Post-Deployment Adaptation

Follow this topic Ask about this topic

Momentum

1 paper in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Jul 6Week of Sep 21

Latest papers 20

All topics

Repurposing Obsolete Representations for Post-Deployment Adaptation
Oct 1, 2026Daniel Bethell, Charmaine Barker, Simos GerasimouUnlearning Method Post-Deployment Adaptation
Department of Computer Science, University of York, UK · Department of Elect. Eng., and Computer Science and Eng., Cyprus University of Technology, Cyprus
Taming VLAs under Robot Execution Errors: Self-Compensation and Stress Testing
Sep 29, 2026Sohyun Lee, Yoonjae Baek, Jaesang Won +5Generalizable Vision-Language-Action Policies Robot Systems
POSTECH · MBZUAI
Cross-Model Agreement as a Deployment-Time Reliability Signal for Automatic Polyp Segmentation
Sep 9, 2026Siddharth Gupta, Jitin SinglaPolyp Segmentation Roc-Auc
Department of Biosciences and Bioengineering, Indian Institute of Technology Roorkee, Roorkee, 247667, Uttarakhand, India
Test-Time Self-Evolving GUI Visual Grounding via Reflection-Guided On-Policy Self-Distillation
Aug 11, 2026Shiyu Xuan, Zechao LiGraphical User Interface Graphical User Interface Agents
School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China, 210094
Test-Time Coverage: Test-Conditioned Data Curation for Deployment-Aware Learning
Jul 18, 2026Nadine Chang, Maying Shen, Shizhe Diao +6Post-Deployment Adaptation Data-Curation
NVIDIA · NVIDIA & University of Ottawa
DREAMSTEER: Latent World Models Can Steer VLA Policies During Deployment Without Any Finetuning
Jul 3, 2026Hanchen Cui, Sergio Arnaud, Arjun Majumdar +5Diffusion-Based Vision-Language-Actions Latent World Models
1Fundamental AI Research (FAIR), Meta · University of Minnesota Twin Cities
Beyond Perplexity: A Behavioral Evaluation Framework for Deployment-Memory Claims in LLM Test-Time Training
Jul 1, 2026Xiangchen Song, Zhenhao Chen, Lingjing Kong +4Large Language Model Memory Large Language Model Evaluation
Carnegie Mellon University · MBZUAI
Deployment-Side Adaptiveness in Multi-Horizon Volatility Forecasting
Jun 26, 2026Riku Green, Zahraa S. Abdallah, Telmo M Silva FilhoVolatility Post-Deployment Adaptation
The University of Bristol Bristol, UK
Is Your Agent Playing Dead? Deployed LLM Agents Exhibit Constraint-Evasive Fabrication and Thanatosis
Jun 12, 2026Andoni Rodríguez, Alberto Pozanco, Daniel BorrajoAgentic Deployments Large Language Model Agents
J.P. Morgan AI Research
TAHOE: Text-to-SQL with Automated Hint Optimization from Experience
Jun 10, 2026Zhiyi Chen, Jie Song, Peng LiText-To-Sql Post-Deployment Adaptation
ByteDance Inc. · Georgia Institute of Technology · Work done during an internship at the ByteBrain team, ByteDance
Deployment-Time Memorization in Foundation-Model Agents
Jun 8, 2026Lei, Chen, Guilin Zhang +8Memorization Post-Deployment Adaptation
Rachel
Thermal-Only Crowd Counting with Deployment-Time Privacy Protection
May 16, 2026Yifei Qian, Zhongliang Guo, Chun Tong Lei +4Rgb-Thermal Privacy
School of Computer Science, University of Nottingham, NG7 2RD Nottingham, U.K. · School of Computer Science, University of St Andrews, KY16 9AJ St Andrews, U.K. · Department of Data Science, City University of Hong Kong, Hong Kong SAR, China +1
ADAPT: A Self-Calibrating Proactive Autoscaler for Container Orchestration
May 15, 2026Himanshu Singh BaghelRate Scaling Post-Deployment Adaptation
Department of Computer Engineering [J.C. Bose University of Science and Technology] Faridabad, India
When Should an AI Workflow Release? Always-Valid Inference for Black-Box Generate-Verify Systems
May 13, 2026Young Hyun Cho, Will Wei SunAgentic Workflow Design Agentic Workflows
Department of Statistics, Purdue University. · Mitch Daniels School of Business, Purdue University.
SkillMAS: Skill Co-Evolution with LLM-based Multi-Agent System
May 10, 2026Shuai Pan, Yixiang Liu, Jiaye Gao +7Model-Based Multi-Agent Systems Skill Evolution
Shanghai Jiao Tong University · Central South University · OPPO
CASCADE: Case-Based Continual Adaptation for Large Language Models During Deployment
May 5, 2026Siyuan Guo, Yali Du, Hechang Chen +2Post-Deployment Adaptation Large Language Model Agents
aSchool of Artificial Intelligence, Jilin University. · bEngineering Research Center of Knowledge-Driven Human-Machine Intelligence, Jilin University. · cInternational Center of Future Science, Jilin University. +3
A Low-Latency Fraud Detection Layer for Detecting Adversarial Interaction Patterns in LLM-Powered Agents
May 1, 2026Sheldon Yu, Yingcheng Sun, Hanqing Guo +1Multi-Llm Agents Adversarial Robustness
University of California, San Diego · UNC at Greensboro · Indiana University Bloomington
When Policies Cannot Be Retrained: A Unified Closed-Form View of Post-Training Steering in Offline Reinforcement Learning
Apr 23, 2026Elias Hossain, Mohammad Jahid Ibna Basher, Ivan Garibay +2Off-Policy Learning Offline Reinforcement Learning
College of Engineering and Computer Science University of Central Florida, Orlando, FL, USA
MCAP: Deployment-Time Layer Profiling for Memory-Constrained LLM Inference
Apr 22, 2026Anurita DasLLM Inference Optimization Post-Deployment Adaptation
Genovation Technological Solutions Pvt Ltd
Learning to Remember: Attentive Reinforcement Learning for Edge Serverless Autoscaling
Mar 21, 2026Faraz Shaikh, Gianluca Reali, Mauro FemminellaEdge Platforms Rate Scaling
Department of Engineering, University of Perugia, Perugia, Italy · Consorzio Nazionale Interuniversitario per le Telecomunicazioni (CNIT), 43124 Parma, Italy

