Text-Only Adaptation

Follow this topic Ask about this topic

Momentum

2 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

Jul 6Week of Sep 21

Latest papers 24

All topics

You Only Reprogram Once: Rethinking Prolonged Training for Visual Reprogramming
Sep 29, 2026Zizhao Li, Mohammed Yaqoob Ansari, Xinyu Su +3Visual In-Context Learning Text-Only Adaptation
The University of Melbourne · Fudan University
Separating personal from population gains when calibrating EEG foundation models for new users
Sep 28, 2026Xilin Tao, Kani ChenElectroencephalography Foundation Models Wireless Foundation Models
Department of Mathematics, The Hong Kong University of Science and Technology, Hong Kong SAR, China · Department of Industrial Engineering and Decision Analytics, The Hong Kong University of Science and Technology, Hong Kong SAR, China
CompAdapt: Adaptable Composite Motion Modeling for Physics-Consistent Text-to-Video Generation
Sep 18, 2026Haoran Qin, Renlong Wu, Tianyu Huang +3Text-To-Video Generation Model Text-To-Video Diffusion Models
Harbin Institute of Technology, China · Taobao, Alibaba Group, China
Privacy-Aligned Personalized Federated Learning with Compact Adaptation and Variable-Length Gaussian Communication
Sep 14, 2026Yilin Xu, Chun Hei Michael Shiu, Chih Wei Ling +1Federated Learning Parameter-Efficient Adaptation
Department of Computer Science, City University of Hong Kong · Department of Electrical and Computer Engineering, University of British Columbia · School of Computer Science and Engineering, Hebrew University of Jerusalem
CoAdapt-GUI: Joint Workflow Context and Policy Adaptation for Unseen GUI Applications
Aug 12, 2026Linqiang Guo, Li Gu, Zihuan Jiang +8Graphical User Interface Agents Text-Only Adaptation
Peter · Concordia University · Mila – Québec AI Institute +2
PAST: Privileged Adaptation from Complete Student Trajectories for On-Policy Self-Distillation
Aug 9, 2026Yangyang Feng, Zhuoyan Feng, Junlan ChenSingle Trajectory Mathematical Reasoning Benchmarks
1The Hong Kong University of Science and Technology (Guangzhou) · 2Sun Yat-sen University
Localized Adaptation Reveals Distinct Learning Signatures in Transformers
Jul 28, 2026Rebecca Ramnauth, Brian ScassellatiText-Only Adaptation Transformer Architectures
Yale University
Open-Ended Scenario Reasoning for Specialist Model Adaptation
Jul 7, 2026Youcheng Zong, Runda Jia, Ranmeng Lin +2Text-Only Adaptation Large Language Model Reliability
College of Information Science and Engineering, Northeastern University, Shenyang 110004, China
LLM-as-a-Tutor: Policy-Aware Prompt Adaptation for Non-Verifiable RL
Jul 5, 2026Yujin Kim, Namgyu Ho, Sangmin Hwang +7Reinforcement Learning With Verifiable Reward Tutors
1KAIST · 2Upstage · University of Toronto +2
CORTIS: Text-Only Adaptation of Spoken Language Models for Task-Oriented Voice Agents
Jun 19, 2026Youngwon Choi, Hyeonyu Kim, Taeyoun Kwon +2Voice Agents Text-Only Adaptation
Maum AI Inc. · Seoul National University · Korea Culture Technology Institute +1
EntroAD: Structural Entropy-Guided Prompt Adaptation for Zero-Shot Anomaly Detection
May 27, 2026Xinyu Zhao, Qingyun Sun, Jiayi Luo +1Multimodal Anomaly Detection Logical Anomalies
Beihang University Beijing, China
StoryLens: Preference-Aligned Story Rewriting via Context-Aware Narrative Enrichment
May 27, 2026Hanwen Cui, Yuting Mei, Yuhang Fu +2Rewrite Narrative Generation
Beijing University of Posts and Telecommunications · AIM3 Lab, Renmin University of China · Nanyang Technological University
Segment Anything with Motion, Geometry, and Semantic Adaptation for Complex Nonlinear Visual Object Tracking
May 21, 2026Deyi Zhu, Yuji Wang, Yong Liu +4Multi-Object Tracking Video Object Segmentation
Shenzhen International Graduate School, Tsinghua University, Shenzhen 518055, China · Department of Automation, Tsinghua University, Beijing 100084, China
Leveraging LLMs for Grammar Adaptation: A Study on Metamodel-Grammar Co-Evolution
May 20, 2026Weixing Zhang, Bowen Jiang, Rahul Sharma +2Large Language Model Adaptation Text-Only Adaptation
Karlsruhe Institute of Techonology, Germany · Universität Rostock, Germany · Chalmers University of Technology and University of Gothenburg, Sweden +1
Continual Fine-Tuning of Large Language Models via Program Memory
May 13, 2026Hung Le, Svetha VenkateshTraining-Side Stage-Aware Low-Rank Adaptation Replay-Based Continual Learning
Deakin Applied AI Initiative, Deakin University, Australia
ConRetroBert: EMA Stabilized Dual Encoders for Template-Based Single-Step Retrosynthesis
May 12, 2026Mohammad Jahid Ibna Basher, Ali Khodabandeh Yalabadi, Ivan Garibay +1Reaction Bert-Based Models
Department of Industrial Engineering University of Central Florida Orlando, FL 32816
Channel Adaptation for EEG Foundation Models: A Systematic Benchmark Across Architectures, Tasks, and Training Regimes
Apr 25, 2026Kuntal Kokate, Bruno Aristimunha, Dung Truong +1Electroencephalography Foundation Models Parameter-Efficient Adaptation
Swartz Center for Computational Neuroscience, Institute for Neural Computation, University of California San Diego, La Jolla, CA 92093, USA · Yneuro, Paris, France · Centre de Recherche Cerveau et Cognition, CNRS, Université Paul Sabatier, Toulouse, France
On the Identifiability of User Adaptation in Co-Adaptive Neural Interfaces
Apr 24, 2026Philip WaggonerText-Only Adaptation Identifiability
Stanford University
Evaluating Adaptive Personalization of Educational Readings with Simulated Learners
Apr 17, 2026Ryan T. Woo, Anmol Rao, Aryan Keluskar +1Computerized Adaptive Testing Text-Only Adaptation
School of Computing and Augmented Intelligence, Arizona State University
EvoSpec: Evolving Speculative Decoding via Real-Time Vocabulary and Parameter Adaptation
Apr 17, 2026Shuyu Zhang, Lingfeng Pan, Qicheng Wang +6Speculative Decoding LLM Inference Optimization
School of Computer Science and Technology Xidian University Xi’an, China
TIDE: Temporal Incremental Draft Engine for Self-Improving LLM Inference
Feb 5, 2026Jiyoung Park, Hankyu Jang, Changseok Song +1LLM Inference Optimization Speculative Decoding
Moreh, Inc.
Text-only adaptation in LLM-based ASR through text denoising
Jan 28, 2026Andrés Carofilis, Sergio Burdisso, Esaú Villatoro-Tello +8Automatic Speech Recognition Large Language Model Adaptation
Idiap Research Institute · EPFL, Lausanne · Uniphore +2
AdaFuse: Adaptive Ensemble Decoding with Test-Time Scaling for LLMs
Jan 9, 2026Chengming Cui, Tianxin Wei, Ziyi Chen +6Large Language Model Adaptation Large Language Model Decoding
University of Illinois Urbana-Champaign
WhisTLE: Deeply Supervised, Text-Only Domain Adaptation for Small Pretrained Speech Recognition Transformers
Sep 12, 2025Akshat Pandey, Karun Kumar, Raphael TangDomain Adaptation Text-Only Adaptation
Comcast · Speech AI · Washington, D.C., USA +3

