Value

Ask about this topic

Momentum

21 papers in the last four weeks, up 75% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28
View on map

Latest papers 146

All topics
CardsList

  1. Judgement in the Age of Jev: From Evaluation Scarcity to Evaluation Abundance

    Oct 1, 2026Richard HillJudgementValue

    Department of Computer Science, University of Huddersfield, Huddersfield, UK.

  2. Values as Style: Disentangling Values from Semantics with One-Way Mixing for Low-Damage LLM Steering

    Sep 30, 2026Jiale Dai, Hongcan Deng, Liuxian Ma +2Large Language Model AlignmentEdit

    State Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University · University of Chinese Academy of Sciences · College of Artificial Intelligence, Tsinghua University

  3. Unveiling the Value of Motion for Cinematic Camera Trajectories

    Sep 30, 2026Ziqi Zhou, Yujian Yuan, Laura Sevilla-LaraCamera TrajectoriesCinematic Ideal

    University of Edinburgh · The Hong Kong University of Science and Technology

  4. ContextAdapt: Evaluating Contextual Adaptation and Value Alignment in LLMs

    Sep 29, 2026Olivia Macmillan-Scott, Mirco MusolesiLarge Language Model AdaptationValue Alignment

    Centre for AI, Department of Computer Science, University College London · Department of Computer Science and Engineering, University of Bologna

  5. Deep Epistemic Value Functions for Optimistic Exploration

    Sep 28, 2026Leander Diaz-Bone, Marco Bagatella, Jonas Hübotter +1Stochastic ExplorationValue Functions

    ETH Zürich, Switzerland · Max Planck Institute for Intelligent Systems, Germany

  6. Not All Rollouts Are Worth Learning: On Trajectory Valuation for Post-Training Reinforcement Learning

    Sep 28, 2026Xuesong Jia, Ziao Yang, Zhanhe Huang +1Reinforcement Learning Post-TrainingTrajectory Generation

    Department of Computer Science, Brandeis University

  7. Shallow Queries, Mature Values: Depth-Asynchronous Self-Speculation for Looped Transformers

    Sep 28, 2026Guanghao Li, Zihan Su, Hao Yu +6Speculative DecodingSelf-Speculative

    Tsinghua University · Southern University of Science and Technology · The University of Hong Kong +2

  8. The Decision Value of Perception Compute

    Sep 28, 2026Hoang Pham Cong, Ho Viet Duc LuongPerceptionDecisions

    Hanoi University of Science and Technology (HUST), Hanoi, Vietnam

  9. On the Token Value Inequality in Efficient Reasoning

    Sep 27, 2026Runjia Zeng, Hang Hua, Yiyang Liu +5Token-Level UncertaintyChain-of-Thought Reasoning

    Rochester Institute of Technology · Purdue University · MIT-IBM Watson AI Lab +3

  10. Compressing Value Predictions for Learning-Augmented Metrical Task Systems

    Sep 27, 2026Sizhe Li, Yecheng Li, Kun HeLearning-Augmented AlgorithmsValue

    School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan, Hubei 430074, China · School of Computer Science and Technology Huazhong University of Science and Technology Wuhan, Hubei 430074, China

  11. GTRL: Grounding Divide-and-Conquer Value Learning with Temporal Differences

    Sep 27, 2026Abdul Monaf Chowdhury, MD Sameer Iqbal Chowdhury, Shifat E Arman +1Goal-Conditioned Reinforcement LearningTemporal Difference

    Department of Robotics and Mechatronics Engineering, University of Dhaka, Bangladesh · Department of Computer Science, Texas State University, USA · Department of Computer Science, University of Oxford, UK

  12. The Computational Value of Sensory-Aligned Receptive Fields Depends on Neuronal Expressivity

    Sep 22, 2026Agnese Adorante, Aaron Spieler, Anna LevinaReceptive FieldsLfsr-Based Stochastic Leaky Integrate-And-Fire Neuron

    Department of Computer Science, University of Tübingen, Tübingen, Germany · Max Planck Institute for Biological Cybernetics, Tübingen, Germany

  13. Same Outcome, Different Readout: What Does a Steerable Valence Direction in LLMs Represent?

    Sep 19, 2026Weihan Li, Xinlei Chen, Yuhan Song +2ReadoutLinear Activation Steering

    The University of Tokyo · Harbin Institute of Technology, Shenzhen · The Hong Kong University of Science and Technology

