data on rare spe… ▽ More Animal visual perception is an important technique for automatically monitoring animal health, understanding animal behaviors, and assisting animal-related research. However, it is challenging to design a deep learning-based perception model that can freely adapt to different animals across various perception tasks, due to the varying poses of a large diversity of animals, lacking data on rare species, and the semantic inconsistency of different tasks. We introduce UniAP, a novel Universal Animal Perception model that leverages few-shot learning to enable cross-species perception among various visual tasks. Our proposed model takes support images and labels as prompt guidance for a query image. Images and labels are processed through a Transformer-based encoder and a lightweight label encoder, respectively. Then a matching module is designed for aggregating information between prompt guidance and the query image, followed by a multi-head label decoder to generate outputs for various tasks. By capitalizing on the shared visual characteristics among different animals and tasks, UniAP enables the transfer of knowledge from well-studied species to those with limited labeled data or even unseen species. We demonstrate the effectiveness of UniAP through comprehensive experiments in pose estimation, segmentation, and classification tasks on diverse animal species, showcasing its ability to generalize and adapt to new classes with minimal labeled examples. △ Less

Submitted 19 August, 2023; originally announced August 2023.

PoSynDA: Multi-Hypothesis Pose Synthesis Domain Adaptation for Robust 3D Human Pose Estimation

Authors: Hanbing Liu, Jun-Yan He, Zhi-Qi Cheng, Wangmeng Xiang, Qize Yang, Wenhao Chai, Gaoang Wang, Xu Bao, Bin Luo, Yifeng Geng, Xuansong Xie

Abstract: Existing 3D human pose estimators face challenges in adapting to new datasets due to the lack of 2D-3D pose pairs in training sets. To overcome this issue, we propose \textit{Multi-Hypothesis \textbf{P}ose \textbf{Syn}thesis \textbf{D}omain \textbf{A}daptation} (\textbf{PoSynDA}) framework to bridge this data disparity gap in target domain. Typically, PoSynDA uses a diffusion-inspired structure to… ▽ More Existing 3D human pose estimators face challenges in adapting to new datasets due to the lack of 2D-3D pose pairs in training sets. To overcome this issue, we propose \textit{Multi-Hypothesis \textbf{P}ose \textbf{Syn}thesis \textbf{D}omain \textbf{A}daptation} (\textbf{PoSynDA}) framework to bridge this data disparity gap in target domain. Typically, PoSynDA uses a diffusion-inspired structure to simulate 3D pose distribution in the target domain. By incorporating a multi-hypothesis network, PoSynDA generates diverse pose hypotheses and aligns them with the target domain. To do this, it first utilizes target-specific source augmentation to obtain the target domain distribution data from the source domain by decoupling the scale and position parameters. The process is then further refined through the teacher-student paradigm and low-rank adaptation. With extensive comparison of benchmarks such as Human3.6M and MPI-INF-3DHP, PoSynDA demonstrates competitive performance, even comparable to the target-trained MixSTE model\cite{zhang2022mixste}. This work paves the way for the practical application of 3D human pose estimation in unseen domains. The code is available at https://github.com/hbing-l/PoSynDA. △ Less

Submitted 16 October, 2023; v1 submitted 18 August, 2023; originally announced August 2023.

Comments: Accepted to ACM Multimedia 2023; 10 pages, 4 figures, 8 tables; the code is at https://github.com/hbing-l/PoSynDA

StableVideo: Text-driven Consistency-aware Diffusion Video Editing

Authors: Wenhao Chai, Xun Guo, Gaoang Wang, Yan Lu

Abstract: Diffusion-based methods can generate realistic images and videos, but they struggle to edit existing objects in a video while preserving their appearance over time. This prevents diffusion models from being applied to natural video editing in practical scenarios. In this paper, we tackle this problem by introducing temporal dependency to existing text-driven diffusion models, which allows them to… ▽ More Diffusion-based methods can generate realistic images and videos, but they struggle to edit existing objects in a video while preserving their appearance over time. This prevents diffusion models from being applied to natural video editing in practical scenarios. In this paper, we tackle this problem by introducing temporal dependency to existing text-driven diffusion models, which allows them to generate consistent appearance for the edited objects. Specifically, we develop a novel inter-frame propagation mechanism for diffusion video editing, which leverages the concept of layered representations to propagate the appearance information from one frame to the next. We then build up a text-driven video editing framework based on this mechanism, namely StableVideo, which can achieve consistency-aware video editing. Extensive experiments demonstrate the strong editing capability of our approach. Compared with state-of-the-art video editing methods, our approach shows superior qualitative and quantitative results. Our code is available at \href{https://github.com/rese1f/StableVideo}{this https URL}. △ Less

Submitted 18 August, 2023; originally announced August 2023.

