Test Time

Ask about this topic

Momentum

24 papers in the last four weeks, up 500% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28
View on map

Latest papers 134

All topics
CardsList

  1. How Much Can Language Models Gain from Test-Time Computation?

    Oct 1, 2026Bangji Yang, Jingyuan Li, Jiajun Fan +8Test TimeSelf

    University of Illinois at Urbana-Champaign · University of Washington · Tsinghua University

  2. Improving Predicted MOS Scores, Not Perceived Quality: Multi-Predictor Test-Time Optimization of Enhanced Speech

    Sep 30, 2026Tsubasa Ochiai, Marc Delcroix, Nahomi Kusunoki +5Mean Opinion ScoresSpeech Enhancement

    NTT, Inc., Japan · Waseda University, Japan

  3. Composing Task-specific Agent Harnesses at Test Time with Reusable Primitives

    Sep 30, 2026Peng Kuang, Haibo Jin, Dehao Wu +4Agent HarnessTest Time

    University of Illinois Urbana-Champaign · University of Michigan, Ann Arbor

  4. Budget Boundary Effects in Test-Time Mathematical Reasoning

    Sep 30, 2026Guilin Zhang, Ziqi Tan, Wulan Guo +5Mathematical ReasoningTest Time

    Yantong AI

  5. Port-Hamiltonian Latent Deliberation: Mitigating the Deliberation Drift Cliff in Test-Time Compute Scaling

    Sep 29, 2026Zeyu JiaTest-Time ScalingEfficient Latent Reasoning

    School of Biomedical Engineering and Technology, Tianjin Medical University, Medical School, Tianjin University

  6. UpliftMem: Learning Set-Level Uplift for Agent Memory Retrieval

    Sep 29, 2026Mengkun Liang, Haoran Qiang, Guannan Liu +1RiseTest Time

    MIIT Key Laboratory of Data and Decision Intelligence Beihang University Beijing, China

  7. T2^2Mem: Learning Test-Time Memory for Robotics

    Sep 29, 2026Yize Liu, Huang Huang, Yining Hong +4Robotic ManipulationTest Time

    Stanford University · NVIDIA · University of Michigan, Ann Arbor

  8. Test-Time Adaptation of Manipulation Policies Under Actuator Degradation

    Sep 28, 2026Som Sagar, Ransalu SenanayakeActuatorGoal-Conditioned Value Function

    School of Computing and Augmented Intelligence, Arizona State University, Tempe, Arizona

  9. Scouting the Dynamics Gap: Test-Time Policy Adaptation via Action-Outcome Feedback

    Sep 28, 2026Yishu Li, Liyuan Geng, Xinyi Mao +2Robot PoliciesMeta-Learning

    Robotics Institute, Carnegie Mellon University · Computer Science and Technology, Tsinghua University

  10. Harness Learning Enables Generalizable Test-Time Adaptation

    Sep 28, 2026Alvin Zhang, Xuecheng Liu, Zixuan Wang +6Agent HarnessEfficient Task Adaptation

  11. Rethinking Personalized Generation: Test-Time Alignment via Factorized Ranking Models

    Sep 28, 2026Qiyao Ma, Junshan Zhang, Zhe ZhaoLarge Language Model PersonalizationLarge Language Model Reranking

    University of California, Davis

  12. Transferable Mass Spectrum Prediction via Reference-Guided Test-time Specialization

    Sep 28, 2026Yunhua Zhong, Runting Li, Yifan Li +5Tandem Mass SpectraMetabolic

    The Hong Kong University of Science and Technology (Guangzhou) · The University of Hong Kong · South China University of Technology +3

  13. Backdoor as Probe: Test-Time Adversarial Defense for CLIP

    Sep 28, 2026Zhongqi Wang, Jie Zhang, Nie Sen +3Test Time

    Key Laboratory of AI Safety of CAS, Institute of Computing Technology, Chinese Academy of Sciences (CAS), Beijing, China · University of Chinese Academy of Sciences, Beijing, China · Xuzhou University of Technology, China

  14. FlexLoop: Depth-Elastic Looped Policies for Adaptive Test-Time Computation in Deep RL

    Sep 28, 2026Xun Wang, Ruishuo Chen, Yu Chen +2Offline Reinforcement LearningLoop

    Institute for Interdisciplinary Information Sciences, Tsinghua University

  15. Knowing When Thinking Is Not Enough: Teaching Small Reasoning Models to Reason Beyond Their Parametric Knowledge

    Sep 28, 2026Chanuk Lee, Minki Kang, Sangwoo Park +3Small Reasoning ModelTest Time