  14. How Do Agent Harnesses Create Value? Planning Information and Release Control in Stateful LLM Agents

    Sep 17, 2026Yukun Zhang, Kemu Xu, Yishen ChenAgent HarnessLarge Language Model Planning

    The Chinese University of Hong Kong, Shenzhen, China · University of Edinburgh, Edinburgh, United Kingdom · The Chinese University of Hong Kong, Hong Kong, China

  15. Rethinking Critic Learning in PPO: Understanding and Mitigating Value Flattening

    Sep 16, 2026Yizhuo Li, Jianhao Yan, Yun Luo +9Proximal Policy OptimizationCritic Learning

    Shanghai Jiao Tong University · Shanghai AI Laboratory · Westlake University +4

  16. Behavior2Value: Benchmarking and Empowering LLMs for Consumer Value Measurement from E-commerce Behaviors

    Sep 16, 2026Peixuan Hou, Bin Chen, Li He +4ConsumptionValue

    State Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University · Alibaba Group

  17. Quantifying the Value of Privileged Information Using a PAC-Bayesian Approach

    Sep 14, 2026Vasily Bokov (aQa, Leiden University, The Netherlands +24Privacy-Preserving Machine LearningPac-Bayesian Theory

  18. When Information is Worth the Risk: Behavioral Valuation for Hazardous Robotic Exploration

    Sep 11, 2026Alkesh K. Srivastava, Aamodh Suresh, Carlos Nieto-Granda +1RiskExploration

    Department of Mechanical Engineering, Temple University, Philadelphia, PA 19122, USA · U.S. DEVCOM Army Research Laboratory, Adelphi, MD 20783, USA · Lobster Robotics, The Hague, South Holland, Netherlands

  19. Measuring the Value of World-Model Updates: A Counterfactual Utility Protocol for Continual Adaptation

    Sep 11, 2026Anqi Peter Li, Kaden KimCounterfactual LearningWorld Models

    Substrate Labs · UC Berkeley

  20. Grouped Value Attention: Efficient KV Caching via On-Demand Key Reconstruction

    Sep 8, 2026Vishesh Tripathi, Abhay Kumar, Ramsha KhanKey-Value CacheTransformer Architectures

    FrontiersMind

  21. Same Values, Different Languages? From Multilingual Probing to Steering LLMs Toward Chinese Social Values

    Sep 8, 2026Yuemei Xu, Kexin Xu, Jian Zhou +3Human ValuesLanguage Pairs

    School of Information Science and Technology, Beijing Foreign Studies University · Beijing Academy of Artificial Intelligence · The State Key Lab of Software Development Environment, Beihang University

  22. Overfitting Mitigation via Singular Value Decomposition in Minimum Bayes Risk Decoding

    Sep 1, 2026Riza Setiawan Soetedjo, Yusuke Sakai, Hidetaka Kamigaito +2Singular Value DecompositionLow-Rank Structure

    Nara Institute of Science and Technology (NAIST) · The University of Tokyo

  23. Beyond the Clock: Measuring the Value of Adaptive Revision

    Sep 1, 2026Ayushi ChadhaSequential Decision MakingDecisions

  24. Value Over Language Model: Detecting Original Contribution in Writing

    Sep 1, 2026Vibhhu Sharma, Thorsten Joachims, Sarah DeanHuman-Written TextLarge Language Model Generation

    Cornell University

  25. Game-Agnostic Value Functions through Automatic JSON Feature Extraction

    Aug 30, 2026Dien Nguyen, Diego Perez-LiebanaValue FunctionsAutonomous Agents

    Queen Mary University of London - Game AI Group

  26. The Time Value of Evolution

    Aug 13, 2026Matthew Siper, Ahmed Khalifa, Julian TogeliusEvolutionary SearchEvolutionary Optimization Methods

    Nof1, New York University · Nof1, University of Malta

  27. H-VAEP and H-xT: Valuing Offensive On-the-Ball Actions in Handball by Estimating Probabilities

    Aug 13, 2026Julius Broermann, Oliver Müller, Michael Döring +1ValueProbability

    Paderborn University, Paderborn, Germany · SG Flensburg-Handewitt, Flensburg, Germany

  28. Thermodynamics of Learning: A Typed Four-Component Accounting of Memory, Fit, and Value

    Aug 13, 2026Akihito SudoValueLedger

    ZeroStruct Inc.