Sep 29, 2026, cs.CVJ/K move · Enter open · S save

You Only Reprogram Once: Rethinking Prolonged Training for Visual Reprogramming

Zizhao Li, Mohammed Yaqoob Ansari, Xinyu Su, Jiayang Ao+2

The University of Melbourne · Fudan University

Visual In-Context Learning Text-Only Adaptation Gradient-Based Optimization Responses

Open paper AskPDF arXiv

Visual reprogramming is a parameter-efficient method for adapting pretrained models, yet its training can remain computationally expensive: even with a frozen backbone, visual prompts are often optimized through the full model for hundreds of epochs. Before changing what the pretrained model sees, we ask whether we are fully using what it already tells us. We find that modeling the full source response can already yield strong downstream predictions without prompt optimization. Motivated by this observation, we introduce You Only Reprogram Once (YORO), which constructs a downstream predictor from the frozen response space in a single forward-only traversal. Its Bayesian Discriminant Mapping (BDM) derives a covariance-aware affine mapping from streaming class statistics, requiring no backpropagation, optimizer updates, or repeated visits to the training set. When further input adaptation helps, YORO-FP optionally refines the visual prompt for 20 epochs. BDM also extends naturally to CLIP by treating attribute-prompt similarities as source responses. Across three full-data settings, YORO improves average accuracy over the strongest prior gradient-free mapping by 18.4--24.4%. On 16-shot CLIP, it raises the four-backbone average from 71.4% to 77.2%. YORO-FP provides further gains on selected tasks, while validation often retains the one-pass predictor. These results suggest a different default for visual reprogramming: read out the frozen response first, and optimize the input only when needed.

Momentum

Related topics

Latest papers 24