[ACL2025 Findings] Migician: Revealing the Magic of Free-Form Multi-Image Grounding in Multimodal Large Language Models
☆92May 20, 2025Updated last year
Alternatives and similar repositories for Migician
Users that are interested in Migician are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- UniVG-R1: Reasoning Guided Universal Visual Grounding with Reinforcement Learning☆169Jun 2, 2025Updated last year
- [CVPR 2024] Multi-modal Instruction Tuned LLMs with Fine-grained Visual Perception☆12Dec 26, 2024Updated last year
- [CVPR2025] Code Release of F-LMM: Grounding Frozen Large Multimodal Models☆117May 29, 2025Updated last year
- ☆12Oct 6, 2026Updated last month
- [ECCV-24] This is the official implementation of the paper "SEGIC: Unleashing the Emergent Correspondence for In-Context Segmentation".☆29Oct 13, 2024Updated 2 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Official code for NeurIPS 2025 paper "GRIT: Teaching MLLMs to Think with Images"☆192Jan 16, 2026Updated 9 months ago
- official code☆13Jul 6, 2026Updated 4 months ago
- [ICCV 2025] Official implementation of "InstructSeg: Unifying Instructed Visual Segmentation with Multi-modal Large Language Models"☆56Feb 10, 2025Updated last year
- Code for ChatRex: Taming Multimodal LLM for Joint Perception and Understanding☆218Oct 15, 2025Updated last year
- [ICLR-2026] Rex-Thinker: Grounded Object Refering via Chain-of-Thought Reasoning☆156Jun 30, 2025Updated last year
- [ECCV2024] Grounded Multimodal Large Language Model with Localized Visual Tokenization☆587Jun 7, 2024Updated 2 years ago
- Emergent Visual Grounding in Large Multimodal Models Without Grounding Supervision☆46Oct 19, 2025Updated last year
- Official repo for "FineCops-Ref: A new Dataset and Task for Fine-Grained Compositional Referring Expression Comprehension." EMNLP 2024☆13Oct 11, 2025Updated last year
- KARL: Knowledge-Aware Reasoning and Reinforcement Learning for Knowledge-Intensive Visual Grounding☆72Apr 5, 2026Updated 7 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Video Reasoning Segmentation☆27Nov 29, 2024Updated last year
- [Neurips'24 Spotlight] Visual CoT: Advancing Multi-Modal Language Models with a Comprehensive Dataset and Benchmark for Chain-of-Thought …☆446Dec 22, 2024Updated last year
- Group-wise Temporal Logit Adjustment for TAS☆12Oct 24, 2024Updated 2 years ago
- R1-Track: Direct Application of MLLMs to Visual Object Tracking via Reinforcement Learning.☆67May 14, 2025Updated last year
- [ICLR'25] Official code for the paper 'MLLMs Know Where to Look: Training-free Perception of Small Visual Details with Multimodal LLMs'☆396Apr 20, 2025Updated last year
- Official GPU implementation of the paper "PPLLaVA: Varied Video Sequence Understanding With Prompt Guidance"☆134Nov 19, 2024Updated last year
- [ACL'25 Oral] Code for the paper "UrbanVideo-Bench: Benchmarking Vision-Language Models on Embodied Intelligence with Video Data in Urban…☆30Aug 7, 2026Updated 3 months ago
- [EMNLP'25 main] Official Implementation of ModalPrompt: Towards Efficient Multimodal Continual Instruction Tuning with Dual-Modality Guid…☆28Feb 8, 2026Updated 8 months ago
- ☆32Jun 14, 2026Updated 4 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- The official repository of our paper "Reinforcing Video Reasoning with Focused Thinking"☆38Jun 12, 2025Updated last year
- Dettoolchain: A new prompting paradigm to unleash detection ability of MLLM☆45Oct 12, 2024Updated 2 years ago
- [ICLR 2026] Official implementation of "Patch-as-Decodable-Token: Towards Unified Multi-Modal Vision Tasks in MLLMs"☆167Aug 3, 2026Updated 3 months ago
- Pixel-Level Reasoning Model trained with RL [NeuIPS25]☆311Jul 28, 2026Updated 3 months ago
- LEO: A powerful Hybrid Multimodal LLM☆20Jan 18, 2025Updated last year
- The official repository of paper "Evaluating MLLMs with Multimodal Multi-image Reasoning Benchmark"☆19Jun 20, 2025Updated last year
- Segment Anything with Deictic Prompting☆27May 13, 2025Updated last year
- Project Page For "Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcement"☆645Jan 17, 2026Updated 9 months ago
- ☆14Mar 30, 2026Updated 7 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Knowledge Amalgamation, Multi-teacher KD, Ensemble KD☆12Sep 21, 2021Updated 5 years ago
- ☆19Jun 29, 2025Updated last year
- Code for EMNLP25 paper "Video-RTS: Rethinking Reinforcement Learning and Test-Time Scaling for Efficient and Enhanced Video Reasoning"☆24Feb 18, 2026Updated 8 months ago
- [CVPR2025] Project for "HyperSeg: Towards Universal Visual Segmentation with Large Language Model".☆183Dec 13, 2024Updated last year
- ☆399Jul 29, 2024Updated 2 years ago
- [ICLR26] Understanding VS. Generation: Navigating Optimization Dilemma in Multimodal Models☆29May 6, 2026Updated 6 months ago
- ☆10Apr 7, 2025Updated last year