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."☆41Updated 6 months ago
- ☆59Updated 7 months ago
- ☆28Updated last year
- AdaRFT: Efficient Reinforcement Finetuning via Adaptive Curriculum Learning☆18Updated last week
- Official Pytorch implementation of "Interpreting and Editing Vision-Language Representations to Mitigate Hallucinations" (ICLR '25)☆66Updated last month
- RAG-RewardBench: Benchmarking Reward Models in Retrieval Augmented Generation for Preference Alignment☆16Updated 4 months ago
- [EMNLP 2024] mDPO: Conditional Preference Optimization for Multimodal Large Language Models.☆72Updated 5 months ago
- [NAACL'25 Oral] Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering☆53Updated 4 months ago
- A Dynamic Visual Benchmark for Evaluating Mathematical Reasoning Robustness of Vision Language Models☆19Updated 4 months ago
- In-Context Sharpness as Alerts: An Inner Representation Perspective for Hallucination Mitigation (ICML 2024)☆57Updated last year
- [ICML 2024] Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibrati…☆36Updated 9 months ago
- [NeurIPS 2024] Calibrated Self-Rewarding Vision Language Models☆71Updated 10 months ago
- [NAACL 2024] Vision language model that reduces hallucinations through self-feedback guided revision. Visualizes attentions on image feat…☆44Updated 8 months ago
- ☆53Updated 5 months ago
- The repository of the project "Fine-tuning Large Language Models with Sequential Instructions", code base comes from open-instruct and LA…☆29Updated 5 months ago
- ☆10Updated 2 months ago
- [𝐄𝐌𝐍𝐋𝐏 𝐅𝐢𝐧𝐝𝐢𝐧𝐠𝐬 𝟐𝟎𝟐𝟒 & 𝐀𝐂𝐋 𝟐𝟎𝟐𝟒 𝐍𝐋𝐑𝐒𝐄 𝐎𝐫𝐚𝐥] 𝘌𝘯𝘩𝘢𝘯𝘤𝘪𝘯𝘨 𝘔𝘢𝘵𝘩𝘦𝘮𝘢𝘵𝘪𝘤𝘢𝘭 𝘙𝘦𝘢𝘴𝘰𝘯𝘪𝘯…☆49Updated 11 months ago
- ABC: Achieving Better Control of Multimodal Embeddings using VLMs☆10Updated 2 weeks ago
- M-STAR (Multimodal Self-Evolving TrAining for Reasoning) Project. Diving into Self-Evolving Training for Multimodal Reasoning☆56Updated 3 months ago
- Enhancing Large Vision Language Models with Self-Training on Image Comprehension.☆65Updated 10 months ago
- Official code for ICML 2024 paper on Persona In-Context Learning (PICLe)☆23Updated 9 months ago
- Less is More: Mitigating Multimodal Hallucination from an EOS Decision Perspective (ACL 2024)☆46Updated 5 months ago
- ☆16Updated 4 months ago
- Public code repo for COLING 2025 paper "Aligning LLMs with Individual Preferences via Interaction"☆26Updated 2 weeks ago
- ☆34Updated last month
- Official code for Guiding Language Model Math Reasoning with Planning Tokens☆11Updated last year
- A Survey on the Honesty of Large Language Models☆57Updated 4 months ago
- EMNLP2023 - InfoSeek: A New VQA Benchmark focus on Visual Info-Seeking Questions☆22Updated 10 months ago
- Code and data for "Timo: Towards Better Temporal Reasoning for Language Models" (COLM 2024)