activity
20242026
most citedInformation-Theoretic Optimization for Task-Adapted Compressed Sensing Magnetic Resonance Imaging

1 citations · 1 across the 5 of their papers we have counts for

collaborators

5 papers

cs.LG2026★ 1 cited

Information-Theoretic Optimization for Task-Adapted Compressed Sensing Magnetic Resonance Imaging

Xinyu Peng, Ziyang Zheng, Wenrui Dai +5

Task-adapted compressed sensing magnetic resonance imaging (CS-MRI) is emerging to address the specific demands of downstream clinical tasks with significantly fewer k-space measur…

cs.CV2026

Towards Holistic Modeling for Video Frame Interpolation with Auto-regressive Diffusion Transformers

Xinyu Peng, Han Li, Yuyang Huang +7

Existing video frame interpolation (VFI) methods often adopt a frame-centric approach, processing videos as independent short segments (e.g., triplets), which leads to temporal inc…

cs.CV2025

OneCAT: Decoder-Only Auto-Regressive Model for Unified Understanding and Generation

Han Li, Xinyu Peng, Yaoming Wang +7

We introduce OneCAT, a unified multimodal model that seamlessly integrates understanding, generation, and editing within a novel, pure decoder-only transformer architecture. Our fr…

cs.CV2025

Noise Conditional Variational Score Distillation

Xinyu Peng, Ziyang Zheng, Yaoming Wang +6

We propose Noise Conditional Variational Score Distillation (NCVSD), a novel method for distilling pretrained diffusion models into generative denoisers. We achieve this by reveali…

cs.CV2024

Improving Diffusion Models for Inverse Problems Using Optimal Posterior Covariance

Xinyu Peng, Ziyang Zheng, Wenrui Dai +4

Recent diffusion models provide a promising zero-shot solution to noisy linear inverse problems without retraining for specific inverse problems. In this paper, we reveal that rece…