Long-Term

Follow this topic Ask about this topic

Momentum

11 papers in the last four weeks, up 83% on the four weeks before. 0.1% of all new papers.

Jul 6Week of Sep 21

Latest papers 86

All topics

LongDPM: Overlap-Aware 4D Reconstruction from Long Monocular Videos
May 17, 2026Chenyi Xu, Yihao Wu, Liqi Yan +4Monocular Video 4D Reconstruction
Hangzhou Dianzi University
From Observed Viability to Internal Predictive Approximation: A Single-Subject Latent-Space Analysis of Gait Dynamics Under Occlusal Constraint
May 15, 2026Jacques Raynal, Pierre Slangen, Elsa Raynal +1Gait Dynamics Biomechanics
Laboratory of Bioengineering and Nanosciences (LBN), University of Montpellier, France · 2EuroMov Digital Health in Motion, University of Montpellier, IMT Mines Alès, Alès, France · 3Certified Sophrologist and Dental Assistant, Sensorimotor Practice, Montpellier, France +1
PESD-TSF: A Period-Aware and Explicit Structured Decomposition Framework for Long-Term Time Series Forecasting
May 15, 2026Hua Wang, Xianhao Jiao, Fan ZhangMultivariate Time Series Forecasting Multivariate Time-Series
School of Computer and Artificial Intelligence, Ludong University, Yantai, Shandong 264025, China · School of Computer and Artificial Intelligence, Ludong University, Yantai, Shandong 264025, China. · School of Computer Science and Technology, Shandong Technology and Business University, Yantai, Shandong 264005, China +1
Understanding How International Students in the U.S. Are Using Conversational AI to Support Cross-Cultural Adaptation
May 14, 2026Laleh Nourian, Anisa Callis, Stephanie Patterson +3Conversational Artificial Intelligence Student
Rochester Institute of Technology, Rochester, NY, USA · School of Information, Rochester Institute of Technology, Rochester, NY, USA
Watch your neighbors: Training statistically accurate chaotic systems with local phase space information
May 14, 2026Joon-Hyuk Ko, Andrus Giraldo, Deok-Sun LeeChaos Surrogate Models
Center for AI and Natural Sciences Korea Institute for Advanced Study Seoul, Korea 02455 · School of Computational Sciences Korea Institute for Advanced Study Seoul, Korea 02455
Three-Stage Learning Unlocks Strong Performance in Simple Models for Long-Term Time Series Forecasting
May 13, 2026Zhenan Yu, Guangxin Jiang, Jin YangLong-Term Residual Learning
1Harbin Institute of Technology
The Readability Spectrum: Patterns, Issues, and Prompt Effects in LLM-Generated Code
May 13, 2026Hengzhi Ye, Fengyuan Ran, Weiwei Xu +1Code Generation Readability
Peking university · Beijing, Beijing, China · Wuhan University +1
A Proprioceptive-Only Benchmark for Quadruped State Estimation: ATE, RPE, and Runtime Trade-offs Between Filters and Smoothers
May 12, 2026Ylenia Nisticò, João Carlos Virgolino Soares, Joan Solà +1State Estimation Extended Kalman Filter
Dynamic Legged Systems (DLS) Lab, Istituto Italiano di Tecnologia, 16163 Genova, Italy · Institut de Rob`otica i Inform`atica Industrial - CSIC, 08028 Barcelona, Spain
PnP-Corrector: A Universal Correction Framework for Coupled Spatiotemporal Forecasting
May 9, 2026Hao Wu, Fan Xu, Yuxu Lu +9Spatio-Temporal Forecasting Global Climate Models
Tsinghua University · Tencent · Shenzhen Loop Area Institute +6
LARGO: Low-Rank Hypernetwork for Handling Missing Modalities
May 7, 2026Niels Vyncke, Pooya Ashtari, Aleksandra PižuricaMissing Modalities Modalities
Department of Telecommunications and Information Processing Ghent University Ghent, Belgium
Online Localized Conformal Prediction
May 6, 2026Yuheng Lai, Garvesh RaskuttiOnline Conformal Prediction Conformal Inference
University of Wisconsin - Madison
Memory as a Markov Matrix: Sample Efficient Knowledge Expansion via Token-to-Dictionary Mapping
May 5, 2026Kaustubh Pethkar, Ziyang Xiong, Zuofeng Shang +1Large Language Model Memory Autoregressive Language Models
New Jersey Institute of Technology · University of California, Berkeley
LiDAR Teach, Radar Repeat: Robust Cross-Modal Navigation in Degenerate and Varying Environments
May 4, 2026Renxiang Xiao, Yichen Chen, Yuanfan Zhang +5Lidar Radar
School of Intelligence Science and Engineering, Harbin Institute of Technology, Shenzhen, China · School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China
Validation of an AI-based end-to-end model for prostate pathology using long-term archived routine samples
May 4, 2026Xiaoyi Ji, Renata Zelic, Oskar Aspegren +11Prognostics Multiple Instance Learning
Department of Medical Epidemiology and Biostatistics, Karolinska Institutet, Stockholm, Sweden · Department of Molecular Medicine and Surgery, Karolinska Institutet, Stockholm, Sweden · Department of Pelvic Cancer, Cancer Theme, Karolinska University Hospital, Stockholm, Sweden +8
AsymTalker: Identity-Consistent Long-Term Talking Head Generation via Asymmetric Distillation
May 1, 2026Yuxin Lu, Jiayang Sun, Guibo Zhu +1Talk Spatial Encoding
Soochow University · Institute of Automation, Chinese Academy of Sciences
KellyBench: A Benchmark for Long-Horizon Sequential Decision Making
Apr 30, 2026Thomas Grady, Kip Parker, Iliyan Zarov +3Betting Sequential Decision Making
General Reasoning, Inc.
EviMem: Evidence-Gap-Driven Iterative Retrieval for Long-Term Conversational Memory
Apr 30, 2026Yuyang Li, Yime He, Zeyu Zhang +1Conversational Memory Retrievers
The Australian National University · UNSW Sydney
CLVAE: A Variational Autoencoder for Long-Term Customer Revenue Forecasting
Apr 24, 2026Jeffrey Näf, Riana Valera Mbelson, Markus MeiererConditional Variational Autoencoder Autoregressive Model
Research Institute for Statistics and Information Science, University of Geneva · Institute of Management, University of Geneva
Short-Term Gain, Long-Term Fragility: AI Labor Substitution and the Erosion of Sustainable Capability
Apr 23, 2026Wolfgang RohdeArtificial Intelligence Systems Human Agency
AiSuNe Foundation Research
A multi-platform LiDAR dataset for standardized forest inventory measurement at long term ecological monitoring sites
Apr 16, 2026Michael R. Chang, Anna Candotti, Karl von Ellenrieder +2Forest Biomass Lidar
Faculty of Engineering, Free University of Bozen-Bolzano, via Bruno Buozzi 1, Bolzano, 39100, BZ, Italy · Faculty of Agricultural, Environmental and Food Sciences, Free University of Bozen-Bolzano, piazza Università, 5, Bolzano, 39100, BZ, Italy · Competence Centre for Mountain Innovation Ecosystems, Free University of Bozen-Bolzano +1
SHIFT: Motion Alignment in Video Diffusion Models with Adversarial Hybrid Fine-Tuning
Mar 18, 2026Xi Ye, Wenjia Yang, Yangyang Xu +4Video Diffusion Models Diffusion Alignment
Tsinghua University · Ant Group · University of Chinese Academy of Sciences
TTSA3R: Training-Free Temporal-Spatial Adaptive Persistent State for Streaming 3D Reconstruction
Jan 30, 2026Zhijie Zheng, Xinhao Xiang, Jiawei Zhang3D Reconstruction Streaming
University of California, Davis · CA 95616, USA
Agentic Very Long Video Understanding
Jan 26, 2026Aniket Rege, Arka Sadhu, Yuliang Li +5Video Agent Video Understanding
Reality Labs Research at Meta · University of Wisconsin-Madison · Work done during internship at Meta
Neural non-canonical Hamiltonian dynamics for long-time simulations
Oct 2, 2025Clémentine Courtès, Emmanuel Franck, Michael Kraus +2Hamiltonian Long-Term
IRMA, MACARON · Institut de Recherche Mathématique Avancée, UMR 7501 Université de Strasbourg et CNRS, 7 rue René Descartes 672000 Strasbourg, France. · INRIA Nancy-Grand Est, MACARON Project, Strasbourg, France. +5
Impatient Bandits: Optimizing for the Long-Term Without Delay
Jan 14, 2025Kelly W. Zhang, Thomas Baldwin-McDonald, Kamil Ciosek +2Bandits Long-Term
Imperial College London · University of Manchester · Spotify +2
The Vienna 4G/5G Drive-Test Dataset
Date pendingWilfried Wiedner, Lukas Eller, Mariam Mussbah +4Mobile Networks Naturalistic Driving Data
Institute of Telecommunications, TU Wien, Gusshausstraße 25, 1040 Vienna, Austria · Christian Doppler Laboratory for Digital Twin assisted AI for sustainable Radio Access Networks, TU Wien

