Senyu Fei(SII)

le-wm. Official code base for LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels

vjepa2. PyTorch code and models for VJEPA2 self-supervised learning from video.

Thinking-with-Video. We introduce 'Thinking with Video', a new paradigm leveraging video generation for multimodal reasoning. Our VideoThinkBench shows that Sora-2 surpasses GPT5 by 10% on eyeballing puzzles and reaches 69% accuracy on MMMU.

MOSS-TTS. MOSS‑TTS Family is an open‑source speech and sound generation model family from MOSI.AI and the OpenMOSS team. It is designed for high‑fidelity, high‑expressiveness, and complex real‑world scenarios, covering stable long‑form speech, multi‑speaker dialogue, voice/character design, environmental sound effects, and real‑time streaming TTS.

RLinf. RLinf: Reinforcement Learning Infrastructure for Embodied and Agentic AI

LIBERO-plus. Official repository of LIBERO-plus, a generalized benchmark for in-depth robustness analysis of vision-language-action models.

hwid-changer. HWID Spoofer securely modifies hardware IDs to bypass bans in games.

fullyexternal-cs2. FullyExternalCS2 is a cutting-edge external cheat for Counter-Strike 2, designed to enhance your gaming experience without altering game memory. This tool offers a suite of advanced features, including AimBot, Esp, and Trigger Bot, to give you a competitive edge. Compatible with the latest game updates, it ensures seamless performance and VAC safet

binance-futures-grid-bot. Binance Futures Grid Bot for automated trading, profit optimization, and passive income.

ledger-live-staking-bot. Ledger Live Staking Bot automates crypto staking and rewards, supports multiple coins

fisch-script. Roblox Fisch Script 2025 offers stable, customizable automation for Roblox developers.

minecraft-account-checker. Easily and securely verify multiple Minecraft accounts

LIBERO-plus. Official repository of LIBERO-plus, a generalized benchmark for in-depth robustness analysis of vision-language-action models.

RoboOmni. Official code of "RoboOmni: Proactive Robot Manipulation in Omni-modal Context"

ImageBind. ImageBind One Embedding Space to Bind Them All

siiRL. siiRL: Shanghai Innovation Institute RL Framework for Advanced LLMs and Multi-Agent Systems

libero2lerobot. 支持自动识别RLDS和HDF5格式，自动解析成LeRobotDataSet格式，支持多线程操作

World-Aware-Planning. Python