zepingyu0512 / llava-mechanism
code for arxiv paper: Understanding Multimodal LLMs: the Mechanistic Interpretability of Llava in Visual Question Answering
☆16Updated 3 months ago
Alternatives and similar repositories for llava-mechanism:
Users that are interested in llava-mechanism are comparing it to the libraries listed below
- Code for paper "Unraveling Cross-Modality Knowledge Conflicts in Large Vision-Language Models."☆42Updated 5 months ago
- A Dynamic Visual Benchmark for Evaluating Mathematical Reasoning Robustness of Vision Language Models☆18Updated 4 months ago
- RAG-RewardBench: Benchmarking Reward Models in Retrieval Augmented Generation for Preference Alignment☆16Updated 3 months ago
- In-Context Sharpness as Alerts: An Inner Representation Perspective for Hallucination Mitigation (ICML 2024)☆57Updated last year
- ☆59Updated 6 months ago
- [NAACL'25 Oral] Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering☆52Updated 4 months ago
- [𝐄𝐌𝐍𝐋𝐏 𝐅𝐢𝐧𝐝𝐢𝐧𝐠𝐬 𝟐𝟎𝟐𝟒 & 𝐀𝐂𝐋 𝟐𝟎𝟐𝟒 𝐍𝐋𝐑𝐒𝐄 𝐎𝐫𝐚𝐥] 𝘌𝘯𝘩𝘢𝘯𝘤𝘪𝘯𝘨 𝘔𝘢𝘵𝘩𝘦𝘮𝘢𝘵𝘪𝘤𝘢𝘭 𝘙𝘦𝘢𝘴𝘰𝘯𝘪𝘯…☆48Updated 10 months ago
- ☆43Updated 5 months ago
- M-STAR (Multimodal Self-Evolving TrAining for Reasoning) Project. Diving into Self-Evolving Training for Multimodal Reasoning☆56Updated 3 months ago
- [EMNLP 2024] mDPO: Conditional Preference Optimization for Multimodal Large Language Models.☆70Updated 4 months ago
- ☆19Updated last month
- [ICML 2024] Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibrati…☆33Updated 9 months ago
- [ICLR 2025] The official pytorch implement of "Dynamic-LLaVA: Efficient Multimodal Large Language Models via Dynamic Vision-language Cont…☆26Updated 4 months ago
- ☆48Updated 4 months ago
- ☆12Updated 8 months ago
- FeatureAlignment = Alignment + Mechanistic Interpretability☆28Updated 3 weeks ago
- MoCLE (First MLLM with MoE for instruction customization and generalization!) (https://arxiv.org/abs/2312.12379)☆34Updated 11 months ago
- Official code for ICML 2024 paper on Persona In-Context Learning (PICLe)☆23Updated 9 months ago
- ☆27Updated last year
- ☆13Updated 8 months ago
- Official code for Guiding Language Model Math Reasoning with Planning Tokens☆11Updated last year
- The repository of the project "Fine-tuning Large Language Models with Sequential Instructions", code base comes from open-instruct and LA…☆29Updated 4 months ago
- Official implementation of Bootstrapping Language Models via DPO Implicit Rewards☆43Updated 8 months ago
- [NeurIPS 2024 Spotlight] Code and data for the paper "Finding Transformer Circuits with Edge Pruning".☆47Updated 3 weeks ago
- Code and datasets for "What’s “up” with vision-language models? Investigating their struggle with spatial reasoning".☆44Updated last year
- Code & Data for our Paper "Alleviating Hallucinations of Large Language Models through Induced Hallucinations"☆63Updated last year
- The official repository of "Improving Large Language Models via Fine-grained Reinforcement Learning with Minimum Editing Constraint"☆37Updated last year
- This is the official repo for Towards Uncertainty-Aware Language Agent.☆24Updated 7 months ago
- Less is More: Mitigating Multimodal Hallucination from an EOS Decision Perspective (ACL 2024)☆45Updated 5 months ago
- ☆25Updated 2 years ago