collaborators

7 papers

cs.CL2026

Context-Aware RL for Agentic and Multimodal LLMs

Peiyang Xu, Bangzheng Li, Sijia Liu +4

Large language models (LLMs) often fail when answering requires identifying a small but decisive piece of evidence within a long or complex context, such as a single line in a tool…

cs.CV2026

WorldBench: A Challenging and Visually Diverse Multimodal Reasoning Benchmark

Yida Yin, Harish Krishnakumar, Chung Peng Lee +9

In real-world applications, models are expected to perform reliably across diverse settings. Yet, many existing multimodal benchmarks expand task types without capturing the visual…

cs.LG2026

From Parameters to Data: A Task-Parameter-Guided Fine-Tuning Pipeline for Efficient LLM Alignment

Hao Chen, Qi Zhang, Liyao Li +7

Adapting Large Language Models (LLMs) to specialized domains typically incurs high data and computational overhead. While prior efficiency efforts have largely treated data selecti…

cs.CV2026

When Vision Speaks for Sound

Xiaofei Wen, Wenjie Jacky Mo, Xingyu Fu +6

Despite rapid progress in video-capable MLLMs, we find that their apparent audio understanding in videos is often vision-driven: models rely on visual cues to infer or hallucinate…

cs.CL2026

DataProphet: Demystifying Supervision Data Generalization in Multimodal LLMs

Xuan Qi, Luxi He, Dan Roth +1

Conventional wisdom for selecting supervision data for multimodal large language models (MLLMs) is to prioritize datasets that appear similar to the target benchmark, such as text-…

cs.CV2025

Learning Human-Perceived Fakeness in AI-Generated Videos via Multimodal LLMs

Xingyu Fu, Siyi Liu, Yinuo Xu +13

Can humans identify AI-generated (fake) videos and provide grounded reasons? While video generation models have advanced rapidly, a critical dimension -- whether humans can detect…