mllms

InternRobotics' open platform for building generalized navigation foundation models.

This is the repo for the paper "OS Agents: A Survey on MLLM-based Agents for Computer, Phone and Browser Use" (ACL 2025 Oral).

[CVPR 2025 Highlight] Official code for "Olympus: A Universal Task Router for Computer Vision Tasks"

[ICLR 2025] This is the official repository of our paper "MedTrinity-25M: A Large-scale Multimodal Dataset with Multigranular Annotations for Medicine“

[AAAI2026] X-SAM: From Segment Anything to Any Segmentation

Efficient Multimodal Large Language Models: A Survey

[CVPR 2026] G2VLM: Geometry Grounded Vision Language Model with Unified 3D Reconstruction and Spatial Reasoning

[Survey Paper] This repository collects research papers of large Foundation Models for Scenario Generation and Analysis in Autonomous Driving. The repository will be continuously updated to track the latest update.

🦦 Crayotter: A Multimodal AI-Agent for Video-Editing, Video-Composing, and Video Production. Powered by Multimodal LLMs for autonomous Text-to-Video agentic framework. | 基于多模态大模型 (Multimodal LLMs) 的 AI 剪辑智能体，支持从文字需求到视频成品的端到端全自动生产与创作。

不想啃 5000+ 全文？我已经替你和 LLM 啃完了 — ICLR 2026 全景中文导读

[ACL 2025] The code repository for "Mitigating Visual Forgetting via Take-along Visual Conditioning for Multi-modal Long CoT Reasoning" in PyTorch.

[NeurIPS 2025] Official Repo of Omni-R1: Reinforcement Learning for Omnimodal Reasoning via Two-System Collaboration

🔥[CVPR2025] EventGPT: Event Stream Understanding with Multimodal Large Language Models

[CVPR2025] SegAgent: Exploring Pixel Understanding Capabilities in MLLMs by Imitating Human Annotator Trajectories

[NeurIPS25 & ICML25 Workshop on Reliable and Responsible Foundation Models] A Simple Baseline Achieving Over 90% Success Rate Against the Strong Black-box Models of GPT-4.5/4o/o1. Paper at: https://arxiv.org/abs/2503.10635

[TCSVT] Official repository of the paper "A Glimpse to Compress: Dynamic Visual Token Pruning for Large Vision-Language Models"

[ECCV 2026🔥] SRUM: Fine-Grained Self-Rewarding for Unified Multimodal Models

[CVPR 2025] Crab: A Unified Audio-Visual Scene Understanding Model with Explicit Cooperation

[ICML2026] ACTIVE-O3: Empowering Multimodal Large Language Models with Active Perception via GRPO

PDF Parsing Tool: GOT's vLLM acceleration implementation, MinerU for layout recognition, and GOT for table formula parsing.