[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:
- [NeurIPS'26] In this work, we investigate how Large Language Models (LLMs) adapt their internal representations when encountering inputs …☆25Updated this week
- VAEGAN, I Love u☆16Aug 15, 2023Updated 3 years ago
- The code for paper "MemGym: a Long-Horizon Memory Environment for LLM Agents".☆23Jun 2, 2026Updated 3 months ago
- MemEye: A Visual-Centric Evaluation Framework for Multimodal Agent Memory☆54May 17, 2026Updated 4 months ago
- [FCS'24] LVLM Safety paper☆19Jan 4, 2025Updated last year
- Open source password manager - Proton Pass • AdSecurely store, share, and autofill your credentials with Proton Pass, the end-to-end encrypted password manager trusted by millions.
- ☆25May 17, 2025Updated last year
- [ACL'25] We propose a novel fine-tuning method, Separate Memory and Reasoning, which combines prompt tuning with LoRA.☆89Nov 2, 2025Updated 10 months ago
- [ICLR 2025] Official implementation of paper "Dynamic Low-Rank Sparse Adaptation for Large Language Models".☆25Mar 16, 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
- Confidence Regulation Neurons in Language Models (NeurIPS 2024)☆16Feb 1, 2025Updated last year
- ☆121Jan 23, 2026Updated 8 months ago
- [EMNLP 2025🔥] UNComp: Can Matrix Entropy Uncover Sparsity? -- A Compressor Design from an Uncertainty-Aware Perspective☆20Jan 7, 2026Updated 8 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☆105Jan 26, 2026Updated 8 months ago
- Open source password manager - Proton Pass • AdSecurely store, share, and autofill your credentials with Proton Pass, the end-to-end encrypted password manager trusted by millions.
- [ICLR 2025] Understanding and Enhancing Safety Mechanisms of LLMs via Safety-Specific Neuron☆36Apr 30, 2025Updated last year
- A curated collection of resources focused on the Mechanistic Interpretability (MI) of Large Multimodal Models (LMMs). This repository agg…☆220Mar 4, 2026Updated 6 months ago
- The open-source materials for paper "Sparsing Law: Towards Large Language Models with Greater Activation Sparsity".☆32Nov 12, 2024Updated last year
- Official PyTorch code for ICLR 2025 paper "Gnothi Seauton: Empowering Faithful Self-Interpretability in Black-Box Models"☆24Mar 4, 2025Updated last year
- [ICML 2025] Fourier Position Embedding: Enhancing Attention’s Periodic Extension for Length Generalization☆121Jun 2, 2025Updated last year
- [KDD Explore'24]Time Series Forecasting with LLMs: Understanding and Enhancing Model Capabilities☆17May 7, 2025Updated last year
- [CVPR 2025] Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Att…☆84Oct 9, 2025Updated 11 months ago
- [EMNLP 2024 Findings🔥] Official implementation of ": LOOK-M: Look-Once Optimization in KV Cache for Efficient Multimodal Long-Context In…☆103Nov 9, 2024Updated last year
- ☆20Mar 25, 2026Updated 6 months ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- [CVPR 2025] Mitigating Object Hallucinations in Large Vision-Language Models with Assembly of Global and Local Attention☆70Jul 16, 2024Updated 2 years ago
- [CVPR 2025] VASparse: Towards Efficient Visual Hallucination Mitigation via Visual-Aware Token Sparsification☆51Mar 24, 2025Updated last year
- Code and data for paper "Exploring Hallucination of Large Multimodal Models in Video Understanding: Benchmark, Analysis and Mitigation".☆25Oct 22, 2025Updated 11 months ago
- [ICLR 2025] See What You Are Told: Visual Attention Sink in Large Multimodal Models☆119Feb 16, 2025Updated last year
- [ICLR 2025] When Attention Sink Emerges in Language Models: An Empirical View (Spotlight)☆164Jul 8, 2025Updated last year
- [NeurIPS 2024] Mitigating Object Hallucination via Concentric Causal Attention☆69Aug 30, 2025Updated last year
- Official code for paper Understanding the Reasoning Ability of Language Models From the Perspective of Reasoning Paths Aggregation☆21Feb 29, 2024Updated 2 years ago
- [NeurIPS 2025] Official repository for “FlowCut: Rethinking Redundancy via Information Flow for Efficient Vision-Language Models”☆34Dec 9, 2025Updated 9 months ago
- Official PyTorch implementation of the paper "Accelerating Diffusion Large Language Models with SlowFast Sampling: The Three Golden Princ…☆46Jul 18, 2025Updated last year
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- ☆36Jun 13, 2025Updated last year
- [ICLR 26] Context Tokens are Anchors: Understanding the Repeat Curse in dMLLMs from an Information Flow Perspective☆33Mar 6, 2026Updated 6 months ago
- Code for Blog Post: Can Better Cold-Start Strategies Improve RL Training for LLMs?☆20Mar 9, 2025Updated last year
- [ICML 2025] Official PyTorch implementation of "FlatQuant: Flatness Matters for LLM Quantization"☆228Nov 25, 2025Updated 10 months ago
- ☆22Feb 10, 2025Updated last year
- ☆22Jan 2, 2026Updated 8 months ago
- [NeurIPS 2025] The official implementation of the paper "DRIFT: Dynamic Rule-Based Defense with Injection Isolation for Securing LLM Agen…☆61Jul 16, 2026Updated 2 months ago