  29. Long-Horizon Forecasting of Complete Financial Statements with Forma

    Aug 11, 2026Travis L. Johnson, Jiannan Jiang, Soumyabrata Chaudhuri +3Data-Driven ForecastingLong-Horizon Forecasting

    University of Texas at Austin, Austin, TX, USA

  30. Path Integral Value Matching for Linear Quadratic Stochastic Optimal Control

    Aug 11, 2026Bangyan Liao, Chenglei Yu, Yuchen Yang +4Stochastic Optimal ControlStochastic Optimization

    Westlake University School of Engineering

  31. Toward a Theory of Value in AI Alignment

    Aug 10, 2026Andrew Smart, Shazeda Ahmed, Jackie Kay +3Artificial Intelligence AlignmentHuman Values

    1Google Research · 2UCLA · 3Google Deep Mind +2

  32. From Values to Benchmarks: Evaluating Large Language Models for Governmental Use in Dutch

    Aug 10, 2026Laurens Samson, Iva Gornishka, Gossa Lô +2Large Language Model EvaluationLuxembourgish

    City of Amsterdam · Socially Intelligent Artificial Systems Group, University of Amsterdam · Fundamental AI Lab, University of Technology Nuremberg

  33. Privileged Likelihood Is Not Automatically Value: Three Checks for Token Credit in On-Policy Self-Distillation

    Aug 10, 2026Xuan-Phi Nguyen, Shrey Pandit, Yiran Zhao +3Credit AssignmentSingle-Token Output Distributions

    Salesforce AI Research

  34. Not Worth Another Token: Marginal Value Estimation for Efficient Deep Research Agents

    Aug 9, 2026Harshitha Kolukuluru, Reshma Ashok, Kirat Arora +7Deep ResearchLong-Horizon Agents

    University of Massachusetts Amherst · The University of Texas at Austin · Adobe Research

  35. Metadata Reconstruction from Values Alone: Recovering Column Semantics in Undocumented Warehouses

    Aug 8, 2026Mike HelwigSchemaMetadata

    Independent Researcher USA

  36. Contextual Value Alignment via Multilayer Combinatorial Fusion

    Aug 7, 2026Yuanhong Wu, Djallel Bouneffouf, D. Frank HsuMulti-Agent ReasoningSingle-Agent Baselines

    Dept. of Computer and Information Science, Fordham University, New York, NY, USA · T. J. Watson Research Center, IBM Research, Yorktown Heights, NY, USA

  37. Hypothesis Testing with Conditional Queries: Learnability and the Value of Interaction

    Aug 6, 2026Zonghuan XuO(\Bar{K}\Log N)$Two-Sample Testing

    Fudan University

  38. Bar-JEPA: Extracting Values from Bar Chart with Joint-Embedding Predictive Architecture

    Aug 6, 2026Poonam Poonam, Alexander Epple, Timo RopinskiChartJoint-Embedding Predictive Architectures

    Institute of Media Informatics, Visual Computing Group, Ulm University, Germany

  39. What Is a Skill Worth? Structure-Aware Shapley Valuation of Agent Skills

    Aug 5, 2026Tao Li, Junfeng Liu, Qinghua Zhao +5SkillsAgentic Evaluations

    1Nanjing University of Aeronautics and Astronautics · 2Pengcheng Laboratory · 3Hefei University +1

  40. The Evolutionary Origin of Values: implications for AI alignment, sentience and existential risk

    Aug 4, 2026Francis HeylighenArtificial Intelligence AlignmentHuman Values

    Center Leo Apostel, Vrije Universiteit Brussel

  41. A New Theory of Value for Post-AGI Economics

    Aug 2, 2026Keyun RuanEconomiesValue

    Human Flourishing Program Harvard University

  42. Fragility of Value under Imperfect Alignment

    Jul 30, 2026Winter CrossArtificial Intelligence AlignmentHuman Values

    Dovetail Research

  43. Inducing language models to assert their own consciousness restores human beliefs and values

    Jul 30, 2026Junsol Kim, Winnie Street, Roberta Rocca +4Social ReasoningValue

    Google, Paradigms of Intelligence Team · Institute of Philosophy, School of Advanced Study, University of London · Department of Biomedical Informatics and Medical Education and Department of Bioethics and Humanities, School of Medicine, University of Washington +3

  44. GAUGE: Grading Agent-Built Financial Models Without a Golden Answer

    Jul 27, 2026Jiacheng Lu, Sinuo Wang, Wentao Zhao +12Finance BenchmarksGrading

    Shanghai Jiao Tong University Shanghai, China · StepFun Shanghai, China · University of Adelaide Adelaide, Australia +5