    KAIST

  16. JET: Judge-Guided Evolution at Test Time for Agent Programs

    Sep 28, 2026Yao Long Teng, Jiayi Cai, Bo AnEvolutionary Optimization MethodsTest Time

    Nanyang Technological University

  17. Planned Test-Time Scaling with Coordinated Reasoning Paths

    Sep 23, 2026Xueqing Wu, Langxing Bai, Hritik Bansal +5Test-Time ScalingTest Time

    University of California, Los Angeles · Amazon

  18. Beyond Visual Quality: A Study of Test-Time Planning with World Action Models

    Sep 21, 2026Jianhao Yuan, Yu Yuan, Benjamin Ramtoula +5Action SelectionWorld Model Planning

    University of Oxford · Purdue University · UWE Bristol

  19. Intelligence Under Time Constraints: Rethinking Test-Time Compute

    Sep 14, 2026Xiaotian ZhangComputational CostDeadlines

    Trooly.AI

  20. Confidence-Gated Transductive Test Generation for Code Reranking

    Sep 14, 2026Sungjae Lee, Youngsik Yoon, Seockbean Song +3Test GenerationTest Time

    Department of Computer Science and Engineering, POSTECH, South Korea · Graduate School of Artificial Intelligence, POSTECH, South Korea · Microsoft Research Asia, China

  21. An Open Recipe for IMO Gold: Training Nemotron for Olympiad Mathematics

    Sep 12, 2026Ivan Moshkov, Stephen Ge, George Armstrong +3Olympiad-Level ProblemProof

    NVIDIA

  22. Amortized Low-Rank Adaptation for Model-Based Reinforcement Learning

    Sep 10, 2026Fernando Palafox, David Fridovich-KeilModel-Based Reinforcement LearningIn-Context Learning

    University of Texas at Austin Austin, TX, USA

  23. Rethinking Indirect Prompt Injection as a Test-Time Search Problem

    Sep 7, 2026Duong M. Nguyen, Joon Sik Kim, Blazej Manczak +1Indirect Prompt InjectionCyberattacks

    Dynamo AI · University of Illinois Urbana-Champaign

  24. A Removal Based Approach to Improve LLM Faithfulness at Test-Time

    Sep 7, 2026Qinglan Luo, S M A Nahian, John Guttag +2Large Language Model ReliabilityFaithful Explanation

    MIT CSAIL · MGH, HMS

  25. What Else Needs Fixing? Exploring Cost-Effective Test-Time Compute for Revision Propagation in Artifacts Generated Through Conversation

    Sep 3, 2026Daisuke KikutaStructured ArtifactsTest Time

    NTT, Inc.

  26. HSRM: Hidden-State Reward Models for Test-Time Verification

    Aug 31, 2026Xianzhi Li, Xiaodan ZhuMathematical ReasoningTest Time

    Department of Electrical and Computer Engineering & Ingenuity Labs Research Institute Queen’s University

  27. Claim-Level Reliability Assessment for Efficient Test-Time Reasoning

    Aug 12, 2026Sen Xu, Wei Wang, Shixi Liu +5FalsehoodTest Time

    Sina Weibo Inc.

  28. Consilience for Verifier-Free Test-Time Scaling

    Aug 10, 2026Lecheng Kong, Like Hui, Haitao Mao +1Test-Time ScalingTest Time

    AWS AI Labs

  29. Efficient Test-Time Scaling for LLM-based Time Series Forecasting

    Aug 9, 2026Xuan-May Le, Minh-Tuan Tran, Ling Luo +3Time Series ForecastingLarge Language Model Forecasting

    The University of Melbourne Melbourne, Victoria, Australia · Monash University Melbourne, Victoria, Australia

  30. Forgotten History or Test-of-Time? Retrospect and Prospect on RAG from an IR Perspective

    Aug 9, 2026Xiaoyan Zhao, Yujie Cai, Yang Zhang +2HistoryTest Time

    National University of Singapore · Georgetown University

  31. Thought-Level Beam Search for Reasoning

    Aug 8, 2026Lijie Yang, Hongyin Luo, Jiawei Zhao +2Large Reasoning ModelsBeam Search

    Princeton University · MIT CSAIL · Meta AI

  32. Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions

    Aug 8, 2026Chenrui Fan, Yize Cheng, Ming Li +3Large Reasoning ModelsTest Time

    University of Maryland, College Park · MBZUAI, UAE

  33. CoBa: Cost-Effective Test-Time Scaling via Compute-Balanced Routing

    Aug 7, 2026Yan Zhou, Yue Ouyang, Kaiyang Zheng +1Test-Time ScalingTest Time

    School of Mathematics and Statistics, Changsha University of Science and Technology, Changsha, China · School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, China.

