EvolvingLMMs-Lab / MGPOLinks
High-Resolution Visual Reasoning via Multi-Turn Grounding-Based Reinforcement Learning
☆28Updated last week
Alternatives and similar repositories for MGPO
Users that are interested in MGPO are comparing it to the libraries listed below
Sorting:
- Unifying Specialized Visual Encoders for Video Language Models☆21Updated 3 weeks ago
- Official code for Perspective-Aware Reasoning in Vision-Language Models via Mental Imagery Simulation☆32Updated 2 months ago
- Visual Embodied Brain: Let Multimodal Large Language Models See, Think, and Control in Spaces☆73Updated last month
- PyTorch implementation of "Sample- and Parameter-Efficient Auto-Regressive Image Models" from CVPR 2025☆12Updated 4 months ago
- ☆37Updated last month
- Source code for the Paper "Mind the Gap: Benchmarking Spatial Reasoning in Vision-Language Models"☆12Updated last month
- Ego-R1: Chain-of-Tool-Thought for Ultra-Long Egocentric Video Reasoning☆79Updated 2 weeks ago
- ☆21Updated 8 months ago
- Official implementation of Next Block Prediction: Video Generation via Semi-Autoregressive Modeling☆37Updated 5 months ago
- ☆37Updated last month
- [arXiv: 2502.05178] QLIP: Text-Aligned Visual Tokenization Unifies Auto-Regressive Multimodal Understanding and Generation☆76Updated 4 months ago
- ☆45Updated 6 months ago
- Video-Holmes: Can MLLM Think Like Holmes for Complex Video Reasoning?☆60Updated this week
- Task Preference Optimization: Improving Multimodal Large Language Models with Vision Task Alignment☆51Updated 6 months ago
- The code for "VISTA: Enhancing Long-Duration and High-Resolution Video Understanding by VIdeo SpatioTemporal Augmentation" [CVPR2025]☆18Updated 4 months ago
- [ICLR 2025] CREMA: Generalizable and Efficient Video-Language Reasoning via Multimodal Modular Fusion☆48Updated 2 weeks ago
- [CVPR 2025] DiscoVLA: Discrepancy Reduction in Vision, Language, and Alignment for Parameter-Efficient Video-Text Retrieval☆17Updated 3 weeks ago
- ☆86Updated 3 weeks ago
- Multimodal RewardBench☆42Updated 4 months ago
- [NeurIPS-24] This is the official implementation of the paper "DeepStack: Deeply Stacking Visual Tokens is Surprisingly Simple and Effect…☆37Updated last year
- Repo for paper "T2Vid: Translating Long Text into Multi-Image is the Catalyst for Video-LLMs"☆49Updated 4 months ago
- WorldSense: Evaluating Real-world Omnimodal Understanding for Multimodal LLMs☆26Updated 2 months ago
- ☆64Updated 3 weeks ago
- Autoregressive Semantic Visual Reconstruction Helps VLMs Understand Better☆31Updated last month
- ☆22Updated 4 months ago
- FleVRS: Towards Flexible Visual Relationship Segmentation, NeurIPS 2024☆21Updated 7 months ago
- Official repository of "CoMP: Continual Multimodal Pre-training for Vision Foundation Models"☆29Updated 3 months ago
- ☆50Updated 3 weeks ago
- A framework that allows you to apply Sparse AutoEncoder on any models☆29Updated this week
- [ICML 2025] VistaDPO: Video Hierarchical Spatial-Temporal Direct Preference Optimization for Large Video Models☆27Updated last month