[ICML'25] Our study systematically investigates massive values in LLMs' attention mechanisms. First, we observe massive values are concentrated in low-frequency dimensions across different attention heads exclusively in attention queries (Q) and keys (K) while absent in values (V).
☆87Jun 20, 2025Updated last year
Alternatives and similar repositories for Rope_with_LLM
Users that are interested in Rope_with_LLM are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [ICONIP'24]Mingyu.Jin's final year project☆30Aug 23, 2024Updated 2 years ago
- [NeurIPS'26] In this work, we investigate how Large Language Models (LLMs) adapt their internal representations when encountering inputs …☆29Oct 23, 2026Updated 2 weeks ago
- VAEGAN, I Love u☆16Aug 15, 2023Updated 3 years ago
- [COLM'24] We propose Protein Chain of Thought (ProCoT), which replicates the biological mechanism of signaling pathways as language promp…☆73Nov 23, 2025Updated 11 months ago
- MemEye: A Visual-Centric Evaluation Framework for Multimodal Agent Memory☆56May 17, 2026Updated 5 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.
- [FCS'24] LVLM Safety paper☆19Jan 4, 2025Updated last year
- [ICML 2025] On the Emergence of Position Bias in Transformers☆11Nov 12, 2025Updated 11 months ago
- ☆25May 17, 2025Updated last year
- Confidence Regulation Neurons in Language Models (NeurIPS 2024)☆16Feb 1, 2025Updated last year
- [EMNLP 2025 Oral] 🎉 Shallow Focus, Deep Fixes: Enhancing Shallow Layers Vision Attention Sinks to Alleviate Hallucination in LVLMs☆14Dec 10, 2025Updated 10 months ago
- [COLING'25] Exploring Concept Depth: How Large Language Models Acquire Knowledge at Different Layers?☆82Jan 22, 2025Updated last year
- [ACL'24] Chain of Thought (CoT) is significant in improving the reasoning abilities of large language models (LLMs). However, the correla…☆47May 11, 2025Updated last year
- ☆12Jun 7, 2026Updated 5 months ago
- ☆124Jan 23, 2026Updated 9 months ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- [RecSys 2025 Spotlight Oral] Leave No One Behind: Fairness-Aware Cross-Domain Recommender Systems for Non-Overlapping Users☆14Jul 25, 2026Updated 3 months ago
- The code for paper "EPO: Entropy-regularized Policy Optimization for LLM Agents Reinforcement Learning"☆40Jul 13, 2026Updated 3 months ago
- 🚀 First survey on Attention Sink in Transformers — 200+ papers on utilization, interpretation, and mitigation.☆144Oct 28, 2026Updated last week
- [EMNLP 2025🔥] UNComp: Can Matrix Entropy Uncover Sparsity? -- A Compressor Design from an Uncertainty-Aware Perspective☆20Jan 7, 2026Updated 10 months ago
- The code for ICLR2025 paper "SLMRec: Empowering Small Language Models for Sequential Recommendation".☆52Jun 16, 2025Updated last year
- [ICLR 2026] Geometric-Mean Policy Optimization☆106Jan 26, 2026Updated 9 months ago
- ☆16Apr 17, 2026Updated 6 months ago
- A further improvement for the AutoDAN-Turbo through test-time scaling.☆16Oct 21, 2025Updated last year
- [ICML 2024] Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibrati…☆45Jun 30, 2024Updated 2 years ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- [ACL 2025] The official code for "AGrail: A Lifelong Agent Guardrail with Effective and Adaptive Safety Detection".☆46Aug 12, 2026Updated 2 months ago
- Official repo for "FineCops-Ref: A new Dataset and Task for Fine-Grained Compositional Referring Expression Comprehension." EMNLP 2024☆13Oct 11, 2025Updated last year
- A curated collection of resources focused on the Mechanistic Interpretability (MI) of Large Multimodal Models (LMMs). This repository agg…☆223Mar 4, 2026Updated 8 months ago
- [ICLR 2025] Understanding and Enhancing Safety Mechanisms of LLMs via Safety-Specific Neuron☆36Apr 30, 2025Updated last year
- From Commands to Prompts: LLM-based Semantic File System for AIOS☆56Mar 9, 2025Updated last year
- This is the accompanying code for our arxiv pre-print: "BoolNet: Minimizing the Energy Consumption of Binary Neural Networks"☆11Sep 17, 2021Updated 5 years ago
- The open-source materials for paper "Sparsing Law: Towards Large Language Models with Greater Activation Sparsity".☆32Nov 12, 2024Updated last year
- [ICML 2025] Fourier Position Embedding: Enhancing Attention’s Periodic Extension for Length Generalization☆122Jun 2, 2025Updated last year
- Code accompanying the paper "Massive Activations in Large Language Models"☆205Mar 4, 2024Updated 2 years ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Official PyTorch code for ICLR 2025 paper "Gnothi Seauton: Empowering Faithful Self-Interpretability in Black-Box Models"☆24Mar 4, 2025Updated last year
- [CVPR 2025] Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Att…☆85Oct 9, 2025Updated last year
- ☆20Mar 25, 2026Updated 7 months ago
- [NeurIPS'25] ChemOrch: Empowering LLMs with Chemical Intelligence via Synthetic Instructions☆14Sep 23, 2025Updated last year
- [EMNLP 2024 Findings🔥] Official implementation of ": LOOK-M: Look-Once Optimization in KV Cache for Efficient Multimodal Long-Context In…☆104Nov 9, 2024Updated last year
- [ICLR 2025] When Attention Sink Emerges in Language Models: An Empirical View (Spotlight)☆164Jul 8, 2025Updated last year
- Code for ICLR 2025 Paper "What is Wrong with Perplexity for Long-context Language Modeling?"☆118Oct 11, 2025Updated last year