Replay

Follow this topic Ask about this topic

Momentum

13 papers in the last four weeks, up 44% on the four weeks before. 0.2% of all new papers.

Jul 6Week of Sep 21

Latest papers 89

All topics

BBR-Net: Boundary-Balanced Replay for Continual Medical Image Segmentation
Jun 2, 2026Zahid Ullah, Sieun Choi, Jihie KimSemi-Supervised Medical Image Segmentation Echocardiography
Department of Computer Science and Artificial Intelligence, Dongguk University, Seoul, 04620, Republic of Korea
Turning Back Without Forgetting: Selective Backward Refinement for Parameter-Efficient Continual Learning
May 31, 2026Anushka Tiwari, Kaiyi JiReplay-Based Continual Learning Cross-Task Knowledge Transfer
Institute for Artificial Intelligence and Data Science, University at Buffalo, Buffalo, NY, USA · Department of Computer Science and Engineering, University at Buffalo, Buffalo, NY, USA
Canonicalized Stable-List Replay for Private Federated Continual Learning over Language-Model Embeddings
May 29, 2026Ibne Farabi Shihab, Abu Sa-Adat Mohamed Moon-Im Al Ahsan, Anuj SharmaFederated Learning Replay-Based Continual Learning
Department of Computer Science, Iowa State University · Department of Computer Science & Engineering, BRAC University · Department of Civil, Construction & Environmental Engineering, Iowa State University
Dynamic Proxy-Mixing: Transferring Replay Controllers from Small to Large Models for Continual Instruction Tuning
May 29, 2026Ibne Farabi Shihab, Fariya Afrin, Anuj SharmaReinforcement Fine-Tuning Reinforcement Learning Control
Department of Computer Science, Iowa State University · Department of Computer Science, Kalinga Institute of Industrial Technology · Department of Civil, Construction & Environmental Engineering, Iowa State University
PR2: Predictive Routing Replay for MoE-Based LLM Reinforcement Learning
May 29, 2026Daize Dong, Junlin Chen, Haolong Jia +9Large Language Model Reinforcement Learning Replay
♣Rutgers University · ♦AMD · ⋆MBZUAI
REPOT: Recoverable Program-of-Thought via Checkpoint Repair
May 28, 2026Parsa MazaheriRetrying Replay
University of California, Santa Cruz
Continual Learning in Modern Hopfield Networks with an Application to Diffusion Models
May 27, 2026Ken Takeda, Masafumi Oizumi, Ryo KarakidaCatastrophic Forgetting Hopfield Networks
Graduate School of Arts and Science, The University of Tokyo, Tokyo, Japan · Artificial Intelligence Research Center, AIST, Tokyo, Japan
Receipt Replay OOD: A Small Benchmark for Screen Replay Detection Under Domain Shift
May 26, 2026Alexander VinogradovRe-Identification Replay
IU International University of Applied Science
Forgetting in Language Models: Capacity, Optimization, and Self-Generated Replay
May 25, 2026Martin Marek, Dongkyu Cho, Shikai Qiu +3Catastrophic Forgetting Forgetting
New York University
LAPS: Improving Incremental LiDAR Mapping using Active Pooling and Sampling for Neural Distance Fields
May 15, 2026Dongjae Lee, Wooseong Yang, Yifu Tao +2Continuous Distance Field Orb-Slam2
Department of Mechanical Engineering, Seoul National University, S. Korea · Oxford Robotics Institute at the University of Oxford, UK
FutureSim: Replaying World Events to Evaluate Adaptive Agents
May 14, 2026Shashwat Goel, Nikhil Chandak, Arvindh Arun +5Simulation-Based Reinforcement Learning Replay
1ELLIS Institute Tübingen · 2Max Planck Institute for Intelligent Systems · 4Tübingen AI Center +3
Stateful Reasoning via Insight Replay
May 14, 2026Bin Lei, Caiwen Ding, Jiachen Yang +2Chain-of-Thought Reasoning Deepseek
University of Minnesota · 2Simular AI
Decision Support for Marketplace Policies under Incomplete Evidence: From Replay to Launch Readiness
May 13, 2026Prashant Shekhar, Caroline HowardPolicy Evaluation Software Engineering Decision Support
Department of Mathematics Embry-Riddle Aeronautical University, Daytona Beach, FL, USA
Cochise: A Reference Harness for Autonomous Penetration Testing
May 12, 2026Andreas Happe, Jürgen CitoPenetration Testing Test Generation
TU Wien · Vienna, Austria
When Does Non-Uniform Replay Matter in Reinforcement Learning?
May 11, 2026Michal Korniak, Mikołaj Czarnecki, Yarden As +3Deterministic Replay Replay
1ETH Zurich · University of Warsaw · 3UC Berkeley +1
UFO: A Unified Flow-Oriented Framework for Robust Continual Graph Learning
May 11, 2026Danhui Zhang, Zhe Wang, Qing Qing +6Graph Representation Learning Replay-Based Continual Learning
Jilin University · Adelaide University · RMIT University +1
From Passive Reuse to Active Reasoning: Grounding Large Language Models for Neuro-Symbolic Experience Replay
May 10, 2026Yanan Xiao, Yixiang Tang, Zechen Feng +3Prioritized Experience Replay Hierarchical Reinforcement Learning
1Affiliation 1 · 2Affiliation 2 · 3Affiliation 3
A Communication-Theoretic Framework for LLM Agents: Cost-Aware Adaptive Reliability
May 9, 2026Hamed Omidvar, Vahideh AkhlaghiLarge Language Model Routing Large Language Model Agents
INTELLERCE LLC San Jose, CA, USA
ReplaySCM: A Benchmark for Executable Causal Mechanism Induction from Interventions
May 5, 2026Serafim BatzoglouReplay
A Domain Incremental Continual Learning Benchmark for ICU Time Series Model Transportability
May 5, 2026Ryan King, Conrad Krueger, Ethan Veselka +2Intensive Care Unit Prognostics
Computer Science & Engineering, Texas A&M University, College Station, United States
RECAP: An End-to-End Platform for Capturing, Replaying, and Analyzing AI-Assisted Programming Interactions
May 1, 2026Keyu He, Qianou Ma, Valerie Chen +2Ai-Assisted Programming Tasks Ai-Based
Carnegie Mellon University
Continual Learning of Feedback-based Molecular Communication
May 1, 2026Siddhant Setia, Junichi Suzuki, Tadashi NakanoReplay-Based Continual Learning Continual Learning
Department of Computer Science, University of Massachusetts, Boston Boston, MA, 02125, USA · Graduate School of Informatics, Osaka Metropolitan University Osaka, Japan
Hidden Failure Modes of Gradient Modification under Adam in Continual Learning, and Adaptive Decoupled Moment Routing as a Repair
Apr 24, 2026Yuelin Hu, Zhenbo Yu, Zhengxue Cheng +2Adam Replay-Based Continual Learning
Shanghai Jiao Tong University · Shanghai Maritime University
Find, Fix, Reason: Context Repair for Video Reasoning
Apr 17, 2026Haojian Huang, Chuanyu Qin, Yinchuan Li +1Reasoning Skills Large Multimodal Models
The Hong Kong University of Science and Technology (Guangzhou) · Knowin AI · Institute of Information Engineering, Chinese Academy of Sciences
Leveraging Complementary Embeddings for Replay Selection in Continual Learning with Small Buffers
Apr 9, 2026Danit Yanowsky, Daphna WeinshallReplay-Based Continual Learning Continual Learning
School of Computer Science and Engineering The Hebrew University of Jerusalem
Beyond Task Completion: A Verification-vs.-Conformance Gap in Tool-Evolving Agents
Apr 1, 2026Alibek Kaliyev, Artem MaryanskyySynthetic Task Self-Evolving Agents
The University of Texas at Austin · Austin, Texas, USA · Uber +1
Language Generation with Replay: A Learning-Theoretic View of Model Collapse
Mar 12, 2026Giorgio Racca, Michal Valko, Amartya SanyalLarge Language Model Generation Collapse
University of Copenhagen · Isara Labs
Efficient Diversity-based Experience Replay for Deep Reinforcement Learning
Oct 27, 2024Kaiyan Zhao, Yiming Wang, Yuyang Chen +3Rejection Sampling Replay
School of Computer Science, Wuhan University, Wuhan, China · State Key Laboratory of Internet of Things for Smart City, University of Macau, Macao, China · School of Artificial Intelligence Shenzhen Polytechnic University, China
TBR: Transport-Based Rendering with Deposition Strokes for Inverse Graphics
Date pendingTianqi Liu, Yushan Han, Hang LiuImage Reconstruction Replay
Independent Researcher, Beijing, China · Huaxin Design Institute, Hangzhou, China · Communication University of China, Beijing, China

