Vision State Space Models

Follow this topic Ask about this topic

Momentum

5 papers in the last four weeks, against 1 the four weeks before. 0.1% of all new papers.

Jul 6Week of Sep 21

Latest papers 30

All topics

When Should the Count Change? Learning State Maintenance for Causal Video Counting
Sep 28, 2026Pengyiang Liu, Dongyue Lyu, Junbo Niu +3Fine-Grained Video Understanding Vision State Space Models
Beihang University · Peking University
Just MLPs: Efficient Visual State Reconstruction for Multimodal Language Models
Sep 28, 2026Jingdi lei, Junxian Li, Di Zhang +3Long Visual-Token Sequences Multimodal Large Language Models
Nanyang Technological University · Shanghai Jiao Tong University · Fudan University +2
Resolving State-Representation Mismatch: State-Space Visual Reasoning for Open-Loop VLA Planning
Sep 27, 2026Junhao Xiao, Haoxiang Zhao, Menghao Fang +8Vision State Space Models Latent Visual Reasoning
FDU · HUST · TJU +2
Token Clustering and Semantic Sequence Mamba for Hyperspectral Image Classification
Sep 23, 2026Yimin Zhu, Mahmood Elahi, Lincoln Linlin XuHyperspectral Image Mamba-Based Models
Department of Geomatics Engineering, University of Calgary, Canada · Department of Electrical and Software Engineering, University of Calgary, Canada
SBMVTrack: Spike-Budgeted Multi-View Learning for Power-Efficient UAV Tracking
Sep 21, 2026Pengzhi Zhong, Jiwei Mo, Haolun Li +4Unmanned Aerial Vehicle Detection Multi-Object Tracking
College of Computer Science and Engineering, Guilin University of Technology, Guilin 541004, China · School of Information Engineering, Wuhan University of Technology, Wuhan 430070, China
Channel-Wise and Token-Aware Post-Training Quantization for Visual State Space Duality
Sep 15, 2026Jonghyeon Lim, Changhoon YimPost-Training Quantization Vision State Space Models
Intelligent Image Processing Laboratory · Department of Computer Science and Engineering, Konkuk University · Seoul, Republic of Korea
OphBiWSSD: Scaling Temporal Action Localization in Ophthalmic Surgeries with Bidirectional Weight-tied State Space Duality
Sep 14, 2026Yang Liu, Qionghong Ma, Joongwon Chae +10Temporal Action Localization Vision State Space Models
Institute of Biopharmaceutics and Health Engineering, Tsinghua Shenzhen International Graduate School, Shenzhen 518055, China · Department of Ophthalmology, The Fifth Affiliated Hospital of Wenzhou Medical University, Wenzhou Medical University, Lishui 323000, China · School of Optometry, The Hong Kong Polytechnic University +4
EgoAfford: Task-Oriented Affordance Grounding via Egocentric Referring Segmentation
Aug 5, 2026Xinyuan Guan, Feifan Chen, Xinyu Zhan +3Egocentric Vision Goal-Conditioned Dynamic Manipulation
Shanghai Jiao Tong University · Shanghai Innovation Institute · Noematrix Ltd
Norm or Direction? Decoding Vision Mambas for High-Resolution Vision
Jul 21, 2026Jin Yu, Juyoun ParkMamba-Based Models Vision State Space Models
Center for Humanoid Research Korea Institute of Science and Technology
A Hybrid Mamba for Audio-Visual Navigation
Jul 14, 2026Yi Wang, Yinfeng YuAudio-Visual Reasoning Object Goal Navigation
School of Computer Science and Technology, Xinjiang University, Urumqi 830017, China. · Joint Research Laboratory for Embodied Intelligence, Xinjiang University. · Joint International Research Laboratory of Silk Road Multilingual Cognitive Computing, Xinjiang University.
Vision Non-Causal Trapezoidal Mamba: Eliminating Directional Scanning in Vision SSMs with Second-Order Dynamics
Jul 3, 2026Anvitha Ramachandran, Dhruv Parikh, Haoyang Fan +2Vision State Space Models Self-Supervised Vision Transformers
University of Southern California · DEVCOM Army Research Office
MambaLIE: Scene Light Intensity-Boosted Low-Light Image Enhancement with State Space Model
Jul 3, 2026Wanshu Fan, Xiangyu Li, Cong Wang +4Low-Light Image Enhancement Vision State Space Models
National and Local Joint Engineering Laboratory of Computer Aided Design, School of Software Engineering, Dalian University, Dalian, China · Hong Kong Polytechnic University, Hong Kong, China · School of Computer Science and Technology, Dalian University of Technology Dalian, China +1
Spatial-Aware Reduction Framework: Towards Efficient and Faithful Visual State Space Models
Jun 18, 2026Jindi Lv, Aoyu Li, Yuhao Zhou +6Vision State Space Models Spatial Tokens
Sichuan University · GigaAI · Tsinghua University
MambaCount: Efficient Text-guided Open-vocabulary Object Counting with Spatial Sparse State Space Duality Block
Jun 16, 2026Hao-Yuan Ma, Li Zhang, Minjie Qiang +1Vision State Space Models Spatial Tokens
School of Computer Science and Technology, Soochow University, Suzhou, China
VICX: Generalizable Robot Manipulation via Video Generation and In-Context Operator Network
Jun 10, 2026Song Chen, Linyan Xiang, Ying Zhou +1Robotic Manipulation Robot Systems
National University of Singapore
Learning Visual Spatial Planning from Symbolic State via Modality-Gap-Aware Self-Distillation
Jun 4, 2026Haocheng Luo, Jiahui Liu, Ruicheng Zhang +6Vision State Space Models Perception Gap
1Tsinghua University · 2The Hong Kong University of Science and Technology
SP-MoMamba: Superpixel-driven Mixture of State Space Experts for Efficient Image Super-Resolution
May 25, 2026Wenbin Zou, Yawen Cui, Yi Wang +5Vision State Space Models Topomamba
Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University, Hong Kong SAR · School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China
Deformba: Vision State Space Model with Adaptive State Fusion
May 20, 2026Hongyu Ke, Jack Morris, Yongkang Liu +4Vision State Space Models Self-Supervised Vision Transformers
Department of Computer Science, Georgia State University · University of Tennessee Knoxville · InfoTech Labs, Toyota Motor North America R&D.
SurgicalMamba: Dual-Path SSD with State Regramming for Online Surgical Phase Recognition
May 14, 2026Sukju Oh, Sukkyu SunSurgical Videos Vision State Space Models
Department of Computer Science and Artificial Intelligence, Dongguk University, Seoul 04620, Republic of Korea
TCP-SSM: Efficient Vision State Space Models with Token-Conditioned Poles
May 12, 2026Sara Shoouri, Morteza Tavakoli Taba, Hun-Seok KimVision State Space Models State Space Models
University of Michigan
Can Graphs Help Vision SSMs See Better?
May 11, 2026Dhruv Parikh, Anvitha Ramachandran, Haoyang Fan +3Vision State Space Models Semantic Segmentation
USC · UT Austin · DEVCOM ARL Army Research Office, USA
EmambaIR: Efficient Visual State Space Model for Event-guided Image Reconstruction
May 8, 2026Wei Yu, Yunhang QianVision State Space Models Image Reconstruction
1Harbin Institute of Technology
Learning Dynamic Evidence Routes for Vision Transformer Probing
Apr 29, 2026Zice Wang, Zhenyu ZhangLong Visual-Token Sequences Vision State Space Models
School of Future Technology Northeastern University Hunnan Campus, Shenyang, China
$\text{PKS}^4$ :Parallel Kinematic Selective State Space Scanners for Efficient Video Understanding
Apr 29, 2026Lingjie Zeng, Hailun Zhang, Xiwen Wang +1Spatio-Temporal Attention Vision State Space Models
College of Computer Science, Sichuan University Chengdu, China
BVI-Mamba: Video Enhancement Using a Visual State-Space Model for Low-Light and Underwater Environments
Apr 26, 2026Guoxi Huang, Ruirui Lin, Yini Li +2Underwater Image Enhancement Methods Vision State Space Models
Visual Information Laboratory, University of Bristol, Bristol, UK
Exploring High-Order Self-Similarity for Video Understanding
Apr 22, 2026Manjin Kim, Heeseung Kwon, Karteek Alahari +1Fine-Grained Video Understanding Video Understanding
POSTECH · RLWRLD Inc. · INRIA Grenoble Rhône-Alpes
Beyond ZOH: Advanced Discretization Strategies for Vision Mamba
Apr 22, 2026Fady Ibrahim, Guangjun Liu, Guanghui WangVision State Space Models Vision Foundation Models
Toronto Metropolitan University, 350 Victoria St, Toronto, ON M5B 2K3
A Controlled Benchmark of Visual State-Space Backbones with Domain-Shift and Boundary Analysis for Remote-Sensing Segmentation
Apr 20, 2026Nichula Wasalathilaka, Dineth Perera, Oshadha Samarakoon +4Vision State Space Models Vision Transformer
University of Peradeniya Peradeniya, Sri Lanka
HAMSA: Scanning-Free Vision State Space Models via SpectralPulseNet
Apr 16, 2026Badri N. Patro, Vijay S. AgneeswaranVision State Space Models Self-Supervised Vision Transformers
Microsoft
SSM Meets Video Diffusion Models: Efficient Long-Term Video Generation with Structured State Spaces
Mar 12, 2024Yuta Oshima, Shohei Taniguchi, Masahiro Suzuki +1Video Diffusion Models Interactive Video Generation
The University of Tokyo

