Search research

Topics & fields

Multi-Object Tracking233 papers Eye Tracking45 papers Unmanned Aerial Vehicle Tracking44 papers 3D Single Object Tracking21 papers Catheter Tip Tracking11 papers Gaze100 papers Search Algorithms89 papers Motion Estimation35 papers

481–510 of 3,380

Papers

Can Video World Models Track Unobserved World States?
Aug 31, 2026Joonghyuk Shin, Yicong Hong, Jaesik Park +1Video World Models Hidden States
UniTraffic-Agent: Unified Traffic Video Reasoning for AI City Challenge 2026 Track 3 with Two Out-of-Domain Evaluations
Aug 13, 2026Peng Li, Qianqian Xu, Shilong Bao +2Traffic Sign Recognition Textvqa
Multi-Agent Target-Existence Verification and Learned Mask Geometry Refinement: Winning Report of the MeViS-Text Track at the 8th LSVOS Challenge 2026
Aug 11, 2026Jungyoon Lee, Gyuil Lim, Doeon Kim +1Video Object Segmentation Expression
Listen, See and Track: Spatio-Temporal Audio-Visual Sound Event Reasoning for Omni-Modal Language Models
Aug 10, 2026Zhi Zeng, Cheng Zhang, Zesheng Yang +9Audio-Visual Reasoning Spatial Audio
Track-Guided Hierarchical Reinforcement Learning for Autonomous Vehicle Drifting with Minimum-Lap-Time Planning
Jul 31, 2026Sheng Zhao, Bolin Zhao, Xiaodong Wu +1Autonomous Racing Iterative Reinforcement Learning
Multi-Agent Debate and Visual Information Extraction for SeePhys Pro: A 1st-Place Technical Report from ICML 2026 AI4Math Track 3 Challenge
Jul 24, 2026Jiseok Kwak, Suhyeon Jo, Taewoo Kim +3Multi-Agent Debate Single-Agent Baselines
No Subspace to Track: Non-Identifiability and Optimizer State in Low-Rank Training
Jul 7, 2026Noel ThomasLow-Rank Factorization Large Models
Weighted Conformal Prediction for Lab-to-Track Thermal Transfer in EV Motorsport Powertrains
Jul 2, 2026Varshith Roy KotlaConformal Prediction Stochastic Volatility
SUMO: Segment and Track Any Motion with Nonlinear State Space Models
Jun 29, 2026Kexin Tian, Sixu Li, Keshu Wu +2Video Object Segmentation Multi-Object Tracking
Reported Confidence in LLMs Tracks Commitment More Than Correctness
Jun 28, 2026Dharshan KumaranLiar Large Language Model Performance
Follow Your Track: Precise Skeleton Animation Controlled by 3D Trajectories
Jun 24, 2026Yueting Liu, Yanqin Jiang, Nian Liu +44D Generation Skeleton
The Value Axis: Language Models Encode Whether They're on the Right Track
Jun 15, 2026Nick Jiang, Isaac Kauvar, Jack LindseyLarge Language Model Uncertainty Training Language Models
Short-Horizon Position Accuracy of Single-Track Models: Implications for Motion Planning of Autonomous Vehicles
Jun 12, 2026Aron J. Aertssen, Lars A. T. H. van Alen, Igo J. M. Besselink +2Vehicle Dynamics Trajectory Prediction
Evaluation Sovereignty in Metadata-Driven Classification: A Multi-Track Framework for Weakly Supervised Information Systems
Jun 11, 2026Raymond VasquezEvaluation Metrics Multi-Label Classification
Overview of the EReL@MIR 2025 Multimodal Document Retrieval Challenge (Track 1)
Jun 2, 2026Jingbiao MeiMultimodal Retrieval Visual Document Retrieval
IndoBias: A Dual Track Culturally Grounded Benchmark for LLMs Bias Evaluation in Indonesian Languages
May 31, 2026Ikhlasul Akmal Hanif, Muhammad Falensi Azmi, Filbert Aurelian Tjiaranata +2Large Language Model Bias Low-Resource Languages
TrackRef3D: Multi-View Consistent Track-then-Label for Open-World Referring Segmentation in 3D Gaussian Splatting
May 26, 2026Yuyang Tan, Renhe Zhang, Hang Zhang +23D Semantic Segmentation 3D Gaussian Splats
A Robust Semantic Segmentation Pipeline for the CVPR 2026 8th UG2+ Challenge Track 2
May 21, 2026Jinming Chai, Libo Yan, Licheng Jiao +1Dense Semantic Segmentation Cvpr
TinySAM 2: Extreme Memory Compression for Efficient Track Anything Model
May 18, 2026Zhaoyuan Ding, Yijing Yang, Han Shu +1Video Object Segmentation Segment Anything Model
SuperADD: Training-free Class-agnostic Anomaly Segmentation -- CVPR 2026 VAND 4.0 Workshop Challenge Industrial Track
May 14, 2026Lukas Roming, Felix Lehnerer, Jonas V. Funk +4Zero-Shot Anomaly Detection Anomaly Detection
2nd of the 5th PVUW MeViS-Audio Track: ASR-SaSaSa2VA
Apr 27, 2026Zhiyu Wang, Xudong Kang, Shutao LiVideo Object Segmentation Video Dataset
NightFeats @ MMU-RAGent NeurIPS 2025: A Context-Optimized Multi-Agent RAG System for the Text-to-Text Track
Apr 21, 2026Quentin Fever, Naziha AslamRetrieval-Augmented Generation Systems Reranking
DialogueSidon: Recovering Full-Duplex Dialogue Tracks from In-the-Wild Dialogue Audio
Apr 10, 2026Wataru Nakata, Yuki Saito, Kazuki Yamauchi +2Full-Duplex Dialogue Speech Separation
Ordinary, Reasonable Chatbots: Do AI Models Track Human Legal Judgments?
Date pendingNirav Patel, Emily Wenger, Christopher BuccafuscoLarge Language Model Decision-Making Chatbots
Low-Cost Assays for Measuring Model Behavior Across Vendors and Releases
Sep 24, 2026Tapan Parikh
ArGuard Shared Task: Harmful Content Detection in Arabic Memes and LLM Prompts
Sep 24, 2026Firoj Alam, Md. Rafiul Biswas, Mohamed Bayan Kmainasi +5Arabic Natural Language Processing Hate Speech
A Field-Deployable GNSS-based Navigation Stack for Outdoor Mobile Robots
Sep 24, 2026Yiyuan Lin, Cole Regnier, Yu Jiang
Sample, Simulate, Select: Physics-in-the-Loop Text-to-Motion for Humanoids Without Training
Sep 22, 2026Raphael Memmesheimer, Sven BehnkeHuman Motion Generation
Complex KDA: Understanding and Enhancing the Expressivity of Kimi Delta Attention
Sep 21, 2026Julien Siems, Riccardo Grazzi, Korbinian Pöppel +8Quadratic Attention Expressivity
HappyWorld-Bench
Sep 21, 2026Zhiqi Bai, Junai Cai, Yixin Chen +33

