7 papers
VKnowU: Evaluating Visual Knowledge Understanding in Multimodal LLMs
Tianxiang Jiang, Sheng Xia, Yicheng Xu +5
While Multimodal Large Language Models (MLLMs) have become adept at recognizing objects, they often lack the intuitive, human-like understanding of the world's underlying physical…
Temporal-Spectral Alignment with Frequency Adaptation for Source-Free Time-Series Adaptation
Shichang Meng, Linquan Wu, Xuan Ai +1
The goal of source-free domain adaptation (SFDA) for time-series data is to transfer knowledge from a pre-trained source model to an unlabeled target domain without requiring acces…
Mind-Studio: Executable World Models with Lookahead Evaluation for Partially Observable Games
Yifei Dong, Mingen Zheng, Linquan Wu +2
World-model synthesis aims to turn interaction experience into an internal model of environment dynamics. Existing symbolic approaches often fit observed transitions or mixtures of…
Imagine Before You Predict: Interleaved Latent Visual Reasoning for Video Event Prediction
Tianxiang Jiang, Linquan Wu, Sheng Xia +5
Video event prediction (VEP) requires models to infer unobserved future states from partial video evidence. Existing video MLLMs usually verbalize intermediate future reasoning in…
LaViT: Aligning Latent Visual Thoughts for Multi-modal Reasoning
Linquan Wu, Tianxiang Jiang, Yifei Dong +6
Current multimodal latent reasoning often relies on external supervision (e.g., auxiliary images), ignoring intrinsic visual attention dynamics. In this work, we identify a critica…
FaceSleuth-R: Adaptive Orientation-Aware Attention for Robust Micro-Expression Recognition
Linquan Wu, Tianxiang Jiang, Haoyu Yang +5
Micro-expression recognition (MER) has achieved impressive accuracy in controlled laboratory settings. However, its real-world applicability faces a significant generalization clif…