InternLM

LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

Official release of InternLM series (InternLM, InternLM2, InternLM2.5, InternLM3).

🔍 An LLM-based Multi-agent Framework of Web Search Engine (like Perplexity.ai Pro and SearchGPT)

A Next-Generation Training Engine Built for Ultra-Large MoE Models

InternLM-XComposer2.5-OmniLive: A Comprehensive Multimodal System for Long-term Streaming Video and Audio Interactions

HuixiangDou: Overcoming Group Chat Scenarios with LLM-based Technical Assistance

A lightweight framework for building LLM-based agents

LLM&VLM Tutorial

A Scientific Multimodal Foundation Model

Fast multi-modal decision model

State-of-the-art bilingual open-sourced Math reasoning LLMs.

An in-the-wild benchmark for AI agents in the production harness.

InternEvo is an open-sourced lightweight training framework aims to support model pre-training without the need for extensive dependencies.

Enhance LLM agents with rich tool APIs

[ACL2024 Findings] Agent-FLAN: Designing Data and Methods of Effective Agent Tuning for Large Language Models

Official implement on InternBootCamp

LLM Group Chat Framework: chat with multiple LLMs at the same time. 大模型群聊框架：同时与多个大语言模型聊天。

[ICLR 2026] An official implementation of "CapRL: Stimulating Dense Image Caption Capabilities via Reinforcement Learning"

[ICLR 2026] An official implementation of "SIM-CoT: Supervised Implicit Chain-of-Thought"

[CVPR 2026] Official Code for "ARM-Thinker: Reinforcing Multimodal Generative Reward Models with Agentic Tool Use and Visual Reasoning"

Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning

Pre-trained, Scalable, High-performance Reward Models via Policy Discriminative Learning.

[CVPR 2026] Official release of "Spatial-SSRL: Enhancing Spatial Understanding via Self-Supervised Reinforcement Learning"

Turning LLM architecture exploration into reusable knowledge for the community. 🌳

InternLumina-U2: A Multi-Codebook Diffusion Large Language Model for Omni-Visual Understanding, Image Generation and Editing

[ICLR 2026] JanusCoder: Towards a Foundational Visual-Programmatic Interface for Code Intelligence

[NeurIPS 2026] Official Implementation of "Visual-ERM: Reward Modeling for Visual Equivalence"

ResOPD: Tail Residualization for Sparse On-Policy Distillation. Core implementation built on verl.

[EMNLP 2026 Oral] An official implementation of "OVO-S-Bench: A Hierarchical Benchmark for Streaming Spatial Intelligence in Multimodal LLMs"

Intern-S2-Mobius

[ECCV 2026] An official implementation of "EndoCoT". Scaling endogenous Chain-of-Thought (CoT) reasoning in diffusion models for complex structured generation.