xuyang-liu16 / GlobalCom2Links
π Global Compression Commander: Plug-and-Play Inference Acceleration for High-Resolution Large Vision-Language Models
β30Updated 2 weeks 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 Modelβ31Updated 7 months ago
- [ACM MM 2025] TimeChat-online: 80% Visual Tokens are Naturally Redundant in Streaming Videosβ66Updated 3 weeks ago
- β54Updated 3 months ago
- β27Updated 2 months ago
- Code for DeCo: Decoupling token compression from semanchc abstraction in multimodal large language modelsβ63Updated 3 weeks ago
- [ICCV 2025] Official code for "AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and Pruning"β34Updated last month
- VoCoT: Unleashing Visually Grounded Multi-Step Reasoning in Large Multi-Modal Modelsβ71Updated last year
- π Video Compression Commander: Plug-and-Play Inference Acceleration for Video Large Language Modelsβ28Updated last month
- Think or Not Think: A Study of Explicit Thinking in Rule-Based Visual Reinforcement Fine-Tuningβ56Updated 2 months ago
- NoisyRollout: Reinforcing Visual Reasoning with Data Augmentationβ83Updated 2 months ago
- β26Updated 5 months ago
- [ECCV 2024] Paying More Attention to Image: A Training-Free Method for Alleviating Hallucination in LVLMsβ132Updated 9 months ago
- [ICLR 2025] MLLM can see? Dynamic Correction Decoding for Hallucination Mitigationβ96Updated 7 months ago
- [NeurIPS2024] Repo for the paper `ControlMLLM: Training-Free Visual Prompt Learning for Multimodal Large Language Models'β186Updated 3 weeks ago
- [CVPR 2025] Adaptive Keyframe Sampling for Long Video Understandingβ87Updated 3 months ago
- β93Updated 4 months ago
- The official repository for ACL2025 paper "PruneVid: Visual Token Pruning for Efficient Video Large Language Models".β51Updated 2 months ago
- β¨β¨The Curse of Multi-Modalities (CMM): Evaluating Hallucinations of Large Multimodal Models across Language, Visual, and Audioβ46Updated 3 weeks ago
- Official implementation of paper ReTaKe: Reducing Temporal and Knowledge Redundancy for Long Video Understandingβ36Updated 4 months ago
- (CVPR 2025) PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reductionβ117Updated 5 months ago
- Official implement of MIA-DPOβ63Updated 6 months ago
- MME-Unify: A Comprehensive Benchmark for Unified Multimodal Understanding and Generation Modelsβ41Updated 3 months ago
- [NeurIPS 2024] MoME: Mixture of Multimodal Experts for Generalist Multimodal Large Language Modelsβ69Updated 3 months ago
- HallE-Control: Controlling Object Hallucination in LMMsβ31Updated last year
- β85Updated 7 months ago
- Less is More: Mitigating Multimodal Hallucination from an EOS Decision Perspective (ACL 2024)β55Updated 9 months ago
- Github repository for "Bring Reason to Vision: Understanding Perception and Reasoning through Model Merging" (ICML 2025)β68Updated 2 months ago
- β132Updated 5 months ago
- [ICCV 2025] ONLY: One-Layer Intervention Sufficiently Mitigates Hallucinations in Large Vision-Language Modelsβ26Updated last month
- [CVPR 2025 Oral] VideoEspresso: A Large-Scale Chain-of-Thought Dataset for Fine-Grained Video Reasoning via Core Frame Selectionβ108Updated last week