Bottlenecks

Ask about this topic

Momentum

25 papers in the last four weeks, up 213% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28
View on map

Latest papers 200

All topics
CardsList

  1. Rethinking the Information Bottleneck: Structured Decomposition under Label-Induced Partitions

    Oct 1, 2026Jingyao Zhang, Yuxuan Li, Lu Han +2Information BottleneckRepresentation Learning

    School of Computer Science, The University of Sydney Sydney, NSW 2006, Australia

  2. When the Right Answer Is Missing: An Arithmetic-Dependent Rejection Bottleneck in Jev

    Sep 30, 2026Jike Zhong, Ming Li, Yuxiang LaiRejectionAnswer

    University of Southern California · University of Florida · Emory University

  3. About the Influence of Workflow Topology on Task Intensity Prediction through Graph Learning

    Sep 30, 2026Max Otto, Haci Ismail Aslan, Joel Witzke +2Task-LevelAgentic Workflow Design

    Dept. Electrical Engineering and Computer Science, Technical University of Berlin, Berlin, Germany

  4. Importance-Aware Feature Sparsification for Wireless Split Learning

    Sep 30, 2026Bumjun Kim, Yoon Huh, Wan ChoiSparsityBalanced Learning

    Department of Electrical and Computer Engineering, Seoul National University (SNU), and the Institute of New Media and Communications, SNU, Seoul 08826, Korea

  5. When Can Text Replace Vision? Structural Bottlenecks in Diagram Reasoning

    Sep 30, 2026Yunbei Zhang, Janet Wang, Jihun Hamm +1DiagramsVisual Reasoning

    Tulane University · Virginia Tech

  6. Interpretable but Fragile? Robustness of Concept Bottlenecks under Geometric-Semantic Perturbations

    Sep 29, 2026Hanwei Zhang, Tianma Hu, Gaojie Jin +2Dermoscopic Concept Bottleneck ModelsRobustness Verification

    Department of Computer Science Saarland University Saarbrücken, Germany · School of Computer Science and Engineering Tianjin University of Technology Tianjin, China · Department of Artificial Intelligence & Institute of Artificial Intelligence and Brain Sciences University of Macau Macau SAR, China +1

  7. Aperture: Training-Free Multiscale Concept Bottlenecks for Remote Sensing

    Sep 29, 2026Rishabh Mondal, Nipun Batra, Utkarsh MallRemote SensingEarth Observation

    Indian Institute of Technology Gandhinagar, India · Mohamed bin Zayed University of Artificial Intelligence, UAE

  8. LeapQuant: Efficient Linear Attention with Accurate Recurrent State Quantization

    Sep 29, 2026Yi Pan, Haocheng Xi, Kan Zhu +10Large Language Model QuantizationKimi Delta Attention

    UC Berkeley · University of Washington · MIT +2

  9. Why MLLMs Struggle to Count: Overcoming Individuation and Aggregation Bottlenecks with ConvStack

    Sep 29, 2026Liwei Che, Yihao Quan, Sen Fang +4Fine-Grained PerceptionMultimodal Large Language Models

    Department of Computer Science, Rutgers University · Department of Computer Science, University of Washington

  10. ThinQuant: Scalable Rotation Learning for Weight and Activation Quantization of LLMs

    Sep 28, 2026Mehdi Makni, Ryan Lucas, Rahul MazumderLarge Language Model QuantizationQantis

    Operations Research Center Massachusetts Institute of Technology

  11. MS-GLA: Multi-Scale Gated Linear Attention for Addressing Representational Bottlenecks via Multi-Temporal Resolution

    Sep 28, 2026Prasoon Dev, Anirudh Sankar, Vasudeva VarmaLinear AttentionMulti-Scale Attention

    Language Technologies Research Center International Institute of Information Technology Hyderabad Hyderabad, Telangana, India

  12. Representation Alignment as a Bottleneck in LLM-Based Retrosynthesis Planning

    Sep 28, 2026Hyunwoo Yoo, Cassie Huang, Haebin Shin +2MoleculenetSynthesis

    Drexel University · University of Michigan

  13. Mathematics for and by human cognition: A resource-rational search for bottlenecks in problem-solving

    Sep 28, 2026Sneha AenuguMathematicsCognitive Science

    Salk Institute of Biological Studies La Jolla, CA

  14. 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

  15. An Active-Bottleneck Mechanism for Weak-to-Strong Generalization

    Sep 27, 2026Mohammad Zeinalpour, Amir NajafiMulti-Stage TrainingBottlenecks

    Department of Computer Engineering, Sharif University of Technology

  16. Where Cyber Agents Struggle: Bottleneck Analysis of Multi-Stage LLM Agents

    Sep 23, 2026Saeedeh Lohrasbi, Mohammad Mamun, Ahmed Yehia +2Multi-Llm AgentsAgentic Evaluations

