🚀 First survey on Attention Sink in Transformers — 200+ papers on utilization, interpretation, and mitigation.
☆131Jun 5, 2026Updated last month
Alternatives and similar repositories for Awesome-Attention-Sink
Users that are interested in Awesome-Attention-Sink are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- SWE-Lego: Pushing the Limits of Supervised Fine-tuning for Software Issue Resolving☆71Feb 28, 2026Updated 4 months ago
- Code for the paper "Multitasking Framework for Unsupervised Simple Definition Generation" on ACL 2022.☆17Aug 17, 2022Updated 3 years ago
- ☆12Feb 11, 2026Updated 4 months ago
- ☆93Updated this week
- Code for "Variational Reasoning for Language Models"☆60Sep 29, 2025Updated 9 months ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- [ECCV 2024] Official PyTorch implementation of LUT "Learning with Unmasked Tokens Drives Stronger Vision Learners"☆14Dec 1, 2024Updated last year
- Codebase for character-centric story understanding☆14Jan 20, 2022Updated 4 years ago
- SummScreen: A Dataset for Abstractive Screenplay Summarization (ACL 2022)☆41May 22, 2022Updated 4 years ago
- 🩻 A 3D Slicer plugin for fully automated segmentation of 167 anatomical structures in CT.☆31Apr 20, 2026Updated 2 months ago
- ☆12Jan 1, 2024Updated 2 years ago
- ☆15Jun 25, 2025Updated last year
- [MICCAI 2024] Implicit Representation Embraces Challenging Attributes of Pulmonary Airway Tree Structures☆14Nov 13, 2024Updated last year
- Provides current Voreen Sources (with modifications) by Uni Münster to build voreen for PC, server or lrz cluster, including workspaces a…☆15Mar 2, 2024Updated 2 years ago
- ☆11May 1, 2022Updated 4 years ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- Learning Debiased and Disentangled Representations for Semantic Segmentation (NeurIPS 2021)☆13Jan 23, 2022Updated 4 years ago
- [ACL 2026] Paper list of Video LLM hallucination. Welcome to Star and Contribute!☆35Jun 13, 2026Updated 3 weeks ago
- ☆14Jan 3, 2025Updated last year
- Source code for our paper: "LoGU: Long-form Generation with Uncertainty Expressions".☆19May 27, 2025Updated last year
- ☆16May 8, 2025Updated last year
- ☆27Jan 22, 2026Updated 5 months ago
- The official implementation of the paper "Rethinking Pruning for Vision-Language Models: Strategies for Effective Sparsity".☆17Jul 2, 2024Updated 2 years ago
- ☆14Jul 8, 2023Updated 2 years ago
- [CIKM-21] Pytorch implementation of LiteGT: Efficient and Lightweight Graph Transformers☆12Nov 16, 2021Updated 4 years ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- Utilities to parse type information and JSDoc annotations from TypeScript source files, and render Markdown documentation☆12Jun 24, 2023Updated 3 years ago
- Data preprocessing for CCTA☆14May 29, 2025Updated last year
- Official Code for NAACL 2022 paper: "Persona-Guided Planning for Controlling the Protagonist's Persona in Story Generation"☆16Sep 1, 2022Updated 3 years ago
- Self-Distribution BNN☆10Mar 8, 2022Updated 4 years ago
- ☆20Jan 5, 2023Updated 3 years ago
- A python wrapper for Stanford CoreNLP, simple and customizable.☆13Oct 26, 2021Updated 4 years ago
- (NeurIPS 2025 🔥) Official implementation for "Efficient Multi-modal Large Language Models via Progressive Consistency Distillation"☆50Feb 11, 2026Updated 4 months ago
- 深度å¦ä¹ 与围棋å¦ä¹â˜†15Oct 27, 2021Updated 4 years ago
- The Github repo for our survey paper: "Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large…☆143Apr 15, 2026Updated 2 months ago
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- Codes and data for EMNLP 2021 paper "Self- and Pseudo-self-supervised Prediction of Speaker and Key-utterance for Multi-party Dialogue Re…☆16Oct 15, 2022Updated 3 years ago
- The PyTorch implementation of the skea-topo aware loss proposed in paper: Enhancing Boundary Segmentation for Topological Accuracy with S…☆19Sep 7, 2025Updated 9 months ago
- [NeurIPS 2023 (Spotlight)] Uncovering the Hidden Dynamics of Video Self-supervised Learning under Distribution Shifts☆13Jan 30, 2024Updated 2 years ago
- Code for Dissecting Generation Modes for Abstractive Summarization Models via Ablation and Attribution (ACL2021)☆13Jun 2, 2021Updated 5 years ago
- Source code of ACL 2023 Main Conference Paper "PAD-Net: An Efficient Framework for Dynamic Networks".☆14Feb 28, 2026Updated 4 months ago
- Paper list for the paper "Authorship Attribution in the Era of Large Language Models: Problems, Methodologies, and Challenges (SIGKDD Exp…☆19May 25, 2026Updated last month
- ☆15Mar 17, 2021Updated 5 years ago