seilk / VisAttnSinkView external linksLinks
[ICLR 2025] See What You Are Told: Visual Attention Sink in Large Multimodal Models
☆90Feb 16, 2025Updated 11 months ago
Alternatives and similar repositories for VisAttnSink
Users that are interested in VisAttnSink are comparing it to the libraries listed below
Sorting:
- [CVPR 2025 Highlight] Your Large Vision-Language Model Only Needs A Few Attention Heads For Visual Grounding☆60Aug 31, 2025Updated 5 months ago
- [ICML 2024] Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibrati…☆46Jun 30, 2024Updated last year
- [ICCV 2025] Official code for "AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and Pruning"☆54Oct 9, 2025Updated 4 months ago
- [CVPR 2025] Mitigating Object Hallucinations in Large Vision-Language Models with Assembly of Global and Local Attention☆61Jul 16, 2024Updated last year
- [CVPR 2025] PACT: Pruning and Clustering-Based Token Reduction for Faster Visual Language Models☆55Jan 30, 2026Updated 2 weeks ago
- [ICLR'25] Official code for the paper 'MLLMs Know Where to Look: Training-free Perception of Small Visual Details with Multimodal LLMs'☆340Apr 20, 2025Updated 9 months ago
- [CVPR 2025] Your Large Vision-Language Model Only Needs A Few Attention Heads For Visual Grounding☆16Oct 4, 2025Updated 4 months ago
- ☆20Apr 15, 2025Updated 9 months ago
- [ICCV 2025] ONLY: One-Layer Intervention Sufficiently Mitigates Hallucinations in Large Vision-Language Models☆49Jul 7, 2025Updated 7 months ago
- Towards Training-free Open-world Segmentation via Image Prompt Foundation Models,☆18Nov 22, 2024Updated last year
- [NeurIPS 2025] Official Implementation for "Enhancing Vision-Language Model Reliability with Uncertainty-Guided Dropout Decoding"☆22Dec 8, 2024Updated last year
- ☆14Jan 16, 2024Updated 2 years ago
- [CVPR 2025] Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Att…☆62Oct 9, 2025Updated 4 months ago
- Code for paper: Nullu: Mitigating Object Hallucinations in Large Vision-Language Models via HalluSpace Projection☆50Mar 13, 2025Updated 11 months ago
- [ICLR 2025] MLLM can see? Dynamic Correction Decoding for Hallucination Mitigation☆133Sep 11, 2025Updated 5 months ago
- Official Implementation of CODE☆17Sep 26, 2024Updated last year
- MAM: ModularMulti-Agent Framework for Multi-Modal Medical Diagnosis via Role-Specialized Collaboration☆37Jun 25, 2025Updated 7 months ago
- ☆21Nov 29, 2022Updated 3 years ago
- Official implementation for the paper"Towards Understanding How Knowledge Evolves in Large Vision-Language Models"☆26Apr 10, 2025Updated 10 months ago
- [NAACL 2025 Oral] From redundancy to relevance: Enhancing explainability in multimodal large language models☆128Jan 30, 2026Updated 2 weeks ago
- Emergent Visual Grounding in Large Multimodal Models Without Grounding Supervision☆42Oct 19, 2025Updated 3 months ago
- FireQ: Fast INT4-FP8 Kernel and RoPE-aware Quantization for LLM Inference Acceleration☆20Jun 27, 2025Updated 7 months ago
- spatio-temporal tasks☆15Jul 15, 2024Updated last year
- [NeurIPS 2023]DDCoT: Duty-Distinct Chain-of-Thought Prompting for Multimodal Reasoning in Language Models☆49Mar 18, 2024Updated last year
- (CVPR2024 Highlight) Novel Class Discovery for Ultra-Fine-Grained Visual Categorization (UFG-NCD)☆23Jul 1, 2024Updated last year
- ☆21Jul 25, 2022Updated 3 years ago
- [CVPR2025] Code Release of F-LMM: Grounding Frozen Large Multimodal Models☆108May 29, 2025Updated 8 months ago
- DeepPerception: Advancing R1-like Cognitive Visual Perception in MLLMs for Knowledge-Intensive Visual Grounding☆66Jun 10, 2025Updated 8 months ago
- [ICML 2024] Official implementation for "HALC: Object Hallucination Reduction via Adaptive Focal-Contrast Decoding"☆107Dec 4, 2024Updated last year
- STI-Bench : Are MLLMs Ready for Precise Spatial-Temporal World Understanding?☆35Jan 12, 2026Updated last month
- Project Page for GaussianFormer☆24May 30, 2024Updated last year
- Official repository of the paper "A Glimpse to Compress: Dynamic Visual Token Pruning for Large Vision-Language Models"☆90Sep 10, 2025Updated 5 months ago
- [CVPR2025] Project for "HyperSeg: Towards Universal Visual Segmentation with Large Language Model".☆180Dec 13, 2024Updated last year
- A framework that allows you to apply Sparse AutoEncoder on any models☆51Jul 11, 2025Updated 7 months ago
- [CVPR 2025] Towards Training-free Anomaly Detection with Vision and Language Foundation Models☆83May 19, 2025Updated 8 months ago
- Code accompanying the paper "Massive Activations in Large Language Models"☆196Mar 4, 2024Updated last year
- The official implementation of "Sparse-vDiT: Unleashing the Power of Sparse Attention to Accelerate Video Diffusion Transformers" (arXiv …☆50Jun 6, 2025Updated 8 months ago
- a training-free approach to accelerate ViTs and VLMs by pruning redundant tokens based on similarity☆42May 24, 2025Updated 8 months ago
- [ICML'25] Our study systematically investigates massive values in LLMs' attention mechanisms. First, we observe massive values are concen…☆85Jun 20, 2025Updated 7 months ago