conftrace_
← Core AI
Artificial Intelligence › Core AI ›

Interpretability

7,318 papers

Papers per year

Papers

Quality-Informed Segment-Level Error Correction Using Natural Language Explanations from xTower and Large Language Models EMNLP 2025
Who is a Better Talker: Subjective and Objective Quality Assessment for AI-Generated Talking Heads ICCV 2025
Why LVLMs Are More Prone to Hallucinations in Longer Responses: The Role of Context ICCV 2025
CE-FAM: Concept-Based Explanation via Fusion of Activation Maps ICCV 2025
Learnable Fractional Reaction-Diffusion Dynamics for Under-Display ToF Imaging and Beyond ICCV 2025
Processing and acquisition traces in visual encoders: What does CLIP know about your camera? ICCV 2025
Revelio: Interpreting and leveraging semantic information in diffusion models ICCV 2025
VisRL: Intention-Driven Visual Perception via Reinforced Reasoning ICCV 2025
3DGraphLLM: Combining Semantic Graphs and Large Language Models for 3D Scene Understanding ICCV 2025
AIGI-Holmes: Towards Explainable and Generalizable AI-Generated Image Detection via Multimodal Large Language Models ICCV 2025
MINERVA: Evaluating Complex Video Reasoning ICCV 2025
Active Membership Inference Test (aMINT): Enhancing Model Auditability with Multi-Task Learning. ICCV 2025
Constructing Ophthalmic MLLM for Positioning-diagnosis Collaboration Through Clinical Cognitive Chain Reasoning ICCV 2025
Where, What, Why: Towards Explainable Driver Attention Prediction ICCV 2025
Analyzing Finetuning Representation Shift for Multimodal LLMs Steering ICCV 2025
Looking in the Mirror: A Faithful Counterfactual Explanation Method for Interpreting Deep Image Classification Models ICCV 2025
On the Generalization of Representation Uncertainty in Earth Observation ICCV 2025
TAB: Transformer Attention Bottlenecks enable User Intervention and Debugging in Vision-Language Models ICCV 2025
Region-Level Data Attribution for Text-to-Image Generative Models ICCV 2025
ReCoT: Reflective Self-Correction Training for Mitigating Confirmation Bias in Large Vision-Language Models ICCV 2025
Teaching AI the Anatomy Behind the Scan: Addressing Anatomical Flaws in Medical Image Segmentation with Learnable Prior ICCV 2025
LeGrad: An Explainability Method for Vision Transformers via Feature Formation Sensitivity ICCV 2025
SIC: Similarity-Based Interpretable Image Classification with Neural Networks ICCV 2025
Transparent Vision: A Theory of Hierarchical Invariant Representations ICCV 2025
SHIFT: Smoothing Hallucinations by Information Flow Tuning for Multimodal Large Language Models ICCV 2025