activity
20242026
collaborators

5 papers

eess.IV2026

Practical Lossless Volumetric Medical Image Compression via Tri-plane Context Tree Learning

Yuanchao Bai, Yifan Zhao, Kai Wang +5

Lossless compression of volumetric medical images is of paramount importance for clinical and research applications where data fidelity is essential. Traditional compression method…

eess.SP2026

Graph-Guided Adaptive Channel Elimination for KV Cache Compression

Enwei Tong, Yao Zhu, Yuanchao Bai +3

Large Language Models have revolutionized natural language processing, achieving unprecedented success across a vast range of tasks. However, their practical application in long-co…

cs.MM2026

ControlFoley: Unified and Controllable Video-to-Audio Generation with Cross-Modal Conflict Handling

Jianxuan Yang, Xinyue Guo, Zhi Cheng +10

Recent advances in video-to-audio (V2A) generation enable high-quality audio synthesis from visual content, yet achieving robust and fine-grained controllability remains challengin…

cs.CV2025

Rethinking Autoregressive Models for Lossless Image Compression via Hierarchical Parallelism and Progressive Adaptation

Daxin Li, Yuanchao Bai, Kai Wang +3

Autoregressive (AR) models, the theoretical performance benchmark for learned lossless image compression, are often dismissed as impractical due to prohibitive computational cost.…

cs.CV2024

CALLIC: Content Adaptive Learning for Lossless Image Compression

Daxin Li, Yuanchao Bai, Kai Wang +3

Learned lossless image compression has achieved significant advancements in recent years. However, existing methods often rely on training amortized generative models on massive da…