[ICML 2024] Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibration
☆45Jun 30, 2024Updated last year
Alternatives and similar repositories for ACT
Users that are interested in ACT are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [ICLR 2025] When Attention Sink Emerges in Language Models: An Empirical View (Spotlight)☆158Jul 8, 2025Updated 9 months ago
- The official code for [ECCV2020] "HALO: Hardware-aware Learning to Optimize"☆10Mar 22, 2023Updated 3 years ago
- [ICLR 2025] See What You Are Told: Visual Attention Sink in Large Multimodal Models☆104Feb 16, 2025Updated last year
- Code for "Language Models Can Learn from Verbal Feedback Without Scalar Rewards"☆60Jan 5, 2026Updated 3 months ago
- Code accompanying the paper "Massive Activations in Large Language Models"☆198Mar 4, 2024Updated 2 years ago
- Wordpress hosting with auto-scaling on Cloudways • AdFully Managed hosting built for WordPress-powered businesses that need reliable, auto-scalable hosting. Cloudways SafeUpdates now available.
- SysBench: Can Large Language Models Follow System Messages?☆40Sep 4, 2024Updated last year
- [AAAI 2025] Code for paper:Enhancing Multimodal Large Language Models Complex Reasoning via Similarity Computation☆22Jan 14, 2025Updated last year
- [CVPR2025] Code Release of F-LMM: Grounding Frozen Large Multimodal Models☆109May 29, 2025Updated 10 months ago
- [CVPR 2025 Highlight] Your Large Vision-Language Model Only Needs A Few Attention Heads For Visual Grounding☆67Aug 31, 2025Updated 7 months ago
- ☆13Apr 24, 2022Updated 3 years ago
- [ECCV 2024] Paying More Attention to Image: A Training-Free Method for Alleviating Hallucination in LVLMs☆168Nov 6, 2024Updated last year
- ☆66Jan 23, 2026Updated 2 months ago
- Towards a Mechanistic Interpretation of Multi-Step Reasoning Capabilities of Language Models☆15Nov 4, 2023Updated 2 years ago
- Official Repo for FoodieQA paper (EMNLP 2024)☆20Jun 26, 2025Updated 9 months ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- Pytorch Implementation for "Preserving Linear Separability in Continual Learning by Backward Feature Projection" (CVPR 2023)☆18Jun 29, 2023Updated 2 years ago
- Code for our EMNLP 2022 paper: Generative Entity Typing with Curriculum Learning.☆13Aug 19, 2023Updated 2 years ago
- [NeurIPS 2025] Official repository for “FlowCut: Rethinking Redundancy via Information Flow for Efficient Vision-Language Models”☆30Dec 9, 2025Updated 4 months ago
- [ICLR'25] Official code for the paper 'MLLMs Know Where to Look: Training-free Perception of Small Visual Details with Multimodal LLMs'☆364Apr 20, 2025Updated 11 months ago
- LoFiT: Localized Fine-tuning on LLM Representations☆45Jan 15, 2025Updated last year
- [ICCV 2025] Official implementation of "InstructSeg: Unifying Instructed Visual Segmentation with Multi-modal Large Language Models"☆55Feb 10, 2025Updated last year
- Less is More: Mitigating Multimodal Hallucination from an EOS Decision Perspective (ACL 2024)☆57Oct 28, 2024Updated last year
- [NAACL 2025 Oral] From redundancy to relevance: Enhancing explainability in multimodal large language models☆129Jan 30, 2026Updated 2 months ago
- [EMNLP 2024] RoLoRA: Fine-tuning Rotated Outlier-free LLMs for Effective Weight-Activation Quantization☆39Sep 24, 2024Updated last year
- Wordpress hosting with auto-scaling on Cloudways • AdFully Managed hosting built for WordPress-powered businesses that need reliable, auto-scalable hosting. Cloudways SafeUpdates now available.
- Data and code for the paper: Finding Safety Neurons in Large Language Models☆25Jan 29, 2026Updated 2 months ago
- Official code for paper: [CLS] Attention is All You Need for Training-Free Visual Token Pruning: Make VLM Inference Faster.☆110Jun 29, 2025Updated 9 months ago
- [CVPR 2025] Mitigating Object Hallucinations in Large Vision-Language Models with Assembly of Global and Local Attention☆65Jul 16, 2024Updated last year
- Emergent Visual Grounding in Large Multimodal Models Without Grounding Supervision☆43Oct 19, 2025Updated 5 months ago
- [ACL 2024] Official PyTorch implementation of "IntactKV: Improving Large Language Model Quantization by Keeping Pivot Tokens Intact"☆46May 24, 2024Updated last year
- [ECCV 2024 Oral] Code for paper: An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Langua…☆566Jan 4, 2025Updated last year
- [CVPR 2023] Castling-ViT: Compressing Self-Attention via Switching Towards Linear-Angular Attention During Vision Transformer Inference☆30Mar 14, 2024Updated 2 years ago
- The repository for ACL 2024 paper "TimeBench: A Comprehensive Evaluation of Temporal Reasoning Abilities in Large Language Models"☆34Jun 29, 2024Updated last year
- Code for the arXiv preprint "The Unreasonable Effectiveness of Easy Training Data"☆48Jan 17, 2024Updated 2 years ago
- Simple, predictable pricing with DigitalOcean hosting • AdAlways know what you'll pay with monthly caps and flat pricing. Enterprise-grade infrastructure trusted by 600k+ customers.
- Code for our paper: ACM-MILP: Adaptive Constraint Modification via Grouping and Selection for Hardness-Preserving MILP Instance Generatio…☆14Jan 3, 2025Updated last year
- [CVPR 2024 Highlight] Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding☆393Oct 7, 2024Updated last year
- [ICLR 2025] Linear Combination of Saved Checkpoints Makes Consistency and Diffusion Models Better☆16Feb 15, 2025Updated last year
- [CVPR 2024 Highlight] OPERA: Alleviating Hallucination in Multi-Modal Large Language Models via Over-Trust Penalty and Retrospection-Allo…☆403Aug 24, 2024Updated last year
- Compressed LLMs for Efficient Text Generation [ICLR'24 Workshop]☆91Sep 13, 2024Updated last year
- [CVPR 2025] Official Pytorch Code for Distilling Spectral Graph for Object-Context Aware Open-Vocabulary Semantic Segmentation☆50Mar 27, 2025Updated last year
- ☆77Apr 29, 2024Updated last year