Position

Ask about this topic

Momentum

6 papers in the last four weeks, level with the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28
View on map

Latest papers 84

All topics
CardsList

  1. How Local Mixing Encodes Relative Position in Global NoPE Attention

    Sep 29, 2026Cutter Dawes, Nick Alonso, Tom Figliolia +1Positional EncodingTransformer Architectures

    Zyphra Research

  2. Positions Are Not Facts: The Mismatch Between KV Caches and Memory

    Sep 27, 2026Changhai Zhou, Yuhua Zhou, Shiyang Zhang +5Key-Value CacheLarge Language Model Memory

    Fudan University · Baidu · Zhejiang University +2

  3. Position: It is Time to Virtualize Foundation Models with a Self-evolving Operating System Layer

    Sep 16, 2026Suparna Bhattacharya, Tarun Kumar, Cong Xu +7Foundation ModelPosition

    Hewlett Packard Enterprise · Department of Computer Science, University of Chicago & Argonne National Laboratory

  4. Reaching Every Position Without Searching: Rotating Sparse Wiring on the Hypercube as a Substitute for Attention

    Sep 16, 2026Yoshiaki TakashitaDynamic Sparse AttentionAttention Layers

    School of Law, Waseda University

  5. Motion planning in high dimensional spaces hybridizing RRT and HAR via position-direction decoupling

    Sep 15, 2026Frederic Cazals, Nelson FeyeuxMotion PlanningRobot Systems

    Centre Inria at Université Côte d’Azur, France

  6. Comparing Trajectories from Positions Alone: Curvature-Based Time Alignment and Drift Error Metric

    Sep 14, 2026Effie Daum, Daniele De Martini, Claire Dune +1Simultaneous Localization And MappingPosition

    Northern Robotics Laboratory, Universit´e Laval, Qu´ebec City, Qu´ebec, Canada · Mobile Robotics Group, Oxford Robotics Institute, University of Oxford, Oxford, United Kingdom

  7. Position: Unlabeled IS NOT Equal to No Human Supervision in Visual Learning

    Sep 2, 2026Dong LaoUnlabeled DataUnsupervised

    Division of Computer Science and Engineering, Louisiana State University, Louisiana, USA.

  8. Position: Privacy Is a Claim, Not a Property of Synthetic Data

    Sep 1, 2026Jiachen Zhao, Antonia Januszewicz, Taeho JungPrivacySynthetic Data

    Department of Computer Science Engineering, University of Notre Dame, Notre Dame, United States.

  9. MeRoPE: Metric Rotary Position Embedding for Camera-Controlled Video Generation

    Sep 1, 2026Zhijian Qiao, Xinjiang Wang, Jiajie Chen +5Camera ControlCamera Trajectories

    The Hong Kong University of Science and Technology · Zhuoyu Technology

  10. Beyond Object Selection:Markerless Gaze-based Robot Placement at Arbitrary Positions

    Aug 31, 2026Yuzhi Lai, William Marx, Shenghai Yuan +3Category-Level Object Pose EstimationRobot Systems

    University of Tuebingen, Geschwister-Scholl-Platz, 72074 Germany · University of Tuebingen · Nanyang Technological University, 50 Nanyang Avenue, Singapore 639798 +1

  11. Higher-Dimensional Rotary Position Embedding

    Aug 30, 2026Yixing Li, Ruobing Xie, Yudong Zhang +3Rotary Position EmbeddingTransformer Architectures

    The Chinese University of Hong Kong · Tencent Hunyuan · Tsinghua University +1

  12. Where You Measure Decides What You Measure: Position Selection in Ablation-Based SAE Evaluation

    Aug 13, 2026Valentin NoëlImproving Sparse AutoencodersLanguage Model Computes

    Devoteam

  13. Are LLMs Positionally Consistent Ordinal Classifiers? A Systematic Evaluation

    Aug 9, 2026Yu Wang, Zhe Zhou, Menglin Liu +1Position BiasOrder Matters

    Cornell University · University of Washington · The Chinese University of Hong Kong, Shenzhen +1

  14. Position Encoding in Transformers: From Absolute and Relative Methods to Rotary Position Embeddings and Long-Context Scaling

    Aug 9, 2026Jiguo LiRotary Position EmbeddingPositional Encoding

  15. Position: It's Time to Optimize LLMs for Self-Consistency

    Jul 31, 2026Itamar Pres, Belinda Z. Li, Laura Ruis +6Large Language Models FailSelf-Consistency

    MIT CSAIL · Goodfire AI

  16. Static In, Dynamic Out: Counterfactual Action Augmentation for Moving Object Manipulation

    Jul 30, 2026Woo Chul Shin, Zhenyang Chen, Alfred Cueva +5Inverse DynamicsObjects

    Georgia Institute of Technology

  17. Measuring Alignment With Reader Highlights Net of Position and Length

    Jul 30, 2026Kazuki Nakayashiki, Keisuke WatanabeMultiple Centrality MeasuresRanking

    Glasp Inc.

