Ziwei-Zheng / LVLM-Stethoscope
A library of visualization tools for the interpretability and hallucination analysis of large vision-language models (LVLMs).
☆25Updated 3 months ago
Alternatives and similar repositories for LVLM-Stethoscope:
Users that are interested in LVLM-Stethoscope are comparing it to the libraries listed below
- HalluciDoctor: Mitigating Hallucinatory Toxicity in Visual Instruction Data (Accepted by CVPR 2024)☆44Updated 8 months ago
- ☆11Updated 2 months ago
- [ICML 2024] Official implementation for "HALC: Object Hallucination Reduction via Adaptive Focal-Contrast Decoding"☆85Updated 3 months ago
- ECSO (Make MLLM safe without neither training nor any external models!) (https://arxiv.org/abs/2403.09572)☆23Updated 5 months ago
- Less is More: High-value Data Selection for Visual Instruction Tuning☆11Updated 2 months ago
- [ICLR 2025] PyTorch Implementation of "ETA: Evaluating Then Aligning Safety of Vision Language Models at Inference Time"☆16Updated last month
- The First to Know: How Token Distributions Reveal Hidden Knowledge in Large Vision-Language Models?☆27Updated 5 months ago
- Code for paper: Nullu: Mitigating Object Hallucinations in Large Vision-Language Models via HalluSpace Projection☆20Updated 2 weeks ago
- This is the official repo for Debiasing Large Visual Language Models, including a Post-Hoc debias method and Visual Debias Decoding strat…☆77Updated last month
- An implementation for MLLM oversensitivity evaluation☆13Updated 4 months ago
- [CVPR2024 highlight] Generalized Large-Scale Data Condensation via Various Backbone and Statistical Matching (G-VBSM)☆27Updated 5 months ago
- [CVPR23] "Understanding and Improving Visual Prompting: A Label-Mapping Perspective" by Aochuan Chen, Yuguang Yao, Pin-Yu Chen, Yihua Zha…☆53Updated last year
- ICLR 2024, Towards Lossless Dataset Distillation via Difficulty-Aligned Trajectory Matching☆102Updated 10 months ago
- ☆24Updated last month
- Instruction Tuning in Continual Learning paradigm☆44Updated last month
- [ICML 2024] Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models.☆61Updated 2 months ago
- [CVPR 2025] Mitigating Object Hallucinations in Large Vision-Language Models with Assembly of Global and Local Attention☆27Updated 8 months ago
- ☆35Updated last month
- The official repository for paper "MLLM-Protector: Ensuring MLLM’s Safety without Hurting Performance"☆35Updated 11 months ago
- ☆11Updated 4 months ago
- Evaluate robustness of adaptation methods on large vision-language models☆18Updated last year
- [EMNLP'23] The official GitHub page for ''Evaluating Object Hallucination in Large Vision-Language Models''☆82Updated last year
- [ICLR'25] Official code for the paper 'MLLMs Know Where to Look: Training-free Perception of Small Visual Details with Multimodal LLMs'☆97Updated last week
- The official implementation of "2024NeurIPS Dynamic Tuning Towards Parameter and Inference Efficiency for ViT Adaptation"☆43Updated 3 months ago
- [ICCV 2023 oral] This is the official repository for our paper: ''Sensitivity-Aware Visual Parameter-Efficient Fine-Tuning''.☆66Updated last year
- ☆41Updated last year
- ☆45Updated 4 months ago
- [ICLR2025] γ -MOD: Mixture-of-Depth Adaptation for Multimodal Large Language Models☆33Updated last month
- [CVPR 2024] On the Diversity and Realism of Distilled Dataset: An Efficient Dataset Distillation Paradigm☆64Updated last month
- DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models☆38Updated last week