activity
20232026
collaborators

9 papers

cs.CV2026

Progression as Latent Drift: Generative Forecasting of Slow-Evolving Pathologies

Yuxiang Feng, Juncheng Wang, Chao Xu +7

Forecasting the future anatomy of slow-evolving neurodegenerative diseases could enable earlier, more targeted intervention and improve clinical trial design, but it remains challe…

cs.CV2026

NEWTON: Agentic Planning for Physically Grounded Video Generation

Yuxiang Feng, Juncheng Wang, Chao Xu +7

Video generation models produce visually compelling results but systematically violate physical commonsense -- on VideoPhy-2, the best model achieves only 32.6% joint accuracy. We…

cs.MA2026

AD-CARE: A Guideline-grounded, Modality-agnostic LLM Agent for Real-world Alzheimer's Disease Diagnosis with Multi-cohort Assessment, Fairness Analysis, and Reader Study

Wenlong Hou, Sheng Bi, Guangqian Yang +16

Alzheimer's disease (AD) is a growing global health challenge as populations age, and timely, accurate diagnosis is essential to reduce individual and societal burden. However, rea…

cs.LG2026

Decentralized Attention Fails Centralized Signals: Rethinking Transformers for Medical Time Series

Guoqi Yu, Juncheng Wang, Chen Yang +3

Accurate analysis of medical time series (MedTS) data, such as electroencephalography (EEG) and electrocardiography (ECG), plays a pivotal role in healthcare applications, includin…

cs.CV2025

Exploring Scale Shift in Crowd Localization under the Context of Domain Generalization

Juncheng Wang, Lei Shang, Ziqi Liu +5

Crowd localization plays a crucial role in visual scene understanding towards predicting each pedestrian location in a crowd, thus being applicable to various downstream tasks. How…

cs.SD2025

Language Model Based Text-to-Audio Generation: Anti-Causally Aligned Collaborative Residual Transformers

Juncheng Wang, Chao Xu, Cheng Yu +5

While language models (LMs) paired with residual vector quantization (RVQ) tokenizers have shown promise in text-to-audio (T2A) generation, they still lag behind diffusion-based mo…