Stars
ReviewEval: An Evaluation Framework for AI-Generated Reviews
The official code of "Thinking With Videos: Multimodal Tool-Augmented Reinforcement Learning for Long Video Reasoning"
Code and implementations for the paper "AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning" by Zhiheng Xi et al.
SE-Agent is a self-evolution framework for LLM Code agents. It enables trajectory-level evolution to exchange information across reasoning paths via Revision, Recombination, and Refinement, expandi…
Official implementation of "Decoupling Continual Semantic Segmentation". Novel framework separating class-aware detection from class-agnostic segmentation for effective continual learning.
[ECCV24] VISA: Reasoning Video Object Segmentation via Large Language Model
[AAAI 2026] GUI-G²: Gaussian Reward Modeling for GUI Grounding
📚 A collection of papers about Referring Image Segmentation.
Grid Adventure - Java RPG Game 🎮 Grid Adventure is a Java-based, console role-playing game (RPG) where players navigate a 2D grid, battle monsters, and strategize their way to victory.
🚇 Guangzhou Metro Route Planning System A route planning system for Guangzhou Metro Lines 1, 2, and 3, designed to compute the shortest route, minimum travel time, and least number of transfers bet…
[EMNLP 2025] WebAgent-R1: Training Web Agents via End-to-End Multi-Turn Reinforcement Learning
verl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is also the official code for paper "Group-in-Group Policy Optimization for LLM Agent Training"
RAGEN leverages reinforcement learning to train LLM reasoning agents in interactive, stochastic environments.
S2A-Attention for Multimodal 3D SemanticSegmentation Using LiDAR and Cameras inAutonomous Driving
Personalized Fragrance Recommendation for Aromatherapy: A Machine Learning Approach Based on Personality Traits and Electrodermal Activity
Flash Attention 2 pre-built wheels for Windows. Drop-in replacement for PyTorch attention providing up to 10x speedup and 20x memory reduction. Compatible with Python 3.10 and CUDA 11.7+. No build …
A smart system for real-time knee health monitoring, featuring a HarmonyOS app for visualized data, doctor-patient communication, and personalized joint care.
An AI-powered intelligent learning platform that delivers personalized questioning, automated grading, adaptive learning paths, and community-driven support for enhanced student engagement and unde…
Self-Alignment with Principle-Following Reward Models
A Survey of Direct Preference Optimization (DPO)