Vista

Follow this topic Ask about this topic

Momentum

7 papers in the last four weeks, up 133% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 40

All topics

VISTA: A Visual Harness for Reasoning in an Interactive World
Oct 1, 2026Qiushi Han, Keya Hu, Linlu Qiu +2Multimodal Agents Multimodal Reasoning
Massachusetts Institute of Technology
Is Better Teacher Supervision Enough? Unlocking Student-side Learning in Multimodal On-Policy Distillation
Sep 30, 2026Siyuan Liu, Kanghui Tian, Yue Duan +4Perceptually Vista
Nanjing University · Fudan University · Nanjing University of Posts and Telecommunications
Visual Jev: Accurate and Efficient Decisions from Shared Visual Context
Sep 22, 2026Guanxu Yu, Yuhang YaoVisual Representations Vista
Independent Research · Carnegie Mellon University
VISTA: Video-Injected Stylized Text-to-Animation
Sep 20, 2026Monseej Purkayastha, Anindita Ghosh, Philipp SlusallekMotion Capture Vista
Saarland Informatics Campus & German Research Centre for Artificial Intelligence (DFKI), Saarbrücken, Germany · Max Planck Institute for Informatics (MPII), Saarbrücken, Germany
Label-free steering: Compressing test-time reinforcement learning into bias-only subspaces
Sep 16, 2026Naveen Vakada, Mingyuan Li, Shaoxiong JiStable Test-Time Adaptation Test-Time Adaptation
University of Turku, Finland · ELLIS Institute Finland
MEgoVista: Multi-view Ego-aware Motion Estimation for Metric 4D Hands and Head in the Wild
Sep 15, 2026Jiangong Xiao, Zhihao Zhang, Yifei Dong +73D Hand Egocentric Motion Generation
Northwestern Polytechnical University · Maniformer · Xi'an Jiaotong University +1
Vision And Text Transformer For Predicting Answerability On Visual Question Answering
Sep 15, 2026Tung Le, Huy Tien Nguyen, Le Minh NguyenSelf-Supervised Vision Transformers Transformer Architectures
Japan Advanced Institute of Science and Technology, Ishikawa, Japan. · Faculty of Information Technology, University of Science, Ho Chi Minh City, Vietnam · Vietnam National University, Ho Chi Minh City, Vietnam +1
First Things First: Teaching LLM-Based Agents to Prioritize Must-Haves before Nice-to-Haves
Sep 4, 2026Tianjie Ju, Xinyue Xu, Wanxuan Sun +4Vista
School of Computer Science, Shanghai Jiao Tong University · ByteDance
VisLens: Single-Pass Interpretable Visual Search for Multimodal LLMs
Aug 31, 2026Jingyi He, Sanghwan Kim, Zeynep AkataMultiple Vision Tasks Recent Vision-Language Models
Technical University of Munich · Helmholtz Munich · Munich Center for Machine Learning
VisER: Visual Evidence and Reliance for Object Hallucination Detection in LVLMs
Aug 31, 2026Afsaneh Hasanebrahimi, Hanxun Huang, Christopher Leckie +1Citation Hallucination Detection Visual Evidence
School of Computing and Information Systems The University of Melbourne Melbourne, Australia
VISTA-DZ: Visual Semantic Trajectory Adaptation for Personalized Dilemma Zone Prediction
Jun 28, 2026Chuheng Wei, Ziye Qin, Ziran Wang +1Vista Journey
Purdue University, 550 Stadium Mall Drive, West Lafayette, 47907, Indiana, USA · University of California, Riverside, 1084 Columbia Ave, Riverside, 92507, California, USA
Curvature-aware 3D length estimation of greenhouse cucumbers using RGB-D imaging and cubic spline arc-length integration
Jun 21, 2026Manveen Kaur, Rajmeet Singh, Saeed Mozaffri +1Robust Geometric Model Estimation Rgb-Depth Cameras
Department of Mechanical Engineering University of Windsor Windsor, ON N9B 3P4, Canada · Mohamed bin Zayed University of Artificial Intelligence Abu Dhabi, UAE
VisDom: Sparse Novel View Synthesis with Visible Domain Constraint
Jun 18, 2026Mariia Gladkova*, Tarun Yenamandra*, Edmond Boyer +3Novel View Synthesis Geometric Reconstruction
1TU Munich · 2MCML
VIMPO: Value-Implicit Policy Optimization for LLMs
Jun 18, 2026Zhewei Kang, Aosong Feng, Sergey Levine +2Reinforcement Learning With Verifiable Reward Frictive Policy Optimization
UC Berkeley · Yale University
VISTA: Scale-Aware Visual Navigation via Action History Conditioning
Jun 15, 2026Maeva Guerrier, Koki Kobayashi, Simon Roy +2Recent Vision Foundation Models Dynamic Environments
Polytechnique Montreal, MILA · Institute of Science Tokyo · Polytechnique Montreal +2
TimeVista: Exploring and Exploiting Vision-Language Models as Judges for Time Series Forecasting
Jun 15, 2026Zhi Chen, Yuxuan Wang, Jialong Wu +5Time Series Forecasting Time Series
School of Software, BNRist, Tsinghua University, Beijing 100084, China
VISTA: A Versatile Interactive User Simulation Toolkit for Agent Evaluation
Jun 9, 2026Yunan Lu, Ryan Shea, Yusen Zhang +1Agentic Evaluations User Simulation
Department of Computer Science, Columbia University, 2Arklex.ai
Inside the Visual Mind: Neuroscience-Motivated Concept Circuits for Interpreting and Steering Vision Transformers
Jun 4, 2026Tang Li, Yanlin Chen, Mengmeng Ma +1Self-Supervised Vision Transformers Vision Transformer
Department of Computer & Information Science, University of Delaware, Newark, DE, USA · Department of Computer Science, University of Virginia, Charlottesville, VA, USA
VISTA: Vision-Grounded and Physics-Validated Adaptation of UMI data for VLA Training
Jun 3, 2026Siyuan Yang, Linzheng Guo, Ouyang Lu +10Vision-Language-Action Framework Robotic Data Acquisition
Institute of AI (TeleAI), China Telecom · University of Science and Technology of China · 4Northwestern Polytechnical University +5
Federated Learning over Human-Body Communication for On-Body Edge Intelligence: A Survey, Taxonomy, and BODYFED-HBC Scheduling Vignette
May 22, 2026Koffka KhanFederated Learning Intelligent Edge
Department of Computing and Information Technology The University of the West Indies, St. Augustine, Trinidad and Tobago