  18. Position: Evaluation Scores Are Perishable Knowledge Claims

    Jul 28, 2026Sankalp Gilda, Shlok GildaConfidence CalibrationPosition

    DeepThought Solutions · Meta · University of Florida

  19. Engine-Equal, Human-Unequal: A Reproducible Outcome Skew in Engine-Assessed Equal Chess Positions

    Jul 28, 2026Jesung ParkChessSkewness

    Gamakon

  20. Ranked by Position: Order Sensitivity as an Exploitable Attack Surface in LLM Listwise Recommenders

    Jul 26, 2026Ge Zhang, Jingru Cheng, Huiyuan ChenLarge Language Model RerankingOrder Matters

    Stanford University · Independent Researcher

  21. Through the Bottleneck: How Multi-head Latent Attention Separates Content from Position in Language Models

    Jul 25, 2026Dhruvil S, Fenil Sojitra, Ravirajsinh ChauhanMulti-Head AttentionDeepseek

    1Indian Institute of Technology Madras · 2P P Savani University

  22. Position Bias is Hidden Behind Ceiling Effects: A Permutation Diagnostic for LLM Benchmarks

    Jul 23, 2026Hiroki TambaPosition BiasLarge Language Model Evaluation

    Independent researcher.

  23. Occlusion-Aware Panoptic Segmentation with Joint Position Embedding and Occlusion-Level Attention

    Jul 20, 2026Wenbo Wei, Jun Wang, Shan Raza +1Panoptic SegmentationDiverse Occlusion-And-Revelation Scenarios

    Department of Computer Science, University of Warwick, Coventry, UK

  24. Position: Explanation Stability Is a Property of the Model Method Pair, Not the Model

    Jul 18, 2026Kabilan Elangovan, Daniel TingExplainabilityGradient-Weighted Class Activation Mapping

    Singapore Health Services and Singapore Eye Research Institute, Singapore.

  25. From Plausible to Actionable: A Position on LLM Self-Explanations

    Jul 17, 2026Elize Herrewijnen, Benedetta Muscato, Gizem Gezici +1Explainable Artificial IntelligenceExplainable AI Methods

    University of Utrecht, Utrecht, Netherlands · National Police Lab AI, Netherlands Police, Driebergen, Netherlands · Scuola Normale Superiore, Pisa, Italy +1

  26. A Better Start for Language Models: Domain-Conditional Position Offsets

    Jul 17, 2026Ye QiaoPretrainingAutoregressive Language Models

    University of California, Irvine

  27. Position: Vision-Language-Action Models Cannot Be Verified to Perform Physical Reasoning

    Jun 28, 2026Taozhao Chen, Ian Manchester, Huaming ChenSemantic RepresentationsPosition

    School of Electrical and Computer Engineering The University of Sydney Sydney, NSW, Australia · School of Aerospace, Mechanical and Mechatronic Engineering The University of Sydney Sydney, NSW, Australia

  28. Mitigating Position Bias in Transformers via Layer-Specific Positional Embedding Scaling

    Jun 26, 2026Changze Lv, Zhenghua Wang, Yiran Ding +9Rotary Position EmbeddingTransformer Architectures

    Fudan University · Shanghai Key Laboratory of Intelligent Information Processing · Westlake University

  29. Position: RL Researchers Need to Distinguish Between Solving Simulators and Using Simulators as a Proxy

    Jun 26, 2026Matthew Vandergrift, Esraa Elelimy, Martha WhiteSimulation-Based Reinforcement LearningUser Simulation

    Department of Computing Science, University of Alberta · Alberta Machine Intelligence Institute (Amii) · Canada CIFAR AI Chair

  30. Position Spaces and Graphs

    Jun 24, 2026Rita-Nathalia Assaf, Tom Davot, Frédéric Lardeux +1PositionStructural Constraints

    1Univ Angers, LERIA, SFR MATHSTIC, F-49000 Angers, France

  31. What Does ODRL Mean? A Cross-Level Ontological Grounding of Permissions, Prohibitions, and Duties in UFO-L

    Jun 23, 2026Daham M. Mustafa, Christoph Lange, Giancarlo Guizzardi +3Social NormsPolicy Evaluation