May 17, 2026, cs.CVJ/K move · Enter open · S save

LongDPM: Overlap-Aware 4D Reconstruction from Long Monocular Videos

Chenyi Xu, Yihao Wu, Liqi Yan, Chao Yang+3

Hangzhou Dianzi University

Monocular Video 4D Reconstruction 3D Tracking Long-Range Coherence Long-Term

Open paper AskPDF arXiv

Recovering a dynamic 3D scene from a long monocular video is crucial for dense geometry, camera motion, and temporal correspondence to remain consistent in a shared coordinate system. Existing methods face two key challenges: (1) feed-forward reconstruction models provide accurate local predictions but are limited to short clips, and (2) long-range trackers preserve correspondences without producing dense sequence-level reconstruction. This paper presents LongDPM, a novel overlap-aware framework for scalable long-range monocular dynamic reconstruction. First, LongDPM processes long videos in overlapping chunks, keeping inference memory bounded by the chunk length. Second, it connects chunk-local coordinate systems through confidence-weighted registration with static-aware overlap abstraction. Third, it associates dynamic identities across chunk boundaries and fuses matched trajectories to recover coherent long-range 3D motion. Experimental results demonstrate that LongDPM achieves superior long-range reconstruction and tracking performance, reducing dense tracking EPE over V-DPM on PointOdyssey, Kubric-F, and Kubric-G, while obtaining the best TUM-dynamics ATE for camera pose estimation.

Momentum

Related topics

Latest papers 86