让每一次引用都成为可解释的影响力 Turning Every Citation into Explainable Impact

The repo is finally unlocked. enjoy the party! The fastest repo in history to surpass 100K stars ⭐. Join Discord: https://discord.gg/5TUQKqFWd Built in Rust using oh-my-codex.

将冰冷的离别化为温暖的 Skill，欢迎加入数字生命1.0！Transforming cold farewells into warm skills? It's giving rebirth era. Welcome to Digital Life 1.0. 🫶

ClaudeCode related repository

The official repo of EurekaClaw

The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search

Bridge local AI coding agents (Claude Code, Cursor, Gemini CLI, Codex) to messaging platforms (Feishu/Lark, DingTalk, Slack, Telegram, Discord, LINE, WeChat Work). Chat with your AI dev assistant f…

This is the official implementation of our paper "SpecEyes: Accelerating Agentic Multimodal LLMs via Speculative Perception and Planning"

A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows

[ICLR/AAAI 2026] Open-Source LLM-Based Data Analysis Agents

A curated list of autonomous research systems and tools.

Official Repository of "Learning to Reason under Off-Policy Guidance"

Official repo of "Chain-of-Visual-Thought: Teaching VLMs to See and Think Better with Continuous Visual Tokens"

SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning

[CVPR 2026] Group Editing: This repo is the official implementation of "Group Editing: Edit Multiple Images in One Go"

A framework for few-shot evaluation of language models.

[CVPR2026] The repo of paper "The Blind Spot of Adaptation: Quantifying and Mitigating Forgetting in Fine-tuned Driving Models"

MiroThinker is a deep research agent optimized for complex research and prediction tasks. Our latest models, MiroThinker-1.7 and MiroThinker-H1, achieve 74.0 and 88.2 on the BrowseComp, respectively.

OpenClaw-RL: Train any agent simply by talking

ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works…

Official repository of "Reliable Reasoning in SVG-LLMs via Multi-Task Multi-Reward Reinforcement Learning".

Autoresearch for GPU kernels. Give it any PyTorch model, go to sleep, wake up to optimized Triton kernels.

One-for-All Multimodal Evaluation Toolkit Across Text, Image, Video, and Audio Tasks

AI agents running research on single-GPU nanochat training automatically

🔥 LeetCode for PyTorch — practice implementing softmax, attention, GPT-2 and more from scratch with instant auto-grading. Jupyter-based, self-hosted or try online.