Stars
A modern, cross-platform client for the Agent Client Protocol (ACP) on desktop, mobile, and the web — connect to any ACP-compatible AI agent (Claude, Codex, Copilot, Qwen, Gemini, OpenCode, OpenCla…
Finalist solution for the 2025 Tencent Advertising Algorithm Competition (Generative Recommendation Challenge)
Turn GitHub Copilot into OpenAI/Anthropic API compatible server. Usable with Claude Code!
an OpenClaw skill that can generate paper search-review-critque expert-agent relevant to specific topics (we use Scientific ML and 3D geometry surrogate modeling as a demo).
GenRec: Generative Recommender Systems with RQ-VAE semantic IDs, Transformer-based retrieval, and LLM integration. Built on PyTorch with distributed training support.
[ICCV 2025] Factorized Learning for Temporally Grounded Video-Language Models
[AAAI 2026] SlideTailor: Personalized Presentation Slide Generation for Scientific Papers
An Open Foundation Model and Benchmark to Accelerate Generative Recommendation
[TPAMI 2026] Code for paper "3D Hand Pose Estimation via Articulated Anchor-to-Joint 3D Local Regressors"
"AI-Trader: 100% Fully-Automated Agent-Native Trading"
[NeurIPS 2025] Deep Memory Backtracking for Long Video Understanding
[NeurIPS2025] ReID5o: Achieving Omni Multi-modal Person Re-identification in a Single Model
HIT Model: A Hierarchical Interaction-Enhanced Two-Tower Model for Pre-Ranking Systems
Fast and memory-efficient exact attention
EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL
verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework
This repository contains the official implementation of "FastVLM: Efficient Vision Encoding for Vision Language Models" - CVPR 2025
[ICLR2026] This is the first paper to explore how to effectively use R1-like RL for MLLMs and introduce Vision-R1, a reasoning MLLM that leverages cold-start initialization and RL training to incen…
本项目旨在分享大模型相关技术原理以及实战经验（大模型工程化、大模型应用落地）
Awesome-LLM: a curated list of Large Language Model
LLM大模型（重点）以及搜广推等 AI 算法中手写的面试题，（非 LeetCode），比如 Self-Attention, AUC等，一般比 LeetCode 更考察一个人的综合能力，又更贴近业务和基础知识一点
【三年面试五年模拟】AIGC/LLM/AI Agent算法工程师面试秘籍。涵盖AIGC、LLM大模型、AI Agent、传统深度学习、自动驾驶、机器学习、计算机视觉、自然语言处理、强化学习、大数据挖掘、具身智能、元宇宙、AGI等AI行业面试笔试干货经验与核心知识。
Data preparation and loader for AMASS
Official Code for ECCV 2024 paper "EgoPoser: Robust Real-Time Egocentric Pose Estimation from Sparse and Intermittent Observations Everywhere"
“FlowAR: Scale-wise Autoregressive Image Generation Meets Flow Matching” FlowAR employs a simplest scale design and is compatible with any VAE.
Official Implementation of the Paper: Ego-Body Pose Estimation via Ego-Head Pose Estimation (CVPR 2023 Award Candidate)