xuyang-liu16 / GlobalCom2Links
π Global Compression Commander: Plug-and-Play Inference Acceleration for High-Resolution Large Vision-Language Models
β33Updated 3 months ago
Alternatives and similar repositories for GlobalCom2
Users that are interested in GlobalCom2 are comparing it to the libraries listed below
Sorting:
- Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Modelβ35Updated 9 months ago
- [ACM MM 2025] TimeChat-online: 80% Visual Tokens are Naturally Redundant in Streaming Videosβ86Updated last month
- β58Updated 5 months ago
- [NeurIPS2024] Repo for the paper `ControlMLLM: Training-Free Visual Prompt Learning for Multimodal Large Language Models'β195Updated 3 months ago
- Survey: https://arxiv.org/pdf/2507.20198β179Updated last week
- [ICML 2025] Official implementation of paper 'Look Twice Before You Answer: Memory-Space Visual Retracing for Hallucination Mitigation inβ¦β163Updated last month
- [NeurIPS 2025 Spotlight] Think or Not Think: A Study of Explicit Thinking in Rule-Based Visual Reinforcement Fine-Tuningβ69Updated last month
- [ICCV 2025] ONLY: One-Layer Intervention Sufficiently Mitigates Hallucinations in Large Vision-Language Modelsβ40Updated 3 months ago
- Code for DeCo: Decoupling token compression from semanchc abstraction in multimodal large language modelsβ74Updated 3 months ago
- [ICCV 2025] Official code for "AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and Pruning"β42Updated 3 weeks ago
- [ECCV 2024] Paying More Attention to Image: A Training-Free Method for Alleviating Hallucination in LVLMsβ147Updated 11 months ago
- [ICLR 2025] MLLM can see? Dynamic Correction Decoding for Hallucination Mitigationβ118Updated last month
- [CVPR 2025] Adaptive Keyframe Sampling for Long Video Understandingβ120Updated 2 months ago
- This repository is the official implementation of "Look-Back: Implicit Visual Re-focusing in MLLM Reasoning".β66Updated 3 months ago
- Code and data for paper "Exploring Hallucination of Large Multimodal Models in Video Understanding: Benchmark, Analysis and Mitigation".β21Updated last week
- Code release for VTW (AAAI 2025 Oral)β50Updated 3 months ago
- (CVPR 2025) PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reductionβ132Updated 7 months ago
- [NeurIPS 2025] More Thinking, Less Seeing? Assessing Amplified Hallucination in Multimodal Reasoning Modelsβ63Updated 4 months ago
- π Video Compression Commander: Plug-and-Play Inference Acceleration for Video Large Language Modelsβ36Updated last week
- Official implementation of paper ReTaKe: Reducing Temporal and Knowledge Redundancy for Long Video Understandingβ37Updated 7 months ago
- [ACL 2025] PruneVid: Visual Token Pruning for Efficient Video Large Language Modelsβ55Updated 5 months ago
- Code of LVAgent: Long Video Understanding by Multi-Round Dynamical Collaboration of MLLM Agentsβ17Updated 4 months ago
- VoCoT: Unleashing Visually Grounded Multi-Step Reasoning in Large Multi-Modal Modelsβ75Updated last year
- Official repository of 'ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasingββ57Updated 4 months ago
- PyTorch Implementation of "Divide, Conquer and Combine: A Training-Free Framework for High-Resolution Image Perception in Multimodal Largβ¦β30Updated 5 months ago
- A paper list about Token Merge, Reduce, Resample, Drop for MLLMs.β74Updated this week
- This is the official implementation of our paper "QuoTA: Query-oriented Token Assignment via CoT Query Decouple for Long Video Comprehensβ¦β73Updated 6 months ago
- Reinforcement Learning Tuning for VideoLLMs: Reward Design and Data Efficiencyβ55Updated 4 months ago
- Official code for paper: [CLS] Attention is All You Need for Training-Free Visual Token Pruning: Make VLM Inference Faster.β93Updated 4 months ago
- MME-CoT: Benchmarking Chain-of-Thought in LMMs for Reasoning Quality, Robustness, and Efficiencyβ132Updated 2 months ago