Companion code for the global workspace interpretability paper

[ICLR 2026] Neuron-Aware Data Selection in Instruction Tuning for Large Language Models

A curated list of autonomous improvement loops, research agents, and autoresearch-style systems inspired by Karpathy's autoresearch.

NLPCC 2026 Share Task 6: The Second Shared Task on LLM-Generated Text Detection

📰 Must-read papers on KV Cache Compression (constantly updating 🤗).

WeChat-MCP: let Openclaw/Claude/ChatGPT and other AI assistants read and reply to WeChat for you

微信 macOS 聊天记录解密与分析工具 | Decrypt & analyze WeChat chat history on macOS via SQLCipher key extraction from process memory

Claude Code Channel plugin for WeChat — bridge WeChat messages into Claude Code sessions via the official ClawBot ilink API

Fully autonomous & self-evolving research from idea to paper. Chat an Idea. Get a Paper. 🦞

ICLR dataset

整理AI语音技术应用到潮州方言的各类工作

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

Code base for "Decoupling Content and Expression: Two-Dimensional Detection of AI-Generated Text"

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

[ACL 2026] Reasoning While Asking: Transforming Reasoning Large Language Models from Passive Solvers to Proactive Inquirers

[ACL 2026] Reasoning While Asking: Transforming Reasoning Large Language Models from Passive Solvers to Proactive Inquirers

Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models

The raw UserRL repo under construction

OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.

A Dataset for Multi-Turn Dialogue Reasoning

(ICML'25 Outstanding) CollabLLM: From Passive Responders to Active Collaborators

Training Sparse Autoencoders on Language Models

ParamMute: Suppressing Knowledge-Critical FFNs for Faithful Retrieval-Augmented Generation

A list of tools, papers and code related to Deepfake Detection.

[NeurIPS 2024 D&B] DetectRL: Benchmarking LLM-Generated Text Detection in Real-World Scenarios

[NeurIPS 2024] How do Large Language Models Handle Multilingualism?

A version of verl to support diverse tool use [TMLR 2026]

[ACMMM 2025] Official Code of DetectAnyLLM: Towards Generalizable and Robust Detection of Machine-Generated Text Across Domains and Models