  34. Iterate or Widen? When Test-Time Refinement Helps LiDAR Scene Completion: A Controlled Study of Evidence Geometry, Training Coverage, and Compute

    Aug 6, 2026Shijie Hao, Weining ZhangIterative RefinementRefinement

    Phillips Exeter Academy · Cheung Kong Graduate School of Business

  35. Refining Over Resampling: Test-Time Self-Correction for LLM Reasoning

    Aug 6, 2026Ahsan Bilal, Muhammad Ahmed Mohsin, Muhammad Umer +4LLM Reasoning StrategiesTest Time

    University of Oklahoma · Stanford University · Universitat Pompeu Fabra +1

  36. Consistency-Driven Co-Evolution for Self-Supervised Cross-Representation Learning

    Aug 5, 2026Xuehang Guo, Pengyuan Li, Tom Hope +3Self-Supervised RepresentationsImage-To-Code Generation

    William & Mary · IBM · Allen Institute for AI +2

  37. Interpretable Adaptive Sampling for LLM Test-Time Scaling

    Aug 4, 2026Mobina Kashaniyan, Ali JannesariTest-Time ScalingTest Time

    Iowa State University Ames, IA, USA

  38. Aligning Large Vision-Language Models at Test Time: A Trajectory-Guided Structured Sampling Approach

    Aug 4, 2026Tianbao Jiang, Weicong Ni, Gerard de Melo +1Visual ReasoningTest Time

    East China Normal University Shanghai, China · Hasso Plattner Institute Potsdam, Germany · University of Potsdam Potsdam, Germany +1

  39. It's the Decoding Format, Not the Perturbation: Auditing Consistency-Based Selection for Vision-Language Test-Time Scaling

    Aug 2, 2026Puzhuo Zheng, Hasan KurbanTextvqaTest Time

    College of Science and Engineering, Hamad Bin Khalifa University, Doha, Qatar

  40. PeCA: Palette Context Assisted Inference for Test-Time Paint-Bucket Colourisation on Animation Videos

    Aug 2, 2026Dongheng Lin, Jianbo JiaoCanvasPixelloop

    The MIx Group, University of Birmingham, Birmingham, United Kingdom

  41. SVR: Self-Verifying Refinement via Joint Verdict-Confidence Reinforcement Learning for Adaptive Test-Time Compute

    Jul 30, 2026Hongyu Chen, Liang Lin, Guangrun WangReinforcement Learning With Verifiable RewardTest Time

    1Sun Yat-sen University · 2Guangdong Key Laboratory of Big Data Analysis and Processing · 3X-Era AI Lab

  42. Eviction as Estimation: A Fixed-Lag Smoothing View of Test-Time Memory, and When Measuring Beats Accumulating

    Jul 27, 2026Maruthi Vemula, Neeraj Praneeth GajulaWorking MemoryEviction

    University of North Carolina at Chapel Hill · New York University

  43. CachedSearch: Training-Free Cached Exploration for Test-Time Search in Video Diffusion

    Jul 25, 2026Shreshth Saini, Neil Birkbeck, Yilin Wang +2Video Diffusion ModelsTest Time

    1The University of Texas at Austin · 2Google, Inc. · University of Colorado Boulder

  44. When Does Recurrence Become an Algorithm? Convergence Selection in Weight-Tied Looped Transformers

    Jul 22, 2026Tong Zhang, Junhao Hu, Yun Peng +1RecurrenceTransformer Architectures

    Fudan University · Peking University

  45. Test-Time Registers as Global Priors for Tokenized Image Generation

    Jul 18, 2026Cheng-Yao Hong, Yifan Wang, Yuewei Lin +1Visual TokenizersSingle-Cell Foundation Models