    Fraunhofer FIT, Sankt Augustin, Germany · RWTH Aachen University, Aachen, Germany · University of Twente, The Netherlands +1

  32. Whistleblowing and the machine -- towards a considered position

    Jun 19, 2026Marija Slavkovik, Liuwen Yu, Leon van der Torre +1DisclosuresPosition

    University of Bergen Bergen, Norway · University of Luxembourg Luxembourg, Luxembourg

  33. Position: Coding Benchmarks Are Misaligned with Agentic Software Engineering

    Jun 16, 2026Maria I. Gorinova, Macey Baker, Amy Heineike +3Coding AgentsSoftware Engineering

    Tessl London, UK

  34. Position: Align AI to Our Aspirations, Not Our Flaws

    Jun 11, 2026Nikita Kazeev, Bui Nhat Huyen PhanPluralistic AlignmentInternal Pluralism

    1National University of Singapore · 2Shopee Singapore.

  35. Position: The Systemic Lack of Agency in Visual Reasoning

    Jun 11, 2026Yizhao Huang, Haoyang Chen, Shiqin Wang +6Visual ReasoningMultiple Vision Tasks

    National Engineering Research Center for Multimedia Software, Institute of Artificial Intelligence, School of Computer Science, Wuhan University · Hubei Key Laboratory of Multimedia and Network Communication Engineering · Zhongguancun Academy, Beijing, China. +2

  36. nD-RoPE: A Generalized RoPE for n-Dimensional Position Embedding

    Jun 10, 2026Boyang Li, Yulin Wu, Sizhe Xu +5Rotary Position EmbeddingDynamic Rope Manipulation

    New York University, New York, NY, USA · Peking University, Beijing, China · Imperial College London, London, UK +1

  37. Position: AI Must Become Planet-Centered, Not Just Human-Centered

    Jun 9, 2026Maria Perez-OrtizArtificial Intelligence SystemsEcosystems

    Centre for AI, Department of Computer Science, University College London, London, UK.

  38. Position: Preventing AI-Generated CSAM Necessitates New Approaches to AI Safety

    Jun 9, 2026Neil Kale, Rebecca Portnoff, Pratiksha Thaker +5Artificial Intelligence SafetyChild Sexual Abuse Material

    1Carnegie Mellon University · 2Thorn

  39. Where does Absolute Position come from in decoder-only Transformers?

    Jun 4, 2026Valeria Ruscio, Umberto Nanni, Fabrizio SilvestriTransformer EncoderRotary Position Embedding

    Intuition Machines · Sapienza University of Rome

  40. PJ-RoPE: A Fourier-Jet-Affine Position Space for Relative Attention

    Jun 3, 2026Yaobo ZhangRotary Position EmbeddingDynamic Rope Manipulation

    School of Physics, Ningxia University Yinchuan, 750021, China

  41. Wheel-Mounted/GNSS Fusion with AI-Aided Position Updates

    Jun 2, 2026Gal Versano, Itzik KleinInertial Navigation SystemsInertial Measurement Units

    Autonomous Navigation and Sensor Fusion Lab, Hatter Department of Marine Technologies, Charney School of Marine Sciences, University of Haifa, Israel

  42. Position: Deployed Reinforcement Learning should be Continual

    Jun 1, 2026Parnian Behdin, Kevin Roice, Golnaz MesbahiOffline Reinforcement LearningContinual Learning

    Alberta Machine Intelligence Institute (Amii), Edmonton, Canada.

  43. Eyettention II: A Dual-Sequence Architecture for Modeling Fixation Location, Within-Word Landing Position, and Fixation Duration in Reading

    Jun 1, 2026Shuwen Deng, Cui Ding, David R. Reich +2Eye TrackingDeep Learning

    Department of Computer Science, University of Potsdam, Germany. · Department of Computational Linguistics, University of Zurich, Switzerland. · Department of Informatics, University of Zurich, Switzerland.

  44. Position: Prioritize Identifying Structure, Not Complex Models, for Scientific Discovery

    May 30, 2026Tyler H. McCormickScientific DiscoveryPosition

    Departments of Statistics and Sociology, University of Washington, Seattle, WA, USA.

