Scale Gap

Ask about this topic

Momentum

7 papers in the last four weeks, against 1 the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28
View on map

Latest papers 45

All topics
CardsList

  1. Mind the RefGAP: Correcting Reference Attention in Diffusion-Based Visual Editing

    Sep 28, 2026Yanan Wang, Shengcai Liao, Guangyi Liu +1Diffusion-Based Image EditingScale Gap

    Mohamed bin Zayed University of Artificial Intelligence · Institute of Foundation Models · United Arab Emirates University

  2. Encoded but Not Decoded: Layer-Localized Evidence for a Three-Level Gap in LLM Syntax

    Sep 24, 2026Zhenyan Lu, He Wang, Xiaohui HuangSyntactic StructureScale Gap

    College of International Studies, National University of Defense Technology, Nanjing, China

  3. Beyond Class Marginals: Bounding Rehearsal Gaps without Freezing Class Co-occurrence

    Sep 22, 2026Congren Dai, Nat Roongjirarat, Fei YeLayer-Selective Rehearsal StrategyDeterministic Replay

    Imperial College London · King’s College London · University of Electronic Science and Technology of China

  4. EvoOntology: A Self-Evolving Ontology Layer for Data Agents

    Sep 14, 2026Meiduo Chong, Shaolei Zhang, Ju Fan +1Data Science AgentsSelf-Evolving Agents

    Renmin University of China

  5. Reducing the Output-Mode Gap in Speech Language Models via Joint-Output On-Policy Distillation

    Sep 14, 2026Daxin Tan, Dehua Tao, Chengxi Deng +2Speech Language ModelsAutoregressive Generation

    AI Lab, Leibniz Research Center, Huawei · The Chinese University of Hong Kong · City University of Hong Kong

  6. Same Encoder, Different Winner: A Paired-View Framework for Cell Painting Encoder Evaluation

    Sep 14, 2026Tim Treis, Nikita Moshkov, Johan Fredin Haslum +2Pixel-Level AnnotationMean Average Precision

    Institute of Computational Biology, Helmholtz Munich · School of Computation, Information and Technology, Technical University of Munich · Broad Institute of MIT and Harvard

  7. Reality Is the Final Verifier: On Two Key Gaps in Agentic Software Engineering

    Sep 14, 2026Alexander Krentsel, Shubham Agarwal, Mert Cemri +5SoftwareStakeholders

    UC Berkeley

  8. Beyond Parallel Blindness: Information Floors and Model Gaps in Block Drafting

    Aug 27, 2026Xinwei Qiang, Xiang Fang, Chang Chen +2DrafterDrafts

    University of California San Diego

  9. The Horizon Gap: Planning, Memory, Execution, Training, and Evaluation for Long-Horizon LLM Agents

    Aug 7, 2026Mingguang Chen, Licheng Wang, Bo QuLong-Horizon Task PlanningLarge Language Model Agents

    1DeepGrounding · 2AlphaAvatar

  10. The Vulnerability With No CVE: Managing Persistent Gaps Between Mandate and Authority in AI Coding Agents

    Aug 6, 2026Shayell Aharon Salomon Amir Shaked Matan NogaCommon Vulnerabilities And ExposureAuthorization

    Bluebear Security

  11. Floor, Ceiling, and the Fusion Gap: How Much of Crowd Reading Attention Can Machines Predict?

    Aug 3, 2026Kazuki Nakayashiki, Keisuke WatanabeReadabilityCeiling

    Glasp Inc.

  12. Measuring Distortion in the Empty Regions of Dimensionality Reduction Scatterplots with the Gap Index

    Jul 30, 2026Jaume Ros, Alessio Arleo, Fernando PaulovichDimensionality ReductionDistortion

    Eindhoven University of Technology

  13. Where Detectors Fail: Closing the Tail-Domain Gap with Expert-Guided Mutual Distillation

    Jul 29, 2026Xuan Feng, Guihong Liu, Tianlong Gu +5Fake News DetectionMultimodal Domain Generalization

    1Jinan University · 2Guilin University of Electronic Technology · 3Nanyang Technological University +1

  14. Closing the Lab-to-Store Gap: A Data-Efficient Post-Training and Experience-Driven Learning VLA Framework for Retail Humanoids

    Jul 22, 2026Roger Sala Sisó, Tiago Silvério, Jakob Sand +1Post-TrainingHumanoid

    HIVE Robots, Denmark · Department of Engineering Technology, Technical University of Denmark, Denmark