    Stony Brook University · Brookhaven National Laboratory

  46. Efficient Frame Selection for Long Videos at Test Time with Attention-Based MLLM Selectors

    Jul 17, 2026Yilin Wang, Xiangxi Zheng, Dongxing Mao +6Long VideosMultimodal Large Language Models

    ZJU · NJU · CSU +2

  47. EXPLORE: Exploration with Guided Search for Analog Topology Generation using Language Models

    Jul 15, 2026Guanglei Zhou, Chen-Chia Chang, Yikang Shen +5Analog DesignCommunication Topologies

    Electrical and Computer Engineering, Duke University, Durham, USA · MIT-IBM Watson AI Lab, Cambridge, USA · IBM T. J. Watson Research Center, Yorktown Heights, USA

  48. Forgetful Attention: A Trainable Support-Vector Memory with Certified Selection and Exact Unlearning

    Jul 13, 2026Vishwajith RameshLinear AttentionForgetting

    Vy Labs, Inc.

  49. Interaction Scaling: Grounding the Third Axis of Test-Time Compute

    Jul 13, 2026Bojie Li, Noah ShiTest-Time ScalingTest Time

    Pine AI · University of Washington

  50. Efficient Test-Time Optimization for Multi-Agent Proof Autoformalization

    Jul 13, 2026Tian-Shuo Liu, Shiyuan Zhang, Zijie Geng +5AutoformalizationTheorem Proving

    National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China · Polixir Technologies, Nanjing, China · University of Science and Technology of China, Hefei, China

  51. Selective Left-Shift: Turning Test-Time Compute and Difficulty-based Curation into Training Data for Low-Resource Code Generation

    Jul 8, 2026Didula Samaraweera, Anjana Supun, Srinath PereraCode GenerationSmall Large Language Models

    WSO2 Santa Clara, CA, USA

  52. PriGo: Test-Time Primitive Guidance to Diffusion and Flow Policies for Adaptive Robotic Manipulation

    Jul 8, 2026Zezeng Li, Enda Xiang, Thuy Tran +3Robotic ManipulationImitation Learning

    Ecole Centrale de Lyon, France · Beihang University, China

  53. WAM-TTT: Steering World-Action Models by Watching Human Play at Test Time

    Jul 8, 2026Yusen Feng, Bingchen Han, Jiangran Lyu +13Efficient World-Action ModelWorld Models

    Peking University · Galbot · CASIA +1

  54. Cost-Effective Agent Harnesses for Abstract Reasoning and Generalization on ARC-AGI-1

    Jul 7, 2026Kabir Moghe, Peter ChinAgentic ReasoningTest Time

    Department of Computer Science Dartmouth College

  55. DART-VLN: Test-Time Memory Decay and Anti-Loop Regularization for Discrete Vision-Language Navigation

    Jul 1, 2026Shaoheng Zhang, Zhichen Li, Jie MeiVision-Language NavigationFrozen Vision-Language Models

    School of Intelligence Science and Engineering Harbin Institute of Technology, Shenzhen Shenzhen, China · School of Computer Science and Technology Harbin Institute of Technology, Shenzhen Shenzhen, China

  56. Selective Test-Time Debiasing for CLIP via Reward Gating

    Jul 1, 2026Jaeho Han, Jisoo Yang, Hyeondong Woo +3Vision-Language Model AdaptationZero-Shot Robustness

    Department of Artificial Intelligence, Chung-Ang University

  57. 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 MemoryLarge Language Model Evaluation

    Carnegie Mellon University · MBZUAI

  58. ELASTIC: Efficiently Learning to Adaptively Scale Test-Time Compute for Generative Control Policies

    Jun 30, 2026Andrew Zou Li, Gokul Swamy, Yonatan Bisk +1Generative Control PoliciesTest-Time Scaling

    Carnegie Mellon University

  59. Test-Time Verification for Text-to-SQL via Outcome Reward Models

    Jun 29, 2026Mattia Tritto, Giuseppe Farano, Dario Di Palma +4Text-To-SqlTest Time

    Polytechnic University of Bari, Bari, Italy · IBM T.J. Watson Research Center, Yorktown Heights, NY, USA

  60. ReGuide: From Test-Time Guidance to Self-Improving Diffusion Policies

    Jun 27, 2026Tzu-Hsiang Lin, Srinivas Shakkottai, Dileep Kalathil +1Diffusion PoliciesGuidance

    Texas A&M University