Lists (9)
Sort Name ascending (A-Z)
Stars
BVB: Benchmarking Agentic Video Understanding via Programmatic Reconstruction in Blender
Benchmarking Coding Agents for Interactive World Modeling from Embodied Videos - Rethinking Embodied Real2Sim from a Software Engineering Perspective
OpenWorld RPG: a pixel-art open-world RPG in the browser, with the engine and editor it is built on. The world's rules are data; a language model can add new ones at runtime.
This is the official repo for paper InteractiveWorld A Verifiable Human-Centric Environment for Building Better Interactive MLLM Assistants
RSI Bench is an ongoing effort to evaluate whether AI agents can develop the capabilities required to advance AI R&D.
[NeurIPS'25] KVCOMM: Online Cross-context KV-cache Communication for Efficient LLM-based Multi-agent Systems
Official Code for OpenVLHarness: Real-World Visual Agentic Tool‑Use with Multimodal Memory
Multi-Joint dynamics with Contact. A general purpose physics simulator.
SuperDex brings together a purpose-built physics engine, robotics authoring tools, and a scalable reinforcement learning interface in a unified simulation platform, with VR-based teleoperation and …
Project page of paper "Soft Rasterizer: A Differentiable Renderer for Image-based 3D Reasoning"
[CoRL 2026] World-Language-Action Model for Unified World Modeling, Language Reasoning, and Action Synthesis
Schema: Discovering Unknown Environments via Agentic Program Induction
Reverse engineer anything with agents, from app behavior down to native binaries.
humanizer, but for code — an agent skill that removes AI-generated code slop: duplicated helpers, try-import fallbacks, broad excepts, speculative abstractions. Test-gated, behavior-preserving.
A Python library for running thousands of MuJoCo simulations in parallel on CPU
Official implementation of "Hierarchical Continuous Diffusion Language Models"
Learning Native Reflection in Unified Models: reflection SFT and multi-round Flow-GRPO RL for BAGEL
Project page for OmniTaskonomy: When Does Visual Generation Improve Visual Understanding
A simulation benchmarking platform for evaluating generalist robot policies
GigaBrain-0: A World Model-Powered Vision-Language-Action Model
An Open-source RL System from ByteDance Seed and Tsinghua AIR