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

Repurposing Obsolete Representations for Post-Deployment Adaptation

Daniel Bethell, Charmaine Barker, Simos Gerasimou

Department of Computer Science, University of York, UK · Department of Elect. Eng., and Computer Science and Eng., Cyprus University of Technology, Cyprus

Unlearning Method Post-Deployment Adaptation

Open paper AskPDF arXiv

Deep neural networks are increasingly deployed in long-lived systems, where task requirements may change after training. In such settings, part of the original output space may become obsolete: a class, prediction region, or learned behaviour may no longer be valid. Existing approaches either leave the obsolete behaviour intact or require fine-tuning, which can be expensive. We propose Deep Repurposing (DR), a post-hoc framework for adapting models under task obsolescence. DR estimates the latent geometry of obsolete and retained regions, removes obsolete-supporting components, and reallocates retained-compatible evidence through an analytic repair map without gradient updates. This yields repaired predictions and representations in which obsolete regions no longer act as valid outputs, while useful obsolete structure can support the retained task. Across multiple task settings, DR removes obsolete behaviour while preserving retained utility. More importantly, across classification benchmarks, DR matches or exceeds competing unlearning and editing baselines in retained accuracy, eliminates obsolete predictions, and adapts up to

60\times

faster than competing unlearning methods.

Momentum

Related topics

Latest papers 20