collaborators

16 papers

cs.CV2026

Searching Videos as Trees: Self-Correcting Agents for Grounded Long Video QA

Ce Zhang, Ziyang Wang, Yulu Pan +6

Grounded long-video question answering (Grounded LVQA) requires answering a question about a long video while localizing the short evidence interval that supports the answer. Recen…

cs.CV2026

Mixture of Probes: Learning from Privileged Modalities in Multimodal LLMs Through Probing

Dominick Reilly, Qiyu Wu, Hiromi Wakaki +2

Multimodal Large Language Models (MLLMs) are typically designed under the assumption that all modalities available during training will also be accessible at inference. However, ma…

cs.LG2026

DynaVieW: Schema-Guided World Modeling for Understanding Hierarchical Visual Dynamics

Silin Gao, Hao Zhao, Zeming Chen +8

Multimodal LLMs struggle to systematically model the temporal evolution of visual scenes in videos or multi-image sequences. Such inputs require models to predict or simulate multi…

cs.CL2026

MusTBENCH: Benchmarking and Advancing Temporal Grounding in Music LLMs

Daeyong Kwon, Qiyu Wu, Shinobu Kuriya +6

Recent Large Audio-Language Models (LALMs) have demonstrated promising abilities in understanding musical content. However, whether their responses are grounded in the correct temp…

cs.CL2026

Learning to Route Languages for Multilingual Policy Optimization

Geyang Guo, Hiromi Wakaki, Yuki Mitsufuji +2

Large language models~(LLMs) are trained on heterogeneous multilingual corpora, yet existing policy optimization methods often implicitly restrict each training question to a singl…

cs.LG2025

Demystifying MaskGIT Sampler and Beyond: Adaptive Order Selection in Masked Diffusion

Satoshi Hayakawa, Yuhta Takida, Masaaki Imaizumi +2

Masked diffusion models have shown promising performance in generating high-quality samples in a wide range of domains, but accelerating their sampling process remains relatively u…