    Cybersecurity, DTRC, National Research Council, Ottawa, Canada · University of Windsor, Windsor, Ontario, Canada

  17. A principled approach for energy-efficient training via phase-aware GPU frequency tuning

    Sep 21, 2026Miguel Braga, Júlio Pinto, Rahma Nouaji +5Energy-EfficientGraphics Processing Unit Resources

    INESC TEC & U. Minho · McGill University

  18. The Communication Bottleneck: A Round-Trip Study of Tree-Structured Expression Serialization in Language Models

    Sep 18, 2026Xavier Suau, Alex Ferrando de las Morenas, Luca Zappella +1ExpressionBottlenecks

    Apple

  19. TierKV: Long-Context On-Device LLMs via Predictive Multi-Tier KV Caching

    Sep 18, 2026Zhihao Shu, Md Musfiqur Rahman Sanim, Jie Hu +4Kv-Cache ManagementDepthweave-Kv

    University of Georgia Athens, GA, USA · Peking University Beijing, China · Western Digital Research San Jose, CA, USA

  20. Not All AI Agents Are Equal: Characterizing Resource and Performance Dynamics

    Sep 17, 2026Wonmi Choi, Minuk Park, Zhixiong Niu +3Artificial Intelligence AgentsBottlenecks

    Department of Computer Science and Engineering, Korea University · Microsoft Research Asia

  21. Self Improvement via Fast Tree-search

    Sep 17, 2026Xinghong Fu, Aravinth Kulanthaivelu, Yutaro YamadaRecursive Self-ImprovementTree Search

    Massachusetts Institute of Technology · Sakana AI

  22. The Rank the Task Demands: A Causal Rank Law for Matrix Memories Trained on Group Composition

    Sep 14, 2026Samuel LarsonRepresentation SpaceBottlenecks

    Pebble ML

  23. Characterizing Job Power Elasticity for Power-Flexible AI Training

    Sep 12, 2026Philip Colangelo, Charles Dawson, Shayan Sengupta +2Optimal Power ShutoffArtificial Intelligence Infrastructure

    Emerald AI

  24. The Semantic Bottleneck: Leveraging Semantic Representations for Non-Invasive Speech Decoding

    Sep 9, 2026Gilad D. Landau, Dulhan Jayalath, Oiwi Parker JonesNeural RecordingsDiscrete Speech Representations

    PNPL University of Oxford

  25. Photonic reservoir computing with dimensionally compressed readout

    Sep 7, 2026Gerald Kobi, Mohab Abdalla, Miguel C. Soriano +1Reservoir ComputingReservoir

    Université de Lorraine, CentraleSupélec, LMOPS, F-57000 Metz, France · Instituto de Física Interdisciplinar y Sistemas Complejos (IFISC), CSIC–UIB, Campus UIB, E-07122 Palma de Mallorca, Spain

  26. GrowPage: On-Demand KV Budgeting for Efficient LLM Reasoning Serving

    Sep 3, 2026Qiankun Ma, Yanjiang Zhou, Zinan Xiong +5LLM Reasoning StrategiesEfficient Large Language Model

    Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences · Pengcheng Laboratory · University of Chinese Academy of Sciences

  27. Calibration is the Bottleneck: An Action-Class Diagnostic of Multi-Turn Tool-Calling

    Sep 1, 2026Kangjia Zhao, Jiajun Li, Haozhan Shen +8Multi-Turn InteractionsDiagnostic Framework

    Zhejiang University · Shanghai Jiao Tong University · National University of Singapore +3

  28. Are Concept Bottleneck Models Effective as Decision-Support Systems?

    Aug 26, 2026Alessandro Bogani, Nicola Debole, Emanuele Marconato +3Dermoscopic Concept Bottleneck ModelsConcept Bottleneck Models

    DISI, University of Trento, Italy · CIMeC, University of Trento, Italy

  29. Attention from Action, for Action: Emergent Visual Bottlenecks for Policy Learning

    Aug 13, 2026Zheyu Zhuang, Ruiyu Wang, Nick Heppert +4Visuomotor PolicyOpen-Vocabulary Action Recognition

    Department of Robotics, Perception and Learning, KTH Royal Institute of Technology, Sweden · Department of Computer Science, University of Freiburg, Germany · Department of Informatics, Universität Hamburg, Germany

  30. vToken: Token-Level Virtualization for Reclaimable KV Caches

    Aug 13, 2026Yuanhang Gao, Xiangrui Yang, Yuanfeng Chen +4Kv-Cache ManagementKey-Value Cache

    National University of Defense Technology · Changsha, China · Peking University +1

  31. Less Annotation, More Interpretation: Prior-Guided Concept Bottleneck Models for Interpretable Cancer Imaging Diagnosis

