Maryam's Theorem: Generalized Cauchy's Surface Area Formula for Non-Convex Surfaces

A modular library for visual 4D scene understanding

[ICCV'25] 3D-MOOD: Lifting 2D to 3D for Monocular Open-Set Object Detection

Depth Anything 3

FlowFeat: Pixel-Dense Embedding of Motion Profiles (NeurIPS 2025 Spotlight)

Cloud-native search engine for observability. An open-source alternative to Datadog, Elasticsearch, Loki, and Tempo.

Official Repo for Rolling Forcing: Autoregressive Long Video Diffusion in Real Time

LCC data format white paper

Official PyTorch implementation of SegFormer

FlashRNN - Fast RNN Kernels with I/O Awareness

Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

Generalizable Perception Stack for all things 3D, 4D & Scene Understanding

Synthesizer, Sampler, Granulizer written in Rust with Nih-Plug and egui

Binary installation for rust projects

An AI agent system for solving International Mathematical Olympiad (IMO) problems using Google's Gemini, OpenAI, and XAI APIs.

Base docker image used in Codex environments

MotionStream: Real-Time Video Generation with Interactive Motion Controls

Cambrian-S: Towards Spatial Supersensing in Video

Anny, A Free and Interpretable Human Body Model for all ages, written in PyTorch.

Sonoluminescence LENR Project

An unofficial and simplified implementation of SIGGRAPH 2025 best paper nominate: CAST: Component-Aligned 3D Scene Reconstruction from an RGB Image, working in progress

burn depth pro model inference🔥📐😎

The absolute trainer to light up AI agents.

ChronoEdit: Towards Temporal Reasoning for Image Editing and World Simulation

Are Video Models Ready as Zero-shot Reasoners?

Omicron: Oxide control plane

Thermodynamic Hypergraphical Model Library in JAX

Native Multimodal Models are World Learners