Sep 28, 2026, cs.CVJ/K move · Enter open · S save

When Should the Count Change? Learning State Maintenance for Causal Video Counting

Pengyiang Liu, Dongyue Lyu, Junbo Niu, Zhongyue Shi+2

Beihang University · Peking University

Fine-Grained Video Understanding Vision State Space Models State-Tracking Rapid Adaptation Trajectory Generation

Open paper AskPDF arXiv

Continuous video counting requires distinguishing new observations from new objects or completed events. We introduce StaMina (State Maintenance), which learns to maintain counting state through state-conditioned updates. Recurrent visual context supports recognition; learned transitions maintain visibility, persistent identities, and completed-event records. A differentiable recurrence trains event transitions over legal paths constrained by count endpoints; visibility and association objectives train the object branch. A multi-source pipeline organizes 39.8K spatial queries and complementary event annotations into counting trajectories. On SVCBench, we evaluate counting adaptation with partial video overlap and held-out groups of linked annotations. Under prefix replay (Full) and persistent streaming (Stream), 4B and 8B models reach 41.9/36.4 and 44.9/38.2 Gaussian Precision Accuracy, respectively. The 8B model gains 10.9/3.2 points over Counting-SFT on the same queries. Matched-graph comparisons isolate phase conditioning and trajectory supervision, assessing training objectives alongside hard decisions. Online video benchmarks and count-conditioned decisions assess online understanding and task eligibility. Project Page: https://PLACEHOLDER.github.io/StaMina/

Momentum

Related topics

Latest papers 30