Accepted Papers
← Back to workshop homepage
Oral Presentation
1.
Hierarchical Concept Embedding & Pursuit for Interpretable Image Classification
Nghia Nguyen, Tianjiao Ding, Rene Vidal
2.
Do vision language models need to process image tokens?
Sambit Ghosh, Venkatesh Babu Radhakrishnan, Chirag Agarwal
3.
Do VLMs Read or Rewrite?
Gwang Gook Lee, Jay Mohta, Kenan E. Ak, Dimitrios Dimitriadis, Yan Xu
--- ## Poster Presentation
1.
Diverse by Design: Architectural Constraints for Prototype-Based Interpretability
Xinmiao Lin, Matthew Wright
2.
Adaptive Confidence Regularization for Multimodal Failure Detection
Moru Liu, Hao Dong, Olga Fink, Mario Trapp
3.
FaCT: Faithful Concept Traces for Explaining Neural Networks
Amin Parchami-Araghi, Sukrut Rao, Jonas Fischer, Bernt Schiele
4.
SIR: Structured Image Representations for Explainable Robot Learning
Paul Mattes, Jan Schwab, Jens Oliver Bosch, Nils Blank, Maximilian Xiling Li, Minh-Trung Tang, Moritz Haberland, Rudolf Lioutikov
5.
Structured Disentanglement via Concept Bottlenecks: A Framework for Interpretable AI
Tanmoy Mukherjee, Zied Bouraoui
6.
PRIMU: Uncertainty Estimation for Novel Views in Gaussian Splatting from Primitive-Based Representations of Error and Coverage
Thomas Gottwald, Edgar Heinert, Peter Stehr, Chamuditha Jayanga Galappaththige, Matthias Rottmann
7.
Personalized Generative Models for Contextual Debiasing
Xinran Liang, Esin Tureci, Prachi Sinha, Ye Zhu, Vikram V. Ramaswamy, Olga Russakovsky
8.
Beyond Eigenfaces: Distilling Neural Decision Geometry into Simulatable Linear Proxies
Liam Chu
9.
Mitigating Spurious Correlations with Memorization-Guided Coreset Selection
Arda Fazla, Abolfazl Hashemi
10.
When Is Deployment Confidence Recoverable? An Identifiability Frontier for Top-Label Reliability under Shift
Manoj Saravanan
11.
VLM-UQBench: A Benchmark for Modality-Specific and Cross-Modality Uncertainties in Vision Language Models
Chenyu Wang, Tianle Chen, H M Sabbir Ahmad, kayhan Batmanghelich, Wenchao Li
12.
The Geometry of Implicit Bias: Distributed Subspace Encoding in Deep Vision Models
Himanshu Kumar, Sreedath Panat, Raj Dandekar, Rajat Dandekar
13.
Trustworthy Active Learning via Manifold-Preserving Trajectory Sampling
Chenhao wang, Rong Fu, Xi Xiao, Tianyang Wang, JIABAO DOU, Simon James Fong, Kai Li, Yingrui Ji
14.
Improved Vision-Language Alignment via Text-Conditioned Image Embeddings using Sparse Autoencoders
Sweta Mahajan, Sukrut Rao, Jiahao Xie, Alexander Koller, Bernt Schiele
15.
Bias In, Bias Out? Finding Unbiased Subnetworks in Vanilla Models
Ivan Luiz De Moura Matos, Abdel Djalil SAD SAOUD, Ekaterina Iakovleva, Vito Paolo Pastore, Enzo Tartaglione
16.
GridVQA-X: A Framework for Evaluating Multimodal Explainability Methods
Sujay Belsare, Sudarshan Nikhil, Sushant Kumar, Ponnurangam Kumaraguru, Chirag Agarwal
17.
Conformal Video Individual Counting with Statistical Guarantees
Ruixuan Zhang, Stavan Christian, Haoxuan Xie, Juexiao Zhang, Jing Zhang, Kaan Ozbay, Chen Feng
18.
One Perturbation, Two Failure Modes: Probing VLM Safety via Embedding-Guided Typographic Perturbations
Ravikumar Balakrishnan, Sanket Mendapara
19.
MARS-AD: Decision-Aware and Uncertainty-Calibrated Multimodal Representation Learning for Industrial Anomaly Detection
Xiaoyu Deng
20.
Abstain to Assist: Modular and Uncertainty-Aware Hand-Object Video Intelligence for Trustworthy Tremor Assessment
Xinjun Li, Zhenhong Lei