VisAnalog: A Diagnostic Suite for Visual Concept Transfer on Natural Images
May 22, 2026Zhaonan Li, Kyle R. Chickering, Bangzheng Li +13Vision Datasets Vista
Arizona State University · Luma AI · UC Davis
VISTA: Validation-Guided Integration of Spatial and Temporal Foundation Models with Anatomical Decoding for Rare-Pathology VCE Event Detection -- after competition results
May 21, 2026Bo-Cheng Qiu, Fang-Ying Lin, Ming-Han Sun +3Colonoscopy Vista
National Cheng Kung University, Taiwan · National Yang Ming Chiao Tung University, Taiwan
VISTA: Technical Report for the Ego4D Short-Term Object Interaction Anticipation at EgoVis 2026
May 20, 2026Qiaohui Chu, Haoyu Zhang, Yisen Feng +4Temporal Action Localization Video Joint Embedding Predictive Architecture
Harbin Institute of Technology (Shenzhen) · Pengcheng Laboratory · Shandong Jianzhu University
VISTAQA: Benchmarking Joint Visual Question Answering and Pixel-Level Evidence
May 20, 2026Mozhgan Nasr Azadani, Yimu Wang, Yongpeng Zhu +5Weak Visual Grounding Visual Evidence
University of Waterloo · Stanford University · NVIDIA
VISAFF: Speaker-Centered Visual Affective Feature Learning for Emotion Recognition in Conversation
May 18, 2026Linan ZHU, Zihao Zhai, Xiao Han +4Emotion Recognition Automatic Speaker Verification
1Zhejiang University of Technology · 2ETH Zurich, Switzerland
CANSURF: An ASV-View Can Dataset and Benchmark for Detection and Tracking of Surface-Level Debris
May 16, 2026Zaid Aljundi, Zahra F. Rahmatullah, Mostafa Elemam +1Ship Detection Waste
School of Mathematical and Computer Sciences Heriot-Watt University Dubai Dubai, United Arab Emirates · School of Engineering and Physical Sciences Heriot-Watt University Dubai Dubai, United Arab Emirates
Viverra: Text-to-Code with Guarantees
May 14, 2026Haoze Wu, Rocky Klopfenstein, Keith Farkas +1Code Generation Formal Verification
Amherst College · Broadcom
VISTA: A Generative Egocentric Video Framework for Daily Assistance
May 11, 2026Yu-Hsiang Liu, Yu-Chien Tang, An-Zi YenVideo Agent Egocentric Video
Department of Computer Science, National Yang Ming Chiao Tung University, Taiwan
ViSRA: A Video-based Spatial Reasoning Agent for Multi-modal Large Language Models
May 11, 2026Tingshu Mou, Jiabo He, Renying Wang +53D Spatial Reasoning Multimodal Large Language Models
Fudan University · BCAI · Bosch Center for Artificial Intelligence (BCAI) +1
VISTA: A Benchmark for Real-Time Video Streaming under Network Impairments in Surgical Teleoperation
May 9, 2026Zexin Deng, Zhenhui Yuan, Tian Lu +3Surgical Videos Video Quality
Institute for Applied and Translational Technologies in Surgery, University Hospitals Coventry & Warwickshire NHS Trust, UK · College of Control Science and Engineering and the State Key Laboratory of Industrial Control Technology, Zhejiang University, China · South China University of Technology, Guangzhou 511442, China +1
\mathsf{VISTA}: Decentralized Machine Learning in Adversary Dominated Environments
May 8, 2026Hanzaleh Akbari Nodehi, Parsa Moradi, Soheil Mohajer +1Bounded Adversary Adversarial Robustness
University of Minnesota
Toward Visually Realistic Simulation: A Benchmark for Evaluating Robot Manipulation in Simulation
May 7, 2026Yixin Zhu, Zixiong Wang, Jian Yang +4Robotic Manipulation 3D Assets
Nanjing University · Nankai University · ShanghaiTech University
TableVista: Benchmarking Multimodal Table Reasoning under Visual and Structural Complexity
May 7, 2026Zheyuan Yang, Liqiang Shang, Junjie Chen +6Vista Structural Complexity
Tongji University · University of Bristol · Tianjin University +1
TabSurv: Adapting Modern Tabular Neural Networks to Survival Analysis
May 5, 2026Stanislav Kirpichenko, Andrei Konstantinov, Lev UtkinSurvival Analysis Tabular Learning
Higher School of Artificial Intelligence Technologies, Peter the Great St. Petersburg Polytechnic University, St. Petersburg, Russia
CuraView: A Multi-Agent Framework for Medical Hallucination Detection with GraphRAG-Enhanced Knowledge Verification
May 5, 2026Severin Ye, Xiao Kong, Xiaopeng He +2Citation Hallucination Detection Electronic Health Records
School of Computer Science and Engineering Kyungpook National University Daegu, Republic of Korea · School of Airspace Science and Engineering Shandong University Weihai, China · Department of English Language and Literature, Kyungpook National University, Daegu, Republic of Korea
ViewSAM: Learning View-aware Cross-modal Semantics for Weakly Supervised Cross-view Referring Multi-Object Tracking
May 4, 2026Jiawei Ge, Xintian Zhang, Jiuxin Cao +9Multi-Object Tracking Cross-Modal
Southeast University · Universität der Bundeswehr München · Queen Mary, University of London +2
VISTA: Video Interaction Spatio-Temporal Analysis Benchmark
May 2, 2026Alejandro Aparcedo, Akash Kumar, Aaryan Garg +5Fine-Grained Video Understanding Spatio-Temporal Reasoning
University of Central Florida · BITS Pilani · Ho Chi Minh City University of Science +1
AnemiaVision: Non-Invasive Anemia Detection via Smartphone Imagery Using EfficientNet-B3 with TrivialAugmentWide, Mixup Augmentation, and Persistent Patient History Management
Apr 24, 2026Rahul PatelEfficientnet Encoder Fundus Images
Department of Electronics and Communication Engineering Indian Institute of Information Technology, Surat India
Vista4D: Video Reshooting with 4D Point Clouds
Apr 23, 2026Kuan Heng Lin, Zhizheng Liu, Pablo Salamanca +94D Reconstruction 4D
1Eyeline Labs · 3Columbia University · 4UCLA +3
VISTA: Validation-Informed Trajectory Adaptation via Self-Distillation
Apr 13, 2026Eli Corn, Daphna WeinshallParameter-Efficient Adaptation Robust Trajectory
Department of Computer Science, Hebrew University of Jerusalem, Jerusalem, Israel.