  45. Position: Anthropomorphic Misalignment Research Needs Stronger Evidence

    May 29, 2026Vansh Gupta, Peter Nutter, Samuel Stante +5AnthropomorphismEvidence Conflict

    1ETH Zurich

  46. Position: Every Ground Truth is a Human Construction, not an Objective Truth

    May 28, 2026Charlotte Högberg, Ericka Johnson, Kiri L. WagstaffGround TruthHuman-Annotated Benchmark

    Lund University, Lund, Sweden · Linköping University, Linköping, Sweden · Oregon State University, Corvallis, OR, USA.

  47. Position: AI Safety Requires Effective Controllability

    May 26, 2026Yige Li, Yunhao Feng, Jun SunArtificial Intelligence SafetyControllability

    Singapore Management University · Ant Group

  48. Loosely Coupled Factor Graph Optimization for Pseudolite-Augmented Navigation

    May 24, 2026Chih-Chun Chen, Lipeng Tan, Shiyu Bai +1Global Navigation Satellite SystemFactor Graphs

  49. Position: The Turing-Completeness of Autoregressive Transformers Relies Heavily on Context Management

    May 19, 2026Guanyu Cui, Zhewei Wei, Kun HeAutoregressive TransformersTransformer Architectures

    Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China · DEKE Lab, Renmin University of China, Beijing, China

  50. Position: Uncertainty Quantification in LLMs is Just Unsupervised Clustering

    May 19, 2026Tiejin Chen, Longchao Da, Xiaoou Liu +1Large Language Model UncertaintyUncertainty Quantification

    School of Computing and Augmented Intelligence, Arizona State University

  51. Position: Weight Space Should Be a First-Class Generative AI Modality

    May 18, 2026Zhangyang Wang, Peihao Wang, Kai WangModel CheckpointsModel Weights

    University of Texas at Austin · Tencent

  52. Elastic-dLLM: Position Preserving Context Compression and Augmentation of Diffusion LLMs

    May 18, 2026Junyi Wu, Tianchen Zhao, Shaoqiu Zhang +3Diffusion Language ModelsLarge Language Model Decoding

    Tsinghua University · Shanghai Jiao Tong University · Infinigence AI

  53. Position: Age Estimation Models Do Not Process Biometric Data

    May 17, 2026Nikita MarshalkinBiometricsAge

    Sumsub GmbH, Berlin, Germany.

  54. Beyond Geometry: Efficient Topologically-Grounded Navigation in Complex 3D Environments

    May 17, 2026Yifan Du, Chengwei Zhang, Siyu Liao +13D Visual GroundingRobot Navigation

    School of Integrated Circuits Sun Yat-sen University Shenzhen, China

  55. Position: Graph Condensation Needs a Reset -- Move Beyond Full-dataset Training and Model-Dependence

    May 17, 2026Mridul Gupta, Samyak Jain, Vansh Ramani +2Graph Neural NetworksPosition

    Yardi School of Artificial Intelligence, IIT Delhi, India · Department of Computer Science and Engineering, IIT Delhi, India · Department of Chemical Engineering, IIT Delhi, India

  56. Position: State-of-the-Art Claims Require State-of-the-Art Evidence

    May 17, 2026YongKyung OhArtificial Intelligence BenchmarksEvidence Conflict

    Medical & Imaging Informatics (MII), University of California, Los Angeles (UCLA)

  57. Position: Zeroth-Order Optimization in Deep Learning Is Underexplored, Not Underpowered

    May 15, 2026Sijia Liu, Yicheng Lang, Soumyadeep Pal +6Zeroth-Order OptimizationZeroth-Order

    1OPTML Lab, Michigan State University, USA · 2Lawrence Livermore National Laboratory, USA

  58. Position: Artificial Intelligence Needs Meta Intelligence -- the Case for Metacognitive AI

    May 15, 2026Sergei Chuprov, Richard D. Lange, Leon Reznik +3MetacognitionFederated Learning

    University of Texas Rio Grande Valley, Edinburg, TX, USA · Rochester Institute of Technology, Rochester, NY, USA · Syracuse University, Syracuse, NY, USA

  59. RoPE Distinguishes Neither Positions Nor Tokens in Long Contexts, Provably

    May 15, 2026Yufeng Du, Phillip Harris, Minyang Tian +5Rotary Position EmbeddingEfficient Long-Context Inference

    University of Illinois at Urbana-Champaign · USA · University of Bonn +3

  60. Position: Behavioural Assurance Cannot Verify the Safety Claims Governance Now Demands

    May 14, 2026Pratinav Seth, Vinay Kumar SankarapuSafety ClaimsArtificial Intelligence Governance

    Lexsi Labs