Comments: ICCV 2023

Mani-GPT: A Generative Model for Interactive Robotic Manipulation

Authors: Zhe Zhang, Wei Chai, Jiankun Wang

Abstract: In real-world scenarios, human dialogues are multi-round and diverse. Furthermore, human instructions can be unclear and human responses are unrestricted. Interactive robots face difficulties in understanding human intents and generating suitable strategies for assisting individuals through manipulation. In this article, we propose Mani-GPT, a Generative Pre-trained Transformer (GPT) for interacti… ▽ More In real-world scenarios, human dialogues are multi-round and diverse. Furthermore, human instructions can be unclear and human responses are unrestricted. Interactive robots face difficulties in understanding human intents and generating suitable strategies for assisting individuals through manipulation. In this article, we propose Mani-GPT, a Generative Pre-trained Transformer (GPT) for interactive robotic manipulation. The proposed model has the ability to understand the environment through object information, understand human intent through dialogues, generate natural language responses to human input, and generate appropriate manipulation plans to assist the human. This makes the human-robot interaction more natural and humanized. In our experiment, Mani-GPT outperforms existing algorithms with an accuracy of 84.6% in intent recognition and decision-making for actions. Furthermore, it demonstrates satisfying performance in real-world dialogue tests with users, achieving an average response accuracy of 70%. △ Less

Submitted 7 August, 2023; v1 submitted 3 August, 2023; originally announced August 2023.

Virtual Reality Based Robot Teleoperation via Human-Scene Interaction

Authors: Lingxiao Meng, Jiangshan Liu, Wei Chai, Jiankun Wang, Max Q. -H. Meng

Abstract: Robot teleoperation gains great success in various situations, including chemical pollution rescue, disaster relief, and long-distance manipulation. In this article, we propose a virtual reality (VR) based robot teleoperation system to achieve more efficient and natural interaction with humans in different scenes. A user-friendly VR interface is designed to help users interact with a desktop scene… ▽ More Robot teleoperation gains great success in various situations, including chemical pollution rescue, disaster relief, and long-distance manipulation. In this article, we propose a virtual reality (VR) based robot teleoperation system to achieve more efficient and natural interaction with humans in different scenes. A user-friendly VR interface is designed to help users interact with a desktop scene using their hands efficiently and intuitively. To improve user experience and reduce workload, we simulate the process in the physics engine to help build a preview of the scene after manipulation in the virtual scene before execution. We conduct experiments with different users and compare our system with a direct control method across several teleoperation tasks. The user study demonstrates that the proposed system enables users to perform operations more instinctively with a lighter mental workload. Users can perform pick-and-place and object-stacking tasks in a considerably short time, even for beginners. Our code is available at https://github.com/lingxiaomeng/VR_Teleoperation_Gen3. △ Less

Submitted 2 August, 2023; originally announced August 2023.

MovieChat: From Dense Token to Sparse Memory for Long Video Understanding

Authors: Enxin Song, Wenhao Chai, Guanhong Wang, Yucheng Zhang, Haoyang Zhou, Feiyang Wu, Haozhe Chi, Xun Guo, Tian Ye, Yanting Zhang, Yan Lu, Jenq-Neng Hwang, Gaoang Wang

Abstract: Recently, integrating video foundation models and large language models to build a video understanding system can overcome the limitations of specific pre-defined vision tasks. Yet, existing systems can only handle videos with very few frames. For long videos, the computation complexity, memory cost, and long-term temporal connection impose additional challenges. Taking advantage of the Atkinson-S… ▽ More Recently, integrating video foundation models and large language models to build a video understanding system can overcome the limitations of specific pre-defined vision tasks. Yet, existing systems can only handle videos with very few frames. For long videos, the computation complexity, memory cost, and long-term temporal connection impose additional challenges. Taking advantage of the Atkinson-Shiffrin memory model, with tokens in Transformers being employed as the carriers of memory in combination with our specially designed memory mechanism, we propose the MovieChat to overcome these challenges. MovieChat achieves state-of-the-art performance in long video understanding, along with the released MovieChat-1K benchmark with 1K long video and 14K manual annotations for validation of the effectiveness of our method. △ Less

Submitted 9 March, 2024; v1 submitted 31 July, 2023; originally announced July 2023.

Comments: CVPR 2024. First three authors contribute equally to this work. Project Website https://rese1f.github.io/MovieChat/