[ICLR 2025] When Attention Sink Emerges in Language Models: An Empirical View (Spotlight)
☆164Jul 8, 2025Updated last year
Alternatives and similar repositories for Attention-Sink
Users that are interested in 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:
- [ICML 2024] Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibrati…☆45Jun 30, 2024Updated 2 years ago
- Code accompanying the paper "Massive Activations in Large Language Models"☆205Mar 4, 2024Updated 2 years ago
- Official implementation of Bootstrapping Language Models via DPO Implicit Rewards☆49Apr 15, 2025Updated last year
- The official repository for SkyLadder: Better and Faster Pretraining via Context Window Scheduling☆44Dec 29, 2025Updated 10 months ago
- V1: Toward Multimodal Reasoning by Designing Auxiliary Task☆36Apr 14, 2025Updated last year
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- [ICLR 2025] Cheating Automatic LLM Benchmarks: Null Models Achieve High Win Rates (Oral)☆85Oct 23, 2024Updated 2 years ago
- Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses (NeurIPS 2024)☆66Jan 11, 2025Updated last year
- Quantized Attention on GPU☆45Nov 22, 2024Updated last year
- The official implementation of "LightTransfer: Your Long-Context LLM is Secretly a Hybrid Model with Effortless Adaptation"☆22Apr 22, 2025Updated last year
- The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.☆55Oct 18, 2024Updated 2 years ago
- triton ver of gqa flash attn, based on the tutorial☆12Aug 4, 2024Updated 2 years ago
- AnchorAttention: Improved attention for LLMs long-context training☆216Jan 15, 2025Updated last year
- Reinforcing General Reasoning without Verifiers☆103Jun 24, 2025Updated last year
- ☆29Aug 9, 2025Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ☆14Jun 10, 2025Updated last year
- [TMLR 2025] On Memorization in Diffusion Models☆33Oct 5, 2023Updated 3 years ago
- Code for "Language Models Can Learn from Verbal Feedback Without Scalar Rewards"☆65Jan 5, 2026Updated 9 months ago
- [ICLR 2025] See What You Are Told: Visual Attention Sink in Large Multimodal Models☆121Feb 16, 2025Updated last year
- [EMNLP 2025🔥] UNComp: Can Matrix Entropy Uncover Sparsity? -- A Compressor Design from an Uncertainty-Aware Perspective☆20Jan 7, 2026Updated 9 months ago
- Optimizing Anytime Reasoning via Budget Relative Policy Optimization☆54Jul 15, 2025Updated last year
- ☆21Apr 16, 2025Updated last year
- [COLM'25] A Controlled Study on Long Context Extension and Generalization in LLMs☆65Mar 9, 2026Updated 7 months ago
- [ArXiv 2025] Denial-of-Service Poisoning Attacks on Large Language Models☆23Oct 22, 2024Updated 2 years ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Measuring the Signal to Noise Ratio in Language Model Evaluation☆32Aug 19, 2025Updated last year
- Defeating the Training-Inference Mismatch via FP16☆199Nov 14, 2025Updated 11 months ago
- The official implementation of "Interpreting the repeated token phenomenon in LLMs"☆15Sep 23, 2025Updated last year
- The official repository of 'Unnatural Language Are Not Bugs but Features for LLMs'☆25May 20, 2025Updated last year
- ☆15Oct 13, 2025Updated last year
- Code for ICLR 2025 Paper "What is Wrong with Perplexity for Long-context Language Modeling?"☆118Oct 11, 2025Updated last year
- Homepage for ProLong (Princeton long-context language models) and paper "How to Train Long-Context Language Models (Effectively)"☆268Sep 12, 2025Updated last year
- [NeurIPS 2024] The official implementation of paper: Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMs.☆137Mar 21, 2025Updated last year
- 🔱 Sailor2: Sailing in South-East Asia with Inclusive Multilingual LLMs☆74Mar 21, 2025Updated last year
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- Kinetics: Rethinking Test-Time Scaling Laws☆87Jul 11, 2025Updated last year
- Stick-breaking attention☆64Jul 1, 2025Updated last year
- Improving Your Model Ranking on Chatbot Arena by Vote Rigging (ICML 2025)☆27Feb 25, 2025Updated last year
- The Dataset and Official Implementation for <Discursive Socratic Questioning: Evaluating the Faithfulness of Language Models’ Understandi…☆20Aug 7, 2024Updated 2 years ago
- 🌾 OAT: A research-friendly framework for LLM online alignment, including reinforcement learning, preference learning, etc.☆674Jan 29, 2026Updated 9 months ago
- ☆139May 29, 2025Updated last year
- ☆35Apr 22, 2025Updated last year