10 papers
VLM-UQBench: A Benchmark for Modality-Specific and Cross-Modality Uncertainties in Vision Language Models
Chenyu Wang, Tianle Chen, H. M. Sabbir Ahmad +2
Uncertainty quantification (UQ) is vital for ensuring that vision-language models (VLMs) behave safely and reliably. A central challenge is to localize uncertainty to its source, d…
Names Don't Matter: Symbol-Invariant Transformer for Open-Vocabulary Learning
İlker Işık, Wenchao Li
Current neural architectures lack a principled way to handle interchangeable tokens, i.e., symbols that are semantically equivalent yet distinguishable, such as bound variables. As…
Rethinking Robustness: A New Approach to Evaluating Feature Attribution Methods
Panagiota Kiourti, Anu Singh, Preeti Duraipandian +2
This paper studies the robustness of feature attribution methods for deep neural networks. It challenges the current notion of attributional robustness that largely ignores the dif…
Anomaly Detection and Generation with Diffusion Models: A Survey
Yang Liu, Jing Liu, Chengfang Li +7
Anomaly detection (AD) plays a pivotal role across diverse domains, including cybersecurity, finance, healthcare, and industrial manufacturing, by identifying unexpected patterns t…
ContextModule: Improving Code Completion via Repository-level Contextual Information
Zhanming Guan, Junlin Liu, Jierui Liu +7
Large Language Models (LLMs) have demonstrated impressive capabilities in code completion tasks, where they assist developers by predicting and generating new code in real-time. Ho…
Semantic Consistency-Based Uncertainty Quantification for Factuality in Radiology Report Generation
Chenyu Wang, Weichao Zhou, Shantanu Ghosh +2
Radiology report generation (RRG) has shown great potential in assisting radiologists by automating the labor-intensive task of report writing. While recent advancements have impro…
Rethinking Inverse Reinforcement Learning: from Data Alignment to Task Alignment
Weichao Zhou, Wenchao Li
Many imitation learning (IL) algorithms use inverse reinforcement learning (IRL) to infer a reward function that aligns with the demonstration. However, the inferred reward functio…
HyQE: Ranking Contexts with Hypothetical Query Embeddings
Weichao Zhou, Jiaxin Zhang, Hilaf Hasson +2
In retrieval-augmented systems, context ranking techniques are commonly employed to reorder the retrieved contexts based on their relevance to a user query. A standard approach is…
Temporal Logic Specification-Conditioned Decision Transformer for Offline Safe Reinforcement Learning
Zijian Guo, Weichao Zhou, Wenchao Li
Offline safe reinforcement learning (RL) aims to train a constraint satisfaction policy from a fixed dataset. Current state-of-the-art approaches are based on supervised learning w…
DeLF: Designing Learning Environments with Foundation Models
Aida Afshar, Wenchao Li
Reinforcement learning (RL) offers a capable and intuitive structure for the fundamental sequential decision-making problem. Despite impressive breakthroughs, it can still be diffi…