    Aug 13, 2026Baoqiang Ma, Kenneth GilhuijsDermoscopic Concept Bottleneck ModelsCancer Detection

    Image Sciences Institute, University Medical Center Utrecht, Utrecht, The Netherlands

  32. The Objective Is the Bottleneck: Latent World Models Encode What Their Planners Cannot Use

    Aug 13, 2026Joyjeet SinghLatent World ModelsLong-Horizon Task Planning

    Independent researcher

  33. Mitigating Bus Bunching with Reinforcement Learning Enhanced by Semantic Stop Embedding

    Aug 10, 2026Xin Dong, Vikash V. GayahTransportDeep Q-Networks

    Department of Civil and Environmental Engineering, The Pennsylvania State University University Park, PA, 16803

  34. Measuring and Reducing WebGPU Dispatch Overhead for LLM Inference

    Aug 9, 2026Jędrzej MaczanLLM Inference OptimizationBottlenecks

    1Independent Researcher

  35. A QUBO-Inspired Computational Framework for Airport Landside Bottleneck Diagnosis and Dynamic Dispatch Optimization

    Aug 9, 2026Wuming Lei, Xiaobin Li, Mingyan Sun +3Air Traffic ControlTraffic

    East China Jiaotong University, Nanchang, China

  36. Control-Diverse Reinforcement Fine-Tuning: Decoupling the Shared Control Bottleneck of RL Post-Training

    Aug 8, 2026Binwen Tan, Jingchao Wang, Dengzhe Hou +6Post-TrainingModel Fine-Tuning

    1Graduate School of Information Sciences, Tohoku University · School of Computer Science, Peking University · 2Unprecedented-scale Data Analytics Center, Tohoku University +3

  37. Distilling CT Foundation Models into Editable Concept Bottlenecks for Lung Nodule Malignancy Prediction

    Aug 8, 2026Fakrul Islam Tushar, Stephen Adamo, Geoffrey D. RubinLung-Nodule Artificial IntelligenceConcept Bottleneck Models

    Department of Radiology and Imaging Sciences, University of Arizona, Tucson, AZ, USA

  38. TEPA: Revoking Stale Memories for Conflict-Robust Language Agents

    Aug 7, 2026Yan Zhou, Yue Ouyang, Kaiyang Zheng +1Long-Term Agent MemoryGradient Staleness

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

  39. Tytan: Interactive Neurosymbolic Construction of Analytic Semantic Schemas from Relational Data

    Aug 6, 2026Donna Hooshmand, Shubham Shahi, Cameron Barrie +4SchemaSemantic Relationships

    Northwestern University

  40. Hybrid-Adaptive Thread Tuning to Mitigate Simulation Execution Bottlenecks in High-Performance Reinforcement Learning Inference

    Aug 6, 2026Jiming Su, Hantao Hua, Lujia Yin +2Offline Reinforcement LearningBottlenecks

    College of Systems Engineering, National University of Defense Technology · College of Computer Science and Technology, National University of Defense Technology

  41. AnchorKV: Anchor-Residual KV Cache Compression

    Aug 3, 2026Malik Khalaf, Yara Shamshoum, Nitzan Hodos +2Key-Value Cache CompressionKey-Value Cache

    Department of Computer Science, Technion - Israel Institute of Technology

  42. When Replanning Becomes the Bottleneck: Budgeted Replanning for Embodied Agents

    Aug 2, 2026Shuaijun Liu, Feiyang You, Xingwei Chen +1Iterative Re-PlanningEmbodied Agents

    IoT, Information Hub, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, Guangdong, China.

  43. Practical Online KV Cache Compaction for LLM Agents: An Empirical Study

    Aug 2, 2026Yujian Liu, Jiabao Ji, Li An +4Key-Value Cache CompressionCompaction

    UC Santa Barbara · LinkedIn

  44. Generic Vision and Cross-Attention for Reaction Yield Prediction

    Aug 1, 2026Qiwei Han, Chi ZhouMolecular Property PredictionReaction

    Department of Chemistry, Duke University, Durham, NC 27708, USA · Department of Computer Science, Georgia Institute of Technology, Atlanta, GA 30332, USA

  45. AiFlow: Token-Native Reactive Orchestration with Bounded Backpressure for Streaming LLM Applications

    Aug 1, 2026Qunhui ZhangLarge Language Model WorkflowsTaxonomy-Driven Dataflow Model

    School of Software, Shanghai Jiao Tong University, Shanghai 200240, China

  46. MoRAE: Flow-Friendly Self-Supervised Latents for Text-to-Motion Generation

    Jul 31, 2026Yifei Zhu, Mingyi Shi, Yangyang Cai +3Text-To-Motion GenerationLatent Flow

