9 papers
Attention Sinks in VLMs Are Borrowed, Not Seen
Dengjia Zhang, Alexander Martin, Pengyu Yan +6
We study how to detect and mitigate visual attention sinks in vision-language models (VLMs). Visual attention sinks are image tokens that absorb a large share of attention over the…
Multilingual Reasoning Cascades Need More Context
Arnav Mazumder, Dengjia Zhang, Shuyue Stella Li +2
Translation cascades for reasoning translate the query from another language to English, reason in English, and translate the answer back to the original language. This is a compet…
Findings of the MAGMaR 2026 Shared Task
Alexander Martin, Dengjia Zhang, Joel Brogan +7
This overview paper presents the results of the shared task for the second workshop on Multimodal Augmented Generation via Multimodal Retrieval (MAGMaR). In this shared task partic…
Diagnosing Multi-step Reasoning Failures in Black-box LLMs via Stepwise Confidence Attribution
Xiaoou Liu, Tiejin Chen, Dengjia Zhang +3
Large Language Models have achieved strong performance on reasoning tasks with objective answers by generating step-by-step solutions, but diagnosing where a multi-step reasoning t…
MARQUIS: A Three-Stage Pipeline for Video Retrieval-Augmented Generation
Debashish Chakraborty, Dengjia Zhang, Jialiang Jin +7
Retrieval-augmented generation from videos requires systems to retrieve relevant audiovisual evidence from large corpora and synthesize it into coherent, attributed text. Current a…
Unified Multimodal Uncertain Inference
Dengjia Zhang, Alexander Martin, William Jurayj +3
We introduce Unified Multimodal Uncertain Inference (UMUI), a multimodal inference task spanning text, audio, and video, where models must produce calibrated probability estimates…
SELAUR: Self Evolving LLM Agent via Uncertainty-aware Rewards
Dengjia Zhang, Xiaoou Liu, Lu Cheng +3
Large language models (LLMs) are increasingly deployed as multi-step decision-making agents, where effective reward design is essential for guiding learning. Although recent work e…
HLTCOE Evaluation Team at TREC 2025: VQA Track
Dengjia Zhang, Charles Weng, Katherine Guerrerio +5
The HLTCOE Evaluation team participated in TREC VQA's Answer Generation (AG) task, for which we developed a listwise learning framework that aims to improve semantic precision and…
Seeing Through the MiRAGE: Evaluating Multimodal Retrieval Augmented Generation
Alexander Martin, William Walden, Reno Kriz +5
We introduce MiRAGE, an evaluation framework for retrieval-augmented generation (RAG) from multimodal sources. As audiovisual media becomes a more prevalent source of information o…