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 repo for [ICML 2026] "Any2Any: Unified Arbitrary Modality Translation for Remote Sensing"

[EMNLP 2025] Official code for the paper "SafeKey: Amplifying Aha-Moment Insights for Safety Reasoning"

RAGEN leverages reinforcement learning to train LLM reasoning agents in interactive, stochastic environments.

This repository provides the official code release accompanying Red Teaming Large Reasoning Models.

SafeVerse: A Generative Evolution Arena for Trustworthy Embodied AI

Edit Banana: A framework for converting statistical formats into editable.

Worlds first open-source real-time end-to-end spoken dialogue model with personalized voice cloning.

RLinf: Reinforcement Learning Infrastructure for Embodied and Agentic AI

Team Comet's 2025 BEHAVIOR Challenge Codebase

Team Comet's 2025 BEHAVIOR Challenge Codebase

The paper list of "Memory in the Age of AI Agents: A Survey"

A Survey on Reinforcement Learning of Vision-Language-Action Models for Robotic Manipulation

🌐 Permanent Hosting Site: http://ai-paper-finder.info/ 🌐 Hugging Face Hosting: https://huggingface.co/spaces/wenhanacademia/ai-paper-finder

A Benchmark for Low-Level Manipulation in Home Rearrangement Tasks

This is the homepage of a new book entitled "Mathematical Foundations of Reinforcement Learning."

https://arxiv.org/pdf/2506.06677

🤖 RoboOS: A Universal Embodied Operating System for Cross-Embodied and Multi-Robot Collaboration

The official implementation of the paper "Mem-α: Learning Memory Construction via Reinforcement Learning"

[CVPR 2026 Fingdings] This repo is the official implementation of "Euclid’s Gift: Enhancing Spatial Perception and Reasoning in Vision‑Language Models via Geometric Surrogate Tasks"

Implementation for the paper "CoMAS: Co-Evolving Multi-Agent Systems via Interaction Rewards".

SAM with text prompt