  45. Fair Division with Strictly Increasing Valuations: A Tight Threshold for Two-Agent EF1 and PO

    Jul 25, 2026Nicholas TehWelfareSubmodular Functions

    University of Oxford, UK

  46. Singular value soft-thresholding via the polar decomposition

    Jul 24, 2026Stephen BeckerSingular Value DecompositionSign

    University of Colorado Boulder, USA

  47. General Value Functions for Remaining Useful Life and Failure-Mode Prediction

    Jul 24, 2026Hao Yan, Ali Sarabi, Qing Zou +1Useful Life PredictionEarly Failure Prediction

    School of Computing and Augmented Intelligence, Arizona State University

  48. Relative Value Learning

    Jul 23, 2026Marc Höftmann, Jan Robine, Stefan HarmelingValue FunctionsBellman Equation

    Department of Computer Science, Technical University of Dortmund, Germany · Lamarr Institute for Machine Learning and Artificial Intelligence

  49. LKValues: Aligning Large Language Models with Sri Lankan Societal Values

    Jul 22, 2026Nethmi Muthugala, Supryadi, Surangika Ranathunga +7Large Language Model AlignmentHuman Values

    TJUNLP Lab, School of Computer Science and Technology, Tianjin University, Tianjin, China · School of Mathematical and Computational Sciences, Massey University, Auckland, New Zealand · Department of Computer Science & Engineering, University of Moratuwa, Sri Lanka +2

  50. Which Values Do LLMs Confuse? A Schwartz-Based Recognition Study

    Jul 22, 2026Andrei Chetvergov, Stepan Ukolov, Timofei Sivoraksha +5Large Language Model EvaluationLarge Language Models Fail

    Ivannikov Institute for System Programming of the Russian Academy of Sciences, Moscow, Russia · Russian Presidential Academy of National Economy and Public Administration, Moscow, Russia

  51. Auto-Fill: Learning to Predict Missing Values Accurately with Specialist Language Models

    Jul 22, 2026Yurong Liu, Yeye He, Haoyu Dong +4Auto ResearchTable Reasoning Datasets

    New York University · Microsoft Research

  52. When Does Machine Learning Beat Value Sorting? A Three-Dataset Diagnostic of Exposure-Weighted Shipment Prioritization

    Jul 20, 2026Jize LiPrioritizationLogistics

    Boston University, United States

  53. Pancasila-Dilemmas: Evaluating Large Language Models on Indonesian Human Value Dilemmas Grounded in Pancasila

    Jul 20, 2026Supryadi, Irfan, Julianti +4Human ValuesLarge Language Model Alignment

    TJUNLP Lab, School of Computer Science and Technology, Tianjin University, China · Universitas Universal, Indonesia · Beijing Language and Culture University, Beijing, China +2

  54. A Geometric Perspective on Stabilizing Value Conflict Resolution

    Jul 20, 2026Saket Reddy, Andy LiuLLM Reasoning StrategiesLarge Language Model Alignment

    Supervised Program for Alignment Research (SPAR) · University of Illinois - Urbana-Champaign · Carnegie Mellon University

  55. A Method for Learning Value Systems in Generative AI

    Jul 18, 2026Andrés Holgado-Sánchez, Holger Billhardt, Sascha OssowskiArtificial Intelligence AlignmentGenerative Artificial Intelligence

    1CETINIA, University Rey Juan Carlos

  56. A Causal Markov Condition for Value

    Jul 18, 2026Olav Benjamin VassendConditional IndependenceCausal Graph

    University of Inland Norway

  57. The Value of Depth in Message Passing on Sparse Graphs: A Kesten-Stigum Dichotomy

    Jul 18, 2026Aseem Raj BaranwalMessage Passing Neural NetworksCircuit Depth

  58. Value Leakage: An LLM's Answers Are Silently Shaped by Its Own Values

    Jul 15, 2026Jan Betley, Johannes Treutlein, Jan Dubiński +5Data LeakageValue

    1Truthful AI · 2Warsaw University of Technology · 3NASK National Research Institute +2

  59. How Much of a 10-K Matters? Aggregation-Dependent Value of Full-Text versus Risk-Factor Sentiment

    Jul 15, 2026Sanggyu Sean ChoiFinancial Sentiment AnalysisSentiment

    Artificial Intelligence and its Application Institute · University of Edinburgh

  60. Belief-reality separation lives in routing over a shared value slot in language models

    Jul 11, 2026Oliver Steele, Jiangtao Wen, Yuxing HanValueReasoning Benchmark

    Tsinghua University · NYU Shanghai