CRAFT: Causal Responsibility and Failure Tracing in Medical Vision Language Models
cs.CV, cs.AI
Submitted: 2026-09-30
Updated: 2026-10-02
Terminology
Sources
- AttnLRP: Attention-Aware Layer-Wise Relevance Propagation for Transformers
- Qwen3-VL Technical Report
- Qwen2.5-VL Technical Report
- Eliciting Latent Predictions from Transformers with the Tuned Lens
- Localizing Model Behavior with Path Patching
- What Do VLMs NOTICE? A Mechanistic Interpretability Pipeline for Gaussian-Noise-free Text-Image Corruption and Evaluation
- The Llama 3 Herd of Models
- Hulu-Med: A Transparent Generalist Model towards Holistic Medical Vision-Language Understanding
- Taming Knowledge Conflicts in Language Models
- Towards Interpreting Visual Information Processing in Vision-Language Models
- In-context Learning and Induction Heads
- Where Knowledge Collides: A Mechanistic Study of Intra-Memory Knowledge Conflict in Language Models
- Steering Large Language Models using Conceptors: Improving Addition-Based Activation Engineering
- InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency
- Assessing and Mitigating Medical Knowledge Drift and Conflicts in Large Language Models
- Retrieval Head Mechanistically Explains Long-Context Factuality
- Qwen3 Technical Report
- CCD: Mitigating Hallucinations in Radiology MLLMs via Clinical Contrastive Decoding
- Mitigating Object Hallucination in Large Vision-Language Models via Image-Grounded Guidance
- Representation Engineering: A Top-Down Approach to AI Transparency
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models