[ICLR 2026] Youtu-GraphRAG: Vertically Unified Agents for Graph Retrieval-Augmented Complex Reasoning

[SIGIR'25] Revolutionizing Text-to-Image Retrieval as Autoregressive Token-to-Voken Generation.

Code for MME-SID accepted to CIKM 2025 Full Research track.

GenRec: Generative Recommender Systems with RQ-VAE semantic IDs, Transformer-based retrieval, and LLM integration. Built on PyTorch with distributed training support.

The first Interleaved framework for textual reasoning within the visual generation process

Make one prompt become an immersive, production‑ready experience: a single pipeline for Text → Image → Music → Lights → Video, with real Philips Hue / WLED control.把“一个想法”变成“可看、可听、可控”的沉浸式体验：一条流水线完成…

A curated list of papers on reinforcement learning for video generation

Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen2.5, Qwen3, Llama, and more!

[TMLR] LLM-Powered GUI Agents in Phone Automation: Surveying Progress and Prospects

[TMLR 2026] Survey: https://arxiv.org/pdf/2507.20198

😎 A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, Agent, and Beyond

Easy Data Preparation with latest LLMs-based Operators and Pipelines.

Awesome Deep Research list! For more details, please refer to our survey paper -- A Comprehensive Survey of Deep Research: Systems, Methodologies, and Applications

Awesome List for Agentic RL

Build production-ready LLM applications and advanced agents using Python, LangChain, and LangGraph. This is the companion repository for the book on generative AI with LangChain.

Open Source Deep Research Alternative to Reason and Search on Private Data. Written in Python.

Lightning-Fast RL for LLM Reasoning and Agents. Made Simple & Flexible.

📚 Collection of token-level model compression resources.

This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. RAG systems combine information retrieval with generative models to provide accurate and cont…

Official repo for paper ConvSearch-R1

Train your Agent model via our easy and efficient framework

Embodied Chain of Thought: A robotic policy that reason to solve the task.

This is a curated list of "Embodied AI or robot with Large Language Models" research. Watch this repository for the latest updates! 🔥

Research Code for "ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL"

[ArXiv 2025] A survey about controllable video generation: This repo is the official awesome of "Controllable video generation: A survey"

一个简单的多模态RAG项目