ProgResViT is an input‑adaptive Vision Transformer that processes images progressively across multiple rounds, starting with a low‑resolution image and a narrow subnetwork and refining the prediction with higher resolution and a wider subnetwork if needed. The method introduces Progress‑Conditioned Soft Gating (PSG) to share a single backbone across rounds while conditioning token fusion and layer outputs on the current round, block, and input resolution. Experiments on DeiT show improved accuracy‑compute trade‑offs compared to adaptive‑width, adaptive‑depth, and dynamic‑token baselines, and the design also benefits self‑supervised DINO representations and downstream semantic segmentation.
By Ali Hojjat, Janek Haberer, Olaf Landsiedel
The paper introduces Gated Token Recurrence (GTR), a softmax‑free recurrent vision backbone that replaces global softmax attention with gated linear attention, alternating scan directions, and enhanced SwiGLU blocks. GTR is distilled from a DINOv3 teacher using only final‑layer patch‑token alignment, and achieves strong performance on COCO object detection (58.9 box AP) with very low latency (1.908 ms on an RTX 4090). The backbone also transfers to multiple dense prediction tasks and runs efficiently on edge hardware via a specialized CUDA operator and TensorRT deployment.
By Zhe Feng, Longfei Liu, Wei Liu, Kai Chen, Jiangjiang Kong, Wei Zhou, Yifeng Qian, Dexiong Chen, Xuanlong Yu, Xi Shen
arXiv:2605.15195v2 Announce Type: replace
Abstract: Recent feed-forward reconstruction models, such as VGGT, have proven competitive with traditional optimization-based reconstructors while also prov...
By Jianyuan Wang, Minghao Chen, Shangzhan Zhang, Nikita Karaev, Johannes Sch\"onberger, Patrick Labatut, Piotr Bojanowski, David Novotny, Andrea Vedaldi, Christian Rupprecht
arXiv:2605.12006v2 Announce Type: replace
Abstract: The performance of promptable video object segmentation (PVOS) models substantially degrades under input corruptions, which prevents PVOS deploymen...
By Sohyun Lee, Yeho Gwon, Lukas Hoyer, Konrad Schindler, Christos Sakaridis, Suha Kwak
SAM3Dual is a training‑free inference extension of pretrained SAM 3 that won third place in the MOSEv2 track of the 8th Large‑scale Video Object Segmentation Challenge. It separates temporal memory into short‑term and long‑term branches, fuses their responses deterministically, and modulates them with previous‑frame confidence, all while keeping SAM 3 parameters frozen. The approach achieved an official J&F score of 64.37, demonstrating competitive long‑term VOS performance without task‑specific training.
By JeongRae Kim, Chaehyun Kim, Changwon Lim
The paper introduces reViT, a recurrent vision transformer that uses a single Transformer block repeatedly to achieve the accuracy of a full-depth encoder while keeping inference FLOPs comparable. It achieves depth‑specific transformations by expressing each block’s feed‑forward network as a convex combination of a small shared expert bank, with a continuous depth coordinate guiding the mixture. Experiments on ImageNet‑1k and DINOv2 distillation show that reViT matches or surpasses state‑of‑the‑art models, reduces stored parameters by about 70%, and supports elastic‑depth deployment from a single checkpoint.
By Adrian Bulat, Yassine Ouali, Georgios Tzimiropoulos
arXiv:2610.00686v1 Announce Type: new
Abstract: Recent video-based world models pair the scalability of autoregressive (AR) prediction with the visual quality of diffusion models. The choice of scene...
By Mikhail Dereviannykh, Vikram Voleti, Simon Donne, Mallikarjun Byrasandra Ramalinga Reddy, Shimon Vainer, Mark Boss
SCMerge is a training‑free token merging technique for Vision Transformers that jointly considers feature similarity and spatial consistency when pairing tokens. The merged tokens are processed within the encoder and later reconstructed onto the original patch grid during decoding. Experiments on ADE20K, Pascal Context, and Cityscapes demonstrate that SCMerge improves the balance between segmentation accuracy and computational efficiency compared to existing methods.
By Junfeng Ren (Southern University of Science and Technology), Yi Gong (Southern University of Science and Technology), Yuan Zeng (Shenzhen Technology University)
arXiv:2609.23286v1 Announce Type: new
Abstract: 3D reconstruction from a lengthy video stream input poses a dilemma for feed-forward reconstruction models (FFRMs), that a whole-stream inference conte...
By Hongbo Mao (Harbin Institute of Technology), Junjun Jiang (Harbin Institute of Technology), Youyu Chen (Harbin Institute of Technology), Jiaxin Zhang (Harbin Institute of Technology), Zhemeng Dong (Harbin Institute of Technology), Xianming Liu (Harbin Institute of Technology)
The paper investigates whether keeping non‑spatial register tokens in vision transformer decoders improves image reconstruction and generation. Using representation autoencoders with frozen register‑equipped encoders, the authors show that joint self‑attention over both patch and register tokens yields better reconstruction quality on ImageNet‑1K, with lower FID scores and higher PSNRs compared to patch‑only baselines. For generation, a multi‑head attention pooling predictor recovers register features from sampled patches, further reducing FID by nearly 10% over the patch‑only approach.
By David Jacob Drexlin, Julius Hense, Jonas Dippel
arXiv:2609.23733v1 Announce Type: new
Abstract: Feed-forward visual geometry models such as the Visual Geometry Grounded Transformer (VGGT) have recently enabled direct 3D reconstruction from multi-v...
By Abteen Arab, Guile Wu, Chengjie Huang, Dongfeng Bai
arXiv:2607. 13421v1 Announce Type: cross Abstract: Spatio-Temporal Video Grounding (STVG) aims to retrieve the visual trajectory of a specific object from a video stream as described by a natural language expression.
By Kai Chen, Ming Dai, Wenxuan Cheng, Wankou Yang