Abstraction Alignment: Comparing Model-Learned and Human-Encoded Conceptual Relationshipsby Angie Boggust, Hyemin Bang, Hendrik Strobelt, Arvind…
Contrastive Adversarial Training for Unsupervised Domain Adaptationby Jiahong Chen, Zhilin Zhang, Lucy Li, Behzad Shahrasbi,…
Object-Aware Query Perturbation for Cross-Modal Image-Text Retrievalby Naoya Sogi, Takashi Shibata, Makoto TeraoFirst submitted to…
Analyzing the Generalization and Reliability of Steering Vectorsby Daniel Tan, David Chanin, Aengus Lynch, Dimitrios…
Distribution Alignment for Fully Test-Time Adaptation with Dynamic Online Data Streamsby Ziqiang Wang, Zhixiang Chi,…
Does Refusal Training in LLMs Generalize to the Past Tense?by Maksym Andriushchenko, Nicolas FlammarionFirst submitted…
Rethinking Fair Graph Neural Networks from Re-balancingby Zhixun Li, Yushun Dong, Qiang Liu, Jeffrey Xu…