LoopVAE introduces a recurrent depth architecture that reuses a scale‑ and loop‑conditioned core across different spatial scales while keeping resolution‑changing transitions separate. The four‑block core applies 28 block operations per encoder or decoder, enabling a 29M‑parameter convolutional model to achieve 0.28 rFID and 32.54 dB PSNR on ImageNet‑256 with roughly 65% fewer parameters than comparable VAEs. Experiments with both convolutional and Transformer operators, as well as ablations on parameter sharing, demonstrate competitive image quality metrics and reveal how targeted loop interventions and truncation affect reconstruction quality and computational trade‑offs.
By Zhiying Lu
MT‑WAM enhances the Fast‑WAM framework by adding complementary supervision for future 2‑D point trajectories and visual features while keeping the original training objectives. A lightweight dual‑stream branch and structured attention mask isolate motion‑specific processing, and motion‑stream tokens provide additional dynamics cues to the action expert. During inference, MT‑WAM skips future‑video prediction, using cached video and motion information to achieve higher success rates on LIBERO, LIBERO‑Plus, RoboTwin 2.0 Clean2Rand, and several real‑world tasks.
By Yiguang Yang, Jiankun Peng, Xiaoming Wang, Yiran Zhang, Zhibo Fang
arXiv:2605.12491v2 Announce Type: replace
Abstract: Vision Transformers (ViTs) learn rich visual-semantic representations through all-to-all self-attention among patch tokens. However, this design im...
By Alan Z. Song, Yinjie Chen, Mu Nan, Deva Ramanan, Michael J. Tarr, Andrew F. Luo
arXiv:2608.29126v1 Announce Type: new
Abstract: Referring single-object tracking enables language-grounded target initialization and subsequent tracking by jointly leveraging semantic cues and visual...
By Han Wang, Yuxuan Liu, Yuhan Sun, Jian Yang, Xiaotong Xu, Yixuan Lv, Zhuang Zhou, Shengyang Li
arXiv:2603. 00198v2 Announce Type: replace-cross Abstract: Token reduction accelerates long-video vision--language models (VLMs), but existing methods target Transformers, where reduction is treated as token pruning.
By Jindong Jiang, Amala Sanjay Deshmukh, Kateryna Chumachenko, Karan Sapra, Zhiding Yu, Guilin Liu, Andrew Tao, Pavlo Molchanov, Jan Kautz, Wonmin Byeon
LongVU‑TTT is a causal test‑time training method for long‑video multimodal large language models that inserts a convolutional resampler with fast‑weight updates between the vision encoder and the LLM. The fast weights adapt per video and contextualize frame features before compression, while a hybrid selector keeps explicit visual evidence for downstream reasoning. Experiments show that TTT‑Conv outperforms TTT‑MLP and bidirectional Mamba2 on MLVU, and beats attention‑ and fixed‑state recurrent resamplers on three benchmarks, achieving competitive results on five video‑understanding tasks after reducing 512 frames to 128 LLM frames.
By Mahmoud Ahmed, Sameh Abdulah, Olatunji Ruwase, Sam Ade Jacobs, Mathis Bode, Mohamed Elhoseiny
arXiv:2607. 26596v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) have demonstrated remarkable capabilities by integrating visual and textual understanding within a unified transformer architecture.
By Mingkuan Feng, Zhengqi Wen, Jianhua Tao
arXiv:2605. 16366v2 Announce Type: replace-cross Abstract: Video MLLMs face a persistent tension between spatial fidelity and temporal coverage: preserving fine-grained visual details requires many spatial tokens, while capturing short-lived events requires dense temporal sampling.
By Yigui Feng (The College of Computer Science, National University of Defense Technology, Changsha, Hunan, China), Qinglin Wang (The College of Computer Science, National University of Defense Technology, Changsha, Hunan, China), Yang Liu (The Shien-Ming Wu School of Intelligent Engineering, South China University of Technology, Guangzhou, Guangdong, China), Jie Liu (The College of Computer Science, National University of Defense Technology, Changsha, Hunan, China)
arXiv:2607.01630v2 Announce Type: replace
Abstract: Dynamic expansion methods for class-incremental learning (CIL) protect task-specific knowledge by growing dedicated tokens or subnetworks, yet our...
By Bingchen Huang, Yifu Chen, Zhiling Wang, Yuanchao Du
CrossMambaTuning is a new framework that adapts pretrained learned image compression models to machine vision tasks with minimal retraining. It combines State Space Models with cross‑layer interaction, featuring a Mamba adapter that uses task‑specific prompts and multi‑scale branching, and a Scale‑Invariant Cross‑Layer Adapter (SICA) that shares parameters across scales to reduce redundancy. Experiments show that this approach achieves state‑of‑the‑art performance while cutting parameter overhead by 72% compared to existing methods.
By Haobo Xiong, Shaobo Liu, Kai Liu, Chongyang Ding
Understanding the relationship between deep visual representations and the human visual system is a fundamental challenge in computational neuroscience. While modern vision models achieve strong performance in image recognition, their correspondence with the hierarchical organization of the human visual cortex remains an open question.
arXiv:2606. 04772v1 Announce Type: cross Abstract: Understanding the relationship between deep visual representations and the human visual system is a fundamental challenge in computational neuroscience.
By Hoang-Son Vo, Van-Hung Bui, Minh-Huy Mai-Duc, Tien-Dung Mai, Soo-Hyung Kim