3 papers
cs.CV2026
Ultra Flash: Scaling Real-Time Streaming Video Generation to High Resolutions
Luxury, Jie Huang, Zihao Fan +25
While recent autoregressive video diffusion models achieve remarkable streaming quality, they remain confined to low resolutions (e.g., 480P), leaving efficient, scalable, real-tim…
cs.LG2026
SubFlow: Sub-mode Conditioned Flow Matching for Diverse One-Step Generation
Yexiong Lin, Jia Shi, Shanshan Ye +3
Flow matching has emerged as a powerful generative framework, with recent few-step methods achieving remarkable inference acceleration. However, we identify a critical yet overlook…
cs.CV2026
From Inheritance to Saturation: Disentangling the Evolution of Visual Redundancy for Architecture-Aware MLLM Inference Acceleration
Jiaqi Shi, Yuechan Li, Xulong Zhang +2
High-resolution Multimodal Large Language Models (MLLMs) face prohibitive computational costs during inference due to the explosion of visual tokens. Existing acceleration strategi…