Oct 1, 2026, cs.AIJ/K move · Enter open · S save

VISTA: A Visual Harness for Reasoning in an Interactive World

Qiushi Han, Keya Hu, Linlu Qiu, Cathy Wu+1

Massachusetts Institute of Technology

Multimodal Agents Multimodal Reasoning Vista Visual Memory Reasoning Skills World

Open paper AskPDF arXiv

We show that multimodal models possess strong reasoning abilities and that an appropriate harness can unlock their potential to solve tasks across diverse interactive environments. We introduce VISTA, a visual harness that gives a general-purpose multimodal model long-horizon vision. VISTA allows the model to directly perceive the environment through visual observations and maintains a lossless visual memory that preserves past observations in their original form. The model can actively retrieve these observations and reorganize its visual input as it reasons. On ARC-AGI-3, VISTA improves Claude Opus 5.0's Relative Human Action Efficiency score from 40.68 to a perfect 100.00, with the model completing all 25 public games using 57.4% fewer actions than first-time human participants. VISTA's simple design also allows it to extend naturally to diverse visual environments with minimal adaptation. Across three additional benchmarks covering a diverse range of visual games and puzzles, it substantially outperforms baselines using the same underlying model with minimal harnesses. Our results highlight VISTA's potential as a general-purpose visual harness for advancing multimodal agents in complex visual environments.

Momentum

Related topics

Latest papers 40