FAVE (Foveated Adaptive Visual Encoding) is a lightweight, variable‑resolution Vision Transformer that encodes user‑selected image regions at high acuity while maintaining the image’s native geometry. In controlled experiments on small‑object ImageNet crops, FAVE outperforms a fixed‑resolution ViT by 9.4 top‑1 points while using 12.7× fewer FLOPs. When added as a local branch to FastVLM, FAVE improves TextVQA by 1.60 points and GQA attribute accuracy by 1.31 points, achieving a 3.3× speedup over SmolVLM2-2.2B with only 16 extra local tokens.
By Amitangshu Mukherjee, Kaushik Roy
arXiv:2609.00798v1 Announce Type: new
Abstract: Pixel-space diffusion has recently emerged as a promising direction for high-fidelity image generation by modeling images directly in the original pixe...
By Weiyi You, Jinhua Zhang, Xingyu Zhou, Wei Long, Junyu Lou, Shuhang Gu
arXiv:2609.23169v1 Announce Type: new
Abstract: High-quality texture generation is essential for creating realistic and production-ready 3D assets. Recent multi-view diffusion methods have shown prom...
By Yibo Zhang, Ze Yuan, Nan Cao, Li Zhang, Yan-Pei Cao, Yuan-Chen Guo, Rui Ma
arXiv:2606. 00746v1 Announce Type: cross Abstract: Vision foundation models are bottlenecked by the quadratic cost of self-attention, which limits usable resolution and increases the cost of large-scale pretraining.
By Yitong Jiang, Hongjun Wang, Collin McCarthy, Hanrong Ye, David Wehr, Xinhao Li, Qi Dou, Tianfan Xue, Ka Chun Cheung, Simon See, Wonmin Byeon, Ke Chen, Kai Han, Jinwei Gu, Hongxu Yin, Pavlo Molchanov, Jan Kautz, Sifei Liu
arXiv:2511. 18050v1 Announce Type: cross Abstract: Diffusion transformers have recently delivered strong text-to-image generation around 1K resolution, but we show that extending them to native 4K across diverse aspect ratios exposes a tightly coupled failure mode spanning positional encoding, VAE compression, and optimization.
By Tian Ye, Song Fei, Lei Zhu
arXiv:2604. 05182v2 Announce Type: replace-cross Abstract: We introduce the Large Sparse Reconstruction Model to study how scaling transformer context windows affects feed-forward 3D reconstruction.
By Zhengqin Li, Cheng Zhang, Jakob Engel, Zhao Dong
The paper introduces AttWarp, a lightweight technique that uses a multimodal large language model’s cross‑modal attention to perform rectilinear warping of input images at test time. By reallocating spatial resolution toward query‑relevant regions without altering model weights or architecture, AttWarp preserves global context while making small objects and subtle relationships easier for the model to read. Experiments on five benchmarks and four MLLMs show consistent accuracy gains, improved compositional reasoning, and reduced hallucinations compared to baseline image‑manipulation methods.
By Dwip Dalal, Gautam Vashishtha, Utkarsh Mishra, Jeonghwan Kim, Madhav Kanda, Hyeonjeong Ha, Svetlana Lazebnik, Heng Ji, Unnat Jain
arXiv:2608. 08713v1 Announce Type: cross Abstract: Vision-language models offer a promising path toward automating radiology report generation, but applying them to full 3D CT volumes poses substantial computational challenges.
By Jonathan Suprijadi, Raphael Stock, Moritz Langenberg, David Zimmerer, Kim-Celine Kahl, Stefan Denner, Yannick Kirchhoff, Karol Gotkowski, Maximilian Rokuss, Jeremias Traub, Tassilo Wald, Constantin Ulrich, Klaus Maier-Hein
arXiv:2510. 00054v3 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) have made significant strides in visual understanding tasks.
By Xianjie Liu, Yiman Hu, Yixiong Zou, Liang Wu, Jian Xu, Bo Zheng
arXiv:2609.22379v1 Announce Type: new
Abstract: High-resolution orbital imagery offers a rich record of the Martian surface, but sparse geological labels limit supervised representation learning. We...
By Akshay Naik, Marius F. R. Juston, Jay Mahajan
DART is a new RGB‑D pretraining method for surgical vision foundation models that incorporates pseudo‑labeled depth maps as a pixel‑space reconstruction target during training. By adding a depth reconstruction head to DINOv2’s masked iBOT framework, DART improves representation quality without affecting downstream RGB‑only fine‑tuning or inference. Across eight surgical benchmarks—including segmentation, depth estimation, and image‑level recognition—DART outperforms both natural‑image and in‑domain baselines, demonstrating that geometric pseudo‑labels can strengthen foundation model pretraining without extra labels or inference cost.
By John J. Han, Adam Schmidt, Muhammad Abdullah Jamal, Jie Ying Wu, Omid Mohareri
arXiv:2609.06490v1 Announce Type: cross
Abstract: Recursive Super-Resolution (SR) extends fixed-scale SR to extreme magnification by repeatedly feeding predictions back into the same model, analogous...
By Shubhashis Roy Dipta, Sourajit Saha, Shaswati Saha, Nobin Sarwar