The official PyTorch Implementation of Charm: The Missing Piece in ViT fine-tuning for Image Aesthetic Assessment

A comprehensive collection of IQA papers

Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.

Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

Search Self-Play: Pushing the Frontier of Agent Capability without Supervision

Tongyi Deep Research, the Leading Open-source Deep Research Agent

Repo for preprint paper - Understanding Generalization of Federated Learning: the Trade-off between Model Stability and Optimization

🔥🔥🔥 [IEEE TCSVT] Latest Papers, Codes and Datasets on Vid-LLMs.

This is a public repository for Image Clustering Conditioned on Text Criteria (IC|TC)

The implementation for the work "Unconstrained Monotonic Calibration of Predictions in Deep Ranking Systems".

[CVPR 2025] LamRA: Large Multimodal Model as Your Advanced Retrieval Assistant

ICLR 2021, Contrastive Learning with Hard Negative Samples

The official repo of Pai-Megatron-Patch for LLM & VLM large scale training developed by Alibaba Cloud.

Code for 'LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders'

This repo contains the code for "VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding Tasks" [ICLR 2025]

The development and future prospects of large multimodal reasoning models.

Muon is an optimizer for hidden layers in neural networks

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

[TMLR 2025] Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models

Search-R1: An Efficient, Scalable RL Training Framework for Reasoning & Search Engine Calling interleaved LLM based on veRL

Codebase for Paper Reusing Embeddings: Reproducible Reward Model Research in Large Language Model Alignment without GPUs

A programming framework for agentic AI

An open protocol enabling communication and interoperability between opaque agentic applications.

InfiAgent-DABench: Evaluating Agents on Data Analysis Tasks (ICML 2024)

Plug in and Play Implementation of Tree of Thoughts: Deliberate Problem Solving with Large Language Models that Elevates Model Reasoning by atleast 70%

No fortress, purely open ground. OpenManus is Coming.

Code for Paper: Training Software Engineering Agents and Verifiers with SWE-Gym [ICML 2025]

Playwright MCP server