Skip to content
View dazazh's full-sized avatar
  • Shanghai Jiao Tong University

Block or report dazazh

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Showing results

Towards a Generative 3D World Engine for Embodied Intelligence

Python 721 43 Updated Aug 24, 2026

A HUD for Claude Code, Codex and 25 more coding agents. Know your quotas, tokens and sessions at a glance, answer requests and jump back in one click. On Mac, Windows and Linux, your phone and your…

Rust 526 78 Updated Nov 15, 2026

Reverse engineer anything with agents, from app behavior down to native binaries.

TypeScript 462,194 113,185 Updated Nov 16, 2026

A Unified Robot-Use Agent Harness Across Environments

Python 414 36 Updated Nov 15, 2026

RAX harness: coding agents that learn robot tasks by online exploration

349 25 Updated Oct 24, 2026

An autonomous agent that profiles, optimizes, and validates AI training code.

Python 318 15 Updated Nov 12, 2026

[ECCV 2026] Official Pytorch Code of the Paper "WorldWander: Bridging Egocentric and Exocentric Worlds in Video Generation"

Python 45 4 Updated Oct 7, 2026

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence

Python 984 46 Updated Sep 17, 2026

JoyAI-Echo-1.5: Long-Horizon Audio-Visual Generation for Persistent Stories and Interactive Worlds

Python 2,071 173 Updated Nov 4, 2026

Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.

JavaScript 191,518 10,723 Updated Oct 29, 2026

HunyuanVideo: A Systematic Framework For Large Video Generation Model

Python 12,776 1,388 Updated Oct 8, 2026

StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developing

Python 3,945 522 Updated Oct 31, 2026
Python 80 8 Updated Nov 10, 2026

[CoRL 2026] Code for "FACT: Failure-Aware Causal Training for World‑Action Models"

Python 109 6 Updated Sep 15, 2026

A unified framework for easy fine-tuning in Flow-Matching models

Python 752 63 Updated Nov 13, 2026
Python 11,915 881 Updated Oct 28, 2026

Ongoing research training transformer models at scale

Python 18,410 4,736 Updated Nov 16, 2026

[ECCV 2026 Best Paper Award Candidate] LingBot-Map: Geometric Context Transformer for Streaming 3D Reconstruction

Python 18,641 1,982 Updated Oct 14, 2026

[CVPR 2026 Oral] VGGT Omega

Python 4,763 377 Updated Sep 22, 2026

ViGeo: Towards Consistent Video Geometry Estimation

Python 143 6 Updated Oct 15, 2026

[NIPS 2026 Reviewed (6/5/4)] PhysisForcing: Physics Reinforced World Simulator for Robotic Manipulation

Python 138 2 Updated Sep 8, 2026

[CVPR 2026 Oral] PAI-Bench: A Comprehensive Benchmark for Physical AI

Python 108 9 Updated Jun 23, 2026

AHA-WAM:Asynchronous Horizon-Adaptive World-Action Modeling with Observation-Guided Context Routing

Python 116 9 Updated Jul 24, 2026
Python 194 37 Updated Sep 7, 2026

中国专利.skill:专利点挖掘与交底书(发明/实用/外观)编写,通俗解读专利,嗅探政策动向,辅助审查答复。

Python 13,477 1,456 Updated Nov 15, 2026

NVIDIA Cosmos is an open platform of world models, datasets, and tools that enables developers to build Physical AI for robots, autonomous vehicles, smart infrastructure, and more.

12,371 964 Updated Nov 11, 2026

Our inference and training framework to run on the Cosmos Models

Python 642 211 Updated Nov 16, 2026

[CoRL 2026] ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing?

Python 191 12 Updated Jul 30, 2026
Next