The paper presents a zero‑shot framework for high‑throughput generative video super‑resolution (VSR) that operates on a single high‑end consumer GPU without retraining. It decouples spatial upscaling, handled by a time‑distilled one‑step diffusion backbone, from temporal stabilization, achieved with a lightweight pretrained flow‑based interpolator. A resolution‑aware hybrid attention scheme replaces high‑resolution global attention with neighborhood attention to improve scalability, achieving up to ~32 FPS at 720p and a 44% speedup at 4K on an NVIDIA RTX 4090, while maintaining competitive perceptual quality and temporal consistency on standard VSR benchmarks.
By Georgios Panaretou, Sotirios Chatzis
MoE-ViE introduces a Mixture-of-Experts vision encoder that scales efficiently for image and video understanding, outperforming dense counterparts across various sizes. The study shows fine‑grained MoE topologies provide significant gains, and proposes an auxiliary‑loss‑free balancing variant and a specialized MoE kernel to reduce inference latency. With frame‑level distillation and a novel freezing mechanism, the largest MoE‑ViE model matches state‑of‑the‑art zero‑shot performance while being 1.7× larger and 76% faster, and it outperforms other encoders when paired with a language model on both image and video benchmarks.
VETO (Video Efficient Token Optimization for Vision Language Models) is a plug‑in that reduces the quadratic cost of visual tokens in long‑video inference by applying dual‑axis compression: an intra‑frame compressor merges semantically similar tokens within each frame, and an inter‑frame compressor merges temporally redundant frames. By first compressing spatial dimensions, VETO lowers the cost of subsequent global temporal matching, surpassing single‑axis methods and achieving up to 45% faster inference on models such as LLaVA‑OneVision‑7B while maintaining or improving accuracy. The approach is universally applicable across LLaVA‑OneVision, InternVL‑2.5, and LongVA, preserving or enhancing zero‑shot accuracy even under extreme token budgets.
By Gueter Josmy Faure, Hao Ping Wang, Min-Hung Chen, Winston H. Hsu
arXiv:2607. 00687v1 Announce Type: cross Abstract: Comparing transformer backbones for image segmentation is confounded: each is paired with a different decoder, recipe, and pretraining, so reported differences rarely reflect the backbone itself.
By Tobias Christian Nauen, Anosh Billimoria, Federico Raue, Stanislav Frolov, Brian B. Moser, Andreas Dengel
arXiv:2607. 24570v1 Announce Type: cross Abstract: Large-scale video platforms process millions of uploads hourly, requiring moderation systems that can localize when and where policy violations occur within each video.
By Jiameng Zhang, Srikanth Madikeri
arXiv:2605.08158v2 Announce Type: replace-cross
Abstract: Long video understanding with multimodal language models suffers from three compounding bottlenecks: heavy decode cost to obtain dense RGB fr...
By Haopeng Jin, Wenlong Zhao, Tao Yu, Tiankun Yang, Zhenyu Guan, ShiQuan Dong, Yujia Yang, Shani Ye, Chubin Chen, Hongzhu Yi, Jinwen Luo