xuyang-liu16 / GlobalCom2Links
π Global Compression Commander: Plug-and-Play Inference Acceleration for High-Resolution Large Vision-Language Models
β31Updated last month
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 Modelβ34Updated 7 months ago
- β54Updated 3 months ago
- [ACM MM 2025] TimeChat-online: 80% Visual Tokens are Naturally Redundant in Streaming Videosβ73Updated last month
- [ICCV 2025] Official code for "AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and Pruning"β38Updated 2 months ago
- Code for DeCo: Decoupling token compression from semanchc abstraction in multimodal large language modelsβ67Updated last month
- Think or Not Think: A Study of Explicit Thinking in Rule-Based Visual Reinforcement Fine-Tuningβ62Updated 3 months ago
- Official implement of MIA-DPOβ64Updated 7 months ago
- Code release for VTW (AAAI 2025 Oral)β48Updated last month
- Official implementation of paper ReTaKe: Reducing Temporal and Knowledge Redundancy for Long Video Understandingβ36Updated 5 months ago
- (CVPR 2025) PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reductionβ119Updated 5 months ago
- VoCoT: Unleashing Visually Grounded Multi-Step Reasoning in Large Multi-Modal Modelsβ72Updated last year
- π Video Compression Commander: Plug-and-Play Inference Acceleration for Video Large Language Modelsβ29Updated 2 months ago
- TinyLLaVA-Video-R1: Towards Smaller LMMs for Video Reasoningβ96Updated 3 months ago
- [ICML 2025] Official implementation of paper 'Look Twice Before You Answer: Memory-Space Visual Retracing for Hallucination Mitigation inβ¦β145Updated last month
- [CVPR 2025 Oral] VideoEspresso: A Large-Scale Chain-of-Thought Dataset for Fine-Grained Video Reasoning via Core Frame Selectionβ111Updated last month
- This is the official implementation of our paper "QuoTA: Query-oriented Token Assignment via CoT Query Decouple for Long Video Comprehensβ¦β73Updated 4 months ago
- PyTorch Implementation of "Divide, Conquer and Combine: A Training-Free Framework for High-Resolution Image Perception in Multimodal Largβ¦β28Updated 3 months ago
- β28Updated 2 months ago
- [CVPR 2025] Adaptive Keyframe Sampling for Long Video Understandingβ97Updated this week
- [ICCV 2025] p-MoD: Building Mixture-of-Depths MLLMs via Progressive Ratio Decayβ42Updated 2 months ago
- Survey: https://arxiv.org/pdf/2507.20198β107Updated last week
- [NeurIPS2024] Repo for the paper `ControlMLLM: Training-Free Visual Prompt Learning for Multimodal Large Language Models'β190Updated last month
- Official code for paper: [CLS] Attention is All You Need for Training-Free Visual Token Pruning: Make VLM Inference Faster.β85Updated 2 months ago
- [ICCV 2025] ONLY: One-Layer Intervention Sufficiently Mitigates Hallucinations in Large Vision-Language Modelsβ33Updated last month
- β¨β¨The Curse of Multi-Modalities (CMM): Evaluating Hallucinations of Large Multimodal Models across Language, Visual, and Audioβ46Updated last month
- MME-Unify: A Comprehensive Benchmark for Unified Multimodal Understanding and Generation Modelsβ41Updated 4 months ago
- NoisyRollout: Reinforcing Visual Reasoning with Data Augmentationβ85Updated 2 weeks ago
- More Thinking, Less Seeing? Assessing Amplified Hallucination in Multimodal Reasoning Modelsβ45Updated 2 months ago
- [ICLR 2025] MLLM can see? Dynamic Correction Decoding for Hallucination Mitigationβ98Updated 8 months ago
- [CVPR'2025] VoCo-LLaMA: This repo is the official implementation of "VoCo-LLaMA: Towards Vision Compression with Large Language Models".β186Updated 2 months ago