    1Tohoku University, Sendai, Japan · 2The University of Hong Kong, Hong Kong

  47. Information Bottleneck Learning for Faithful Time Series Forecasting Explanations

    Jul 30, 2026Xu Zheng, Wei Cheng, Zhuomin Chen +3Time Series ForecastingData-Driven Forecasting

    Florida International University, Miami, FL, USA · NEC Laboratories America, Princeton, NJ, USA · University of Houston, Houston, TX, USA +1

  48. Schreier-Coset Graph Rewiring

    Jul 29, 2026Aryan Mishra, Randy Martinez, Lizhen LinInhomogeneous Random GraphsGraph Neural Networks

  49. Veritas++: Value-aware On-Policy Distillation for Perception-Enhanced AIGI Detection

    Jul 29, 2026Hao Tan, Jun Lan, Zichang Tan +7Ai-Generated Image DetectionVisual Evidence

    School of Advanced Interdisciplinary Sciences, University of Chinese Academy of Sciences (UCAS), Beijing 101408, China, and also with the State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation Chinese Academy of Sciences (CASIA), Beijing 100190, China · State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing 100190, China · Ant Group +2

  50. VETO: Towards Protecting Images From Frontier AI Editing

    Jul 29, 2026Jonas Grebe, Hossein Shakibania, Tobias Braun +2Ai-Generated Image DetectionLLM Defense Mechanisms

    TU Darmstadt & hessian.AI, Germany · Zuse School ELIZA

  51. Loss Invariance Determines What Concept Layers Encode: Volume Grounding in Echocardiography

    Jul 28, 2026Hyunkyung Han, Min Jung KimLeft-Ventricular Ejection FractionCardiac Motion

    Department of Integrative Medicine, Yonsei University College of Medicine, Seoul 06273, Republic of Korea

  52. The Visual Bottleneck: Sparse-Frame Adaptation of MLLMs for Joint Spatial-Temporal Video Grounding

    Jul 27, 2026Jiameng Zhang, Srikanth MadikeriVideo Temporal GroundingMultimodal Large Language Models

    University of Zurich

  53. 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

  54. How Well Can AI Generate Backlogs from App Mockups?

    Jul 24, 2026Andrea Lezcano Airaldi, Lourdes Romera, Walid MaalejEvaluation AgentBottlenecks

    Department of Informatics · Hasso Plattner Institute

  55. HiKV: Hierarchical Importance-Aware KV Cache with Hardware Acceleration for LLM Decoding

    Jul 24, 2026Chao Fang, Jun Yin, Man Shi +1Key-Value CacheLarge Language Model Decoding

    ESAT-MICAS, KU Leuven, Leuven, Belgium · UC Berkley, CA, USA

  56. Neuromorphic Diffusion Language Models: Addressing Compute and Memory Bottlenecks via Sparsity and Block Denoising

    Jul 24, 2026Dengyu Wu, Clement Ruah, Jiechen Chen +2Diffusion Language ModelsLLM Inference Optimization

    Department of Engineering, King’s College London, London, UK · Institute for Intelligent Networked Systems (INSI), Northeastern University London, London, UK

  57. Beyond Episodic Evaluation: Memory Architectural Bottlenecks in Sequential Embodied Question Answering

    Jul 23, 2026Zikui Cai, Kaushal Janga, Tan Dat Dao +15Visual MemoryEmbodied

    University of Maryland, College Park. · The University of Texas at Austin. · University of Illinois Urbana-Champaign.

  58. Benchmarking Resource-Efficient LLMs for Research Topic Ontology Generation in the Biomedical Field

    Jul 20, 2026Tanay Aggarwal, Angelo Salatino, Francesco Osborne +1Medical OntologyOntology

    Knowledge Media Institute, The Open University, Milton Keynes, UK · Department of Business and Law, University of Milano-Bicocca, Milan, IT

  59. WuYu-EnvLE-Bench: A Benchmark for Evaluating Large Language Models in Environmental Law Enforcement

    Jul 20, 2026Ziliang Yang, Yi Zhang, Kaijun Lin +3EnforcementPolicing

    School of Environment, Tsinghua University · College of Economics and Management, Beijing University of Technology · State Key Laboratory of Iron and Steel Industry Environmental Protection, School of Environment, Tsinghua University +1

  60. Grounded verification of chemical and materials reasoning: detection is the bottleneck

    Jul 19, 2026Can Polat, Mustafa Kurban, Erchin Serpedin +1ChemistryConfabulation

    Department of Electrical and Computer Engineering, Texas A&M University, College Station, TX, USA · Department of Electrical and Computer Engineering, Texas A&M University at Qatar, Doha, Qatar · Department of Prosthetics and Orthotics, Ankara University, Ankara, Turkey +1