Stars
"RecGPT: A Foundation Model for Sequential Recommendation"
Open-source Multi-agent Poster Generation from Papers
Agent S: an open agentic framework that uses computers like a human
An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models
Perplexica is an AI-powered search engine. It is an Open source alternative to Perplexity AI
Scaling Computer-Use Grounding via UI Decomposition and Synthesis
Benchmark of complex, multimodal desktop-oriented tasks for advanced GUI-navigation AI agents
A python module to repair invalid JSON from LLMs
AlphaEdit: Null-Space Constrained Knowledge Editing for Language Models, ICLR 2025 (Outstanding Paper)
A curated collection of resources, tools, and frameworks for developing GUI Agents.
[Lumina Embodied AI Community] 具身智能技术指南 Embodied-AI-Guide
RoboVerse: Towards a Unified Platform, Dataset and Benchmark for Scalable and Generalizable Robot Learning
"LLM4Urban: Urban Computing in the Era of Large Language Models"
A GUI Agent application based on UI-TARS(Vision-Language Model) that allows you to control your computer using natural language.
A general framework for bridging LLMs and recommendation systems via reinforcement learning. https://arxiv.org/pdf/2503.24289
Agent-R1: Training Powerful LLM Agents with End-to-End Reinforcement Learning
"Graph Convolutions Enrich the Self-Attention in Transformers!" NeurIPS 2024
Official implementation for "A Simple LLM Framework for Long-Range Video Question-Answering"
"AI-Creator: Multi-Modal Agents for Video Production"
💡 VideoMind: A Chain-of-LoRA Agent for Long Video Reasoning
[Neurips 24' D&B] Official Dataloader and Evaluation Scripts for LongVideoBench.
Code and data for the paper "Iterative Label Refinement Matters More than Preference Optimization under Weak Supervision".