Jun 2, 2026, cs.CVJ/K move · Enter open · S save

BBR-Net: Boundary-Balanced Replay for Continual Medical Image Segmentation

Zahid Ullah, Sieun Choi, Jihie Kim

Department of Computer Science and Artificial Intelligence, Dongguk University, Seoul, 04620, Republic of Korea

Semi-Supervised Medical Image Segmentation Echocardiography Prioritized Experience Replay U-Net Anatomy Continual Learning+1

Open paper AskPDF arXiv

Continual learning for medical image segmentation remains challenging under domain shift because replay-based methods often preserve appearance information without explicitly modeling anatomical structure. This study investigates whether structural consistency governs knowledge retention in continual cardiac ultrasound segmentation. We propose the Boundary-Balanced Replay Network (BBR-Net), which selects replay samples using boundary-aware priority and class balance to preserve anatomically informative regions. The method is evaluated on CAMUS and CardiacNet under forward (CAMUS to CardiacNet) and reverse (CardiacNet to CAMUS) task orders. In the forward setting, BBR-Net retains source-task performance close to an offline joint-training reference, while markedly reducing catastrophic forgetting and preserving competitive target-task adaptation. Ablation results show that boundary-aware prioritization contributes to retention and improves the balance between source-task preservation and target-task adaptation when combined with class-aware sampling. In contrast, the reverse setting reveals that structure-aware replay fails when initial representations are learned from noisy and structurally inconsistent data. To isolate this effect, we conduct a controlled structural perturbation analysis by progressively corrupting source-task boundaries while keeping the dataset, architecture, and training protocol fixed. Forgetting increases consistently as structural reliability decreases, suggesting that replay effectiveness is strongly influenced by the quality of stored structural information, rather than by memory capacity alone. These findings indicate that preserving anatomical structure under domain shift is a central factor in continual medical image segmentation, and that replay mechanisms should account for structural reliability to support robust knowledge retention.

Momentum

Related topics

Latest papers 89