Metis is the memory foundation model series developed by Metis Group, MemTensor.

A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows

The agent that grows with you

An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of…

Infinity is a high-throughput, low-latency serving engine for text-embeddings, reranking models, clip, clap and colpali

Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen3.6, GPT-OSS, Llama, and more!

Large-scale text embedding model

A hyperparameter optimization framework

(ACL 2025 Main) A Comprehensive Benchmark for Code Information Retrieval.

A collection of AI Agents papers (Updated biweekly)

[COLM’25] DeepRetrieval — 🔥 Training Search Agent by RLVR with Retrieval Outcome

An open-source implementaion for fine-tuning Qwen-VL series by Alibaba Cloud.

LLaVE: Large Language and Vision Embedding Models with Hardness-Weighted Contrastive Learning

OmniGen: Unified Image Generation. https://arxiv.org/pdf/2409.11340

[ACL 2025 Oral] 🔥🔥 MegaPairs: Massive Data Synthesis for Universal Multimodal Retrieval

ABC: Achieving Better Control of Multimodal Embeddings using VLMs [TMLR2025]

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

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

Tevatron - Unified Document Retrieval Toolkit across Scale, Language, and Modality. Demo in SIGIR 2023, SIGIR 2025.

This repo contains the code for "VLM2Vec / MMEB" [ICLR 2025], "VLM2Vec-V2 / MMEB-V2" [TMLR 2026], and "MMEB-V3" [COLM 2026]

Ongoing research training transformer language models at scale, including: BERT & GPT-2

Train 🤗transformers with DeepSpeed: ZeRO-2, ZeRO-3

Example models using DeepSpeed

MultilingualSIFT: Multilingual Supervised Instruction Fine-tuning

Emu Series: Generative Multimodal Models from BAAI

O1 Replication Journey

FlagScale is a large model toolkit based on open-sourced projects.