Paper Archive

Soumitra Kundu, Gargi Panda, Saumik Bhattacharya, Aurobinda Routray, Rajlakshmi Guha 10/31/2025 arxiv

Non-contact electrocardiogram (ECG) reconstruction from radar signals offers a promising approach for unobtrusive cardiac monitoring. We present LifWavNet, a lifting wavelet network based on a multi-resolution analysis and synthesis (MRAS) model for radar-to-ECG reconstruction. Unlike prior models t...

Chenze Shao, Darren Li, Fandong Meng, Jie Zhou 10/31/2025 arxiv

The efficiency of large language models (LLMs) is fundamentally limited by their sequential, token-by-token generation process. We argue that overcoming this bottleneck requires a new design axis for LLM scaling: increasing the semantic bandwidth of each generative step. To this end, we introduce Co...

Xiangyu Fan, Zesong Qiu, Zhuguanyu Wu, Fanzhou Wang, Zhiqian Lin, Tianxiang Ren, Dahua Lin, Ruihao Gong, Lei Yang 10/31/2025 arxiv

Distribution Matching Distillation (DMD) distills score-based generative models into efficient one-step generators, without requiring a one-to-one correspondence with the sampling trajectories of their teachers. However, limited model capacity causes one-step distilled models underperform on complex...

Danyal Maqbool, Changhee Lee, Zachary Huemann, Samuel D. Church, Matthew E. Larson, Scott B. Perlman, Tomas A. Romero, Joshua D. Warner, Meghan Lubner, Xin Tie, Jameson Merkow, Junjie Hu, Steve Y. Cho, Tyler J. Bradshaw 10/31/2025 arxiv

Recent advances in vision-language models (VLMs) have enabled impressive multimodal reasoning, yet most medical applications remain limited to 2D imaging. In this work, we extend VLMs to 3D positron emission tomography and computed tomography (PET/CT), a domain characterized by large volumetric data...

Bo Li, Duyuan Zheng, Xinyang Liu, Qingwen Li, Hong Li, Hongyan Cui, Ge Gao, Chen Liu 10/31/2025 arxiv

Person re-identification (ReID) in surveillance is challenged by occlusion, viewpoint distortion, and poor image quality. Most existing methods rely on complex modules or perform well only on clear frontal images. We propose Sh-ViT (Shuffling Vision Transformer), a lightweight and robust model for o...

Caleb Ziems, William Held, Jane Yu, Amir Goldberg, David Grusky, Diyi Yang 10/31/2025 arxiv

To serve global users safely and productively, LLMs need culture-specific knowledge that might not be learned during pre-training. How do we find such knowledge that is (1) salient to in-group users, but (2) unknown to LLMs? The most common solutions are single-initiative: either researchers define ...

Wei Zhang, Zekun Guo, Yingce Xia, Peiran Jin, Shufang Xie, Tao Qin, Xiang-Yang Li 10/31/2025 arxiv

Structure-based drug design (SBDD), which maps target proteins to candidate molecular ligands, is a fundamental task in drug discovery. Effectively aligning protein structural representations with molecular representations, and ensuring alignment between generated drugs and their pharmacological pro...

Samuel Degnan-Morgenstern, Alexander E. Cohen, Rajeev Gopal, Megan Gober, George J. Nelson, Peng Bai, Martin Z. Bazant 10/31/2025 arxiv

Operando microscopy provides direct insight into the dynamic chemical and physical processes that govern functional materials, yet measurement noise limits the effective resolution and undermines quantitative analysis. Here, we present a general framework for integrating unsupervised deep learning-b...

Dong Heon Han, Xiaohao Xu, Yuxi Chen, Yusheng Zhou, Xinqi Zhang, Jiaqi Wang, Daniel Bruder, Xiaonan Huang 10/31/2025 arxiv

Biological systems, such as the octopus, exhibit masterful cross-scale manipulation by adaptively reconfiguring their entire form, a capability that remains elusive in robotics. Conventional soft grippers, while compliant, are mostly constrained by a fixed global morphology, and prior shape-morphing...

Tom Sprunck, Marcelo Pereyra, Tobias Liaudat 10/31/2025 arxiv

Modern imaging techniques heavily rely on Bayesian statistical models to address difficult image reconstruction and restoration tasks. This paper addresses the objective evaluation of such models in settings where ground truth is unavailable, with a focus on model selection and misspecification diag...