-
Fudan University
- Fudan University, Shanghai
- https://yjyddq.github.io/
- https://scholar.google.com/citations?user=3NSeUiwAAAAJ&hl=zh-CN
Highlights
- Pro
Stars
Open, Jev-compatible System One decision server on DiffusionGemma
Jev-like family of decision models built on top of Qwen3.5/3.8 you can train and run on your own
A nano replica of Jev: parallel decisions, dynamic candidates, and an end-to-end training pipeline.
Non-autoregressive System 1 decision engine. Typed choice, score and yes/no decisions over any text in a single forward pass, in 100+ languages, with a router that picks the right checkpoint per re…
Agenticly track ccf-ranked & worldwide conference deadlines (Website, Python Cli, Wechat Applet)
This is a curated list of "Embodied AI or robot with Large Language Models" research. Watch this repository for the latest updates! 🔥
News: We add many jev+robot in infrastructure. A curated collection of papers and resources on robot-use agents, tool-based robot control, embodied agent runtimes, and self-evolving robotic systems.
Sub2API 一站式开源中转服务,让 Claude、Openai 、Gemini、Grok订阅统一接入,支持拼车共享,更高效分摊成本,原生工具无缝使用。
An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.
LLaDA2.0 is the diffusion language model series developed by InclusionAI team, Ant Group.
Programmable datacenter-scale infrastructure for Agents.
A powerful tool for creating datasets for LLM fine-tuning 、RAG and Eval
[Lumina具身智能社区] 具身智能技术指南 Embodied-AI-Guide
GPT-Image-2 PPT Generator Skill for Creating Image-Based PowerPoint Presentations in Codex and Other Skill-Compatible Agents
专注于绚丽的歌词动画效果的本地音乐/navidrome/第三方多平台在线音乐播放器 A multi-platform music player for local files, Navidrome, and online streaming services, featuring stunning animated lyrics.
LLM 驱动的多市场股票智能分析系统:多源行情、实时新闻、决策看板与自动推送,支持零成本定时运行。 LLM-powered multi-market stock analysis system with multi-source market data, real-time news, decision dashboard, automated notifications, and cost…
OSWorld 2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks
Official Repository for "Glyph: Scaling Context Windows via Visual-Text Compression"
Benchmark for proactive personal assistant agents in long-horizon workflows.
ToolCUA: Towards Optimal GUI-Tool Path Orchestration for Computer Use Agents
A benchmark for LLMs on complicated tasks in the terminal
[ICLR 2026] On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification.
[TMLR] Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe
👾 Open Computer Use – Open-Source Alternative to Codex Computer Use