Aug 31, 2026 · cs.CVJ/K move · Enter open · S save

Can Video World Models Track Unobserved World States?

Joonghyuk Shin, Yicong Hong, Jaesik Park, Xun Huang

Seoul National University · Roblox

Video world models are increasingly used as simulators, yet visual fidelity alone does not show that a model maintains the hidden state of the world. We examine this gap with an action-conditioned video Shell Game, a visual analog of

S_5

state tracking that decouples visual rendering from compositing the hidden state underneath. Bidirectional and autoregressive Transformers, Mamba, and linear attention restricted to nonnegative transition eigenvalues all fit the training horizon of 5 swaps and then fall toward chance on longer swap chains (extrapolation) while still rendering plausible video with additional denoising steps providing no benefit. The pixel-based diffusion target never supervises the unseen hidden state, so the generated frames cannot carry it and the state has to live inside the architecture rather than in the tokens. For a Transformer, that architectural state is only an append-only KV cache, so the model has to re-derive the hidden arrangement from the whole history at every chunk. We find two mechanisms that do extrapolate, and both carry a state across chunks and revise it in place. Linear attention succeeds once its transition eigenvalues may be negative, and TTT with a nonlinear fast weight succeeds by updating the feature map through which it reads its own state. We further examine harder cases in dynamic world exploration tasks, and discuss the broader implications for building stateful video world models.

Video World Models Hidden States

Open paper Ask about it PDF