Thinking with Videos from Open-Source Priors. We reproduce chain-of-frames visual reasoning by fine-tuning open-source video models. Give it a star 🌟 if you find it useful.

The best ChatGPT that $100 can buy.

Compile Cargo project with zig as linker

A novel data compression framework

[CVPR 2025 (Highlight)] ImViD: Immersive Volumetric Videos for Enhanced VR Engagement

Trace Anything: Representing Any Video in 4D via Trajectory Fields

Code for "FlashWorld: High-quality 3D Scene Generation within Seconds"

Video readers, writers, muxers, encoders and decoders for Rust based on ffmpeg libraries.

Cell2Sentence: Teaching Large Language Models the Language of Biology

ROSA+: RWKV's ROSA implementation with fallback statistical predictor

ROSA-Tuning

SoTA Approach for ARC-AGI 2

[SIGGRAPHASIA2025] InfiniHuman: Infinite 3D Human Creation with Precise Control

A comprehensive JAX/NNX library for diffusion and flow matching generative algorithms, featuring DiT (Diffusion Transformer) and its variants as the primary backbone with support for ImageNet train…

Official PyTorch Implementation of "Diffusion Transformers with Representation Autoencoders"

Reasoning Computers. Lambda Calculus, Fully Differentiable. Also Neural Stacks, Queues, Arrays, Lists, Trees, and Latches.

Integration for Steam Audio in Bevy

[ArXiv 25] Stable Video Infinity: Infinite-Length Video Generation with Error Recycling

StreamingVLM: Real-Time Understanding for Infinite Video Streams

The official implement of VITA, VITA15, LongVITA, VITA-Audio, VITA-VLA, and VITA-E.

Thinking with Camera: A Unified Multimodal Model for Camera-Centric Understanding and Generation

MOPA laser settings to make colorful oxide layers on stainless steel

[SIGGRAPH Asia 2025] 4DSloMo: 4D Reconstruction for High Speed Scene with Asynchronous Capture

Realtime path tracing via WebGPU compute shaders

ripgrep recursively searches directories for a regex pattern while respecting your gitignore

Machine settings, photos of material test swatches, and code to generate diffraction patterns on stainless steel with a MOPA fiber laser

Lynx: Towards High-Fidelity Personalized Video Generation

[SIGGRAPH Asia'25] Differentiable Light Transport with Gaussian Surfels via Adapted Radiosity for Efficient Relighting and Geometry Reconstruction

[NeurIPS 2025] Pixel-Perfect Depth