3 papers
cs.AI2026
When Derived Measurements Mislead: Quantifying and Mitigating LLM Over-Trust with Privileged-Modality Reliability Evidence
Zongheng Guo, Tao Chen, Tianli Li +6
The paper defines and quantifies derived-feature over‑trust (DFOT) where large language models treat derived measurements as direct facts, using physiological sensing (PPG vs. ECG)…
cs.CV2026
TAFG-MAN: Timestep-Adaptive Frequency-Gated Latent Diffusion for Efficient and High-Quality Low-Dose CT Image Denoising
Tangtangfang Fang, Yang Jiao, Xiangjian He +2
Low-dose computed tomography (LDCT) reduces radiation exposure but also introduces substantial noise and structural degradation, making it difficult to suppress noise without erasi…
cs.LG2026
SIGMA-PPG: Statistical-prior Informed Generative Masking Architecture for PPG Foundation Model
Zongheng Guo, Tao Chen, Yang Jiao +3
Current foundation model for photoplethysmography (PPG) signals is challenged by the intrinsic redundancy and noise of the signal. Standard masked modeling often yields trivial sol…