activity
20242026
collaborators
Showing cs.LGShow all

5 papers · 1 filter

cs.LG2026

Interpretable GOHR Agents via Sparse Autoencoders

Shiwei Tan, Yusong Zhao, Weiyi Qin +6

A central challenge in interpreting learned decision-making systems is to determine whether their internal representations contain concepts that help explain their behavior. We rep…

cs.LG2026

Causal Decoding for Hallucination-Resistant Multimodal Large Language Models

Shiwei Tan, Hengyi Wang, Weiyi Qin +3

Multimodal Large Language Models (MLLMs) deliver detailed responses on vision-language tasks, yet remain susceptible to object hallucination (introducing objects not present in the…

cs.LG2024

Variational Language Concepts for Interpreting Foundation Language Models

Hengyi Wang, Shiwei Tan, Zhiqing Hong +2

Foundation Language Models (FLMs) such as BERT and its variants have achieved remarkable success in natural language processing. To date, the interpretability of FLMs has primarily…

cs.LG2024

Probabilistic Conceptual Explainers: Trustworthy Conceptual Explanations for Vision Foundation Models

Hengyi Wang, Shiwei Tan, Hao Wang

Vision transformers (ViTs) have emerged as a significant area of focus, particularly for their capacity to be jointly trained with large language models and to serve as robust visi…

cs.LG2024

Multimodal Needle in a Haystack: Benchmarking Long-Context Capability of Multimodal Large Language Models

Hengyi Wang, Haizhou Shi, Shiwei Tan +6

Multimodal Large Language Models (MLLMs) have shown significant promise in various applications, leading to broad interest from researchers and practitioners alike. However, a comp…