Alternatives and similar repositories for VisAttnSink

Users that are interested in VisAttnSink are comparing it to the libraries listed below

• Lackel / AGLA
  [CVPR 2025] Mitigating Object Hallucinations in Large Vision-Language Models with Assembly of Global and Local Attention
  ☆49Updated last year
• mrwu-mac / ControlMLLM
  [NeurIPS2024] Repo for the paper `ControlMLLM: Training-Free Visual Prompt Learning for Multimodal Large Language Models'
  ☆195Updated 3 months ago
• seilk / LocalizationHeads
  [CVPR 2025 Highlight] Your Large Vision-Language Model Only Needs A Few Attention Heads For Visual Grounding
  ☆43Updated 2 months ago
• yu-rp / apiprompting
  [ECCV 2024] API: Attention Prompting on Image for Large Vision-Language Models
  ☆104Updated last year
• ZhangqiJiang07 / middle_layers_indicating_hallucinations
  [CVPR 2025] Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Att…
  ☆48Updated 3 weeks ago
• Sreyan88 / VDGD
  Code for ICLR 2025 Paper: Visual Description Grounding Reduces Hallucinations and Boosts Reasoning in LVLMs
  ☆21Updated 5 months ago
• xing0047 / cca-llava
  [NeurIPS 2024] Mitigating Object Hallucination via Concentric Causal Attention
  ☆63Updated 2 months ago
• zifuwan / ONLY
  [ICCV 2025] ONLY: One-Layer Intervention Sufficiently Mitigates Hallucinations in Large Vision-Language Models
  ☆40Updated 3 months ago
• ncTimTang / AKS
  [CVPR 2025] Adaptive Keyframe Sampling for Long Video Understanding
  ☆120Updated 2 months ago
• Ziwei-Zheng / Nullu
  Code for paper: Nullu: Mitigating Object Hallucinations in Large Vision-Language Models via HalluSpace Projection
  ☆44Updated 7 months ago
• saccharomycetes / mllms_know
  [ICLR'25] Official code for the paper 'MLLMs Know Where to Look: Training-free Perception of Small Visual Details with Multimodal LLMs'
  ☆284Updated 6 months ago
• leaves162 / CLIPtrase
  cliptrase
  ☆46Updated last year
• Hui-design / TSPO
  [✨Official Code of TSPO] Temporal Sampling Policy Optimization for Long-form Video Language Understanding
  ☆53Updated 2 months ago
• PKU-YuanGroup / Look-Back
  This repository is the official implementation of "Look-Back: Implicit Visual Re-focusing in MLLM Reasoning".
  ☆66Updated 3 months ago
• LaVi-Lab / AIM
  [ICCV 2025] Official code for "AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and Pruning"
  ☆42Updated 3 weeks ago
• meetdavidwan / crg
  PyTorch code for "Contrastive Region Guidance: Improving Grounding in Vision-Language Models without Training"
  ☆37Updated last year
• wuw2019 / LoTLIP
  [NeurIPS 2024] Official PyTorch implementation of LoTLIP: Improving Language-Image Pre-training for Long Text Understanding
  ☆45Updated 9 months ago
• zjunlp / Deco
  [ICLR 2025] MLLM can see? Dynamic Correction Decoding for Hallucination Mitigation
  ☆118Updated last month
• Hui-design / Open-LLaVA-Video-R1
  [LLaVA-Video-R1]✨First Adaptation of R1 to LLaVA-Video (2025-03-18)
  ☆34Updated 5 months ago
• mbzuai-oryx / VideoGLaMM
  [CVPR 2025 🔥]A Large Multimodal Model for Pixel-Level Visual Grounding in Videos
  ☆87Updated 6 months ago
• xmed-lab / TAM
  [ICCV25 Oral] Token Activation Map to Visually Explain Multimodal LLMs
  ☆107Updated 2 months ago
• FeipengMa6 / VLoRA
  [NeurIPS 2024] Visual Perception by Large Language Model’s Weights
  ☆52Updated 7 months ago
• yaolinli / DeCo
  Code for DeCo: Decoupling token compression from semanchc abstraction in multimodal large language models
  ☆74Updated 3 months ago
• xuyang-liu16 / GlobalCom2
  🚀 Global Compression Commander: Plug-and-Play Inference Acceleration for High-Resolution Large Vision-Language Models
  ☆33Updated 3 months ago
• minglllli / CLS-RL
  [NeurIPS 2025 Spotlight] Think or Not Think: A Study of Explicit Thinking in Rule-Based Visual Reinforcement Fine-Tuning
  ☆69Updated last month
• FightingFighting / cross-modal-information-flow-in-MLLM
  This is the official repository for paper: cross-modal information flow in multimodal large language models
  ☆29Updated 5 months ago
• congvvc / InstructSeg
  [ICCV 2025] Official implementation of "InstructSeg: Unifying Instructed Visual Segmentation with Multi-modal Large Language Models"
  ☆48Updated 8 months ago
• LijunZhang01 / Octopus
  ☆22Updated 6 months ago
• ys-zong / VL-ICL
  [ICLR 2025] VL-ICL Bench: The Devil in the Details of Multimodal In-Context Learning
  ☆65Updated last month
• cokeshao / Awesome-Multimodal-Token-Compression
  Survey: https://arxiv.org/pdf/2507.20198
  ☆186Updated last week