  15. Adaptive Filtering of the KV Cache: Diagnosing and Correcting Structural-Role Bias in LLM Inference

    Jul 14, 2026Soumil MandalKey-Value CacheLLM Inference Optimization

    ServiceNow

  16. The Seriality Gap in Video Diffusion Models

    Jul 14, 2026Jorge Diaz Chao, Konpat Preechakul, Yuxi Liu +1Video Diffusion ModelsScale Gap

    UC Berkeley

  17. C-GAP: Class-Aware and Online Prompting Improves Vision-Language Models on Imbalanced Classes

    Jul 10, 2026Francis Fernandez, Arash Jahangiri, Salimeh SekehOpen-Vocabulary Object DetectionOpen-Vocabulary

    San Diego State University

  18. MACRO: Training-free Multi-plane Attention for Closeup Render Optimization

    Jul 4, 2026Nitzan Hodos, Roy Amoyal, Lior Fritz +3Novel View SynthesisTraining-Free

    Amazon Prime Video · Technion, Israel Institute of Technology · Ben Gurion University +1

  19. BIFROST: Bridging Invariant Feature Representation for Observation-space Sim2Real Transfer

    Jul 1, 2026Yunfu Deng, Josiah P. HannaSim-To-Real Reinforcement LearningSim-To-Real Gap

    Department of Computer Sciences, University of Wisconsin–Madison, Madison, WI 53706 USA

  20. Creating Impactful Autonomous Driving Datasets: A Strategic Guide from Research Gap to Benchmark

    Jul 1, 2026Richard Schwarzkopf, Jonas Merkert, Frank Bieder +22Naturalistic Driving DataScale Gap

    Karlsruhe Institute of Technology (KIT) · FZI Research Center for Information Technology, Karlsruhe

  21. Can LLMs Hire Fairly? Racial Bias in Resume Screening

    Jun 27, 2026Zhenyu Gao, Wenxi Jiang, Yutong YanLarge Language Model BiasStrong Large Language Model

    Department of Finance, CUHK Business School, The Chinese University of Hong Kong

  22. Bridging the Age Gap: Towards Detecting Neural Audio Codec Synthesized Elderly Speech Deepfake

    Jun 19, 2026Orchid Chetia Phukan, Girish, Mohd Mujtaba Akhtar +1Neural Audio CodecsFace Forgery Detection

    BIIC Lab, NTHU, Taiwan

  23. MEDLAYXPLAIN: Benchmarking the Expert-Lay Gap in Medical Vision-Language Models

    Jun 19, 2026Han Jang, Junhyeok Lee, Songsoo Kim +4Medical Vision-Language ModelsMultimodal Clinical Data

    1Seoul National University · 2Seoul National University Hospital · 3Seoul National University College of Medicine +1

  24. Configurable Clinical Information Extraction with Agentic RAG: What Works, What Breaks, and Why

    Jun 17, 2026Osman Alperen Çinar-Koraş, Marie Bauer, Sameh Khattab +7Information ExtractionExtraction

    Institute for Artificial Intelligence in Medicine (IKIM), University Medicine Essen, Essen, Germany · Faculty of Computer Science, University of Duisburg-Essen, Essen, Germany · Department of Cardiology and Vascular Medicine, University Hospital Essen, Essen, Germany +3

  25. ActWorld: From Explorable to Interactive World Model via Action-Aware Memory

    Jun 16, 2026Zhexiao Xiong, Yizhi Song, Hao Kang +11Video World ModelsMany Worlds

    1Washington University in St. Louis · 2Intelligent Creation, ByteDance · *Work done during internship at ByteDance

  26. Exploring a Layer-Wise Design Space for KV Cache Eviction

    Jun 13, 2026Chao Fei, Kaihua Liang, Hanzhi Hu +4Key-Value Cache CompressionKey-Value Cache

    King Abdullah University of Science and Technology · Fudan University

  27. Closing the Reflection Gap: A Free Calibration Bonus for Agentic RL

    Jun 12, 2026Yinglun ZhuAgentic Reinforcement LearningReflections

    University of California, Riverside

  28. Synthetic Benchmarks Overstate Forward-Forward Scaling: Real-Data Limits of Layer-Local Training

    Jun 4, 2026Yucheng ChenForward PropagationSingular Learning Theory

    Amplimit Toronto, ON, Canada

  29. Encoded but Not Routed: Explaining the Table-Chart Gap in Scientific Claim Verification

    Jun 1, 2026Sunisth Kumar, Xanh Ho, Tim Schopf +3Evidence ConflictChart

    The University of Tokyo · NII LLMC · National Institute of Informatics +2

  30. MomentKV: Closing the Directional Gap in KV Cache Eviction for Long-Context Inference

    Jun 1, 2026Yu Li, Binxu Li, Tian LanKey-Value Cache EvictionKey-Value Cache

    George Washington University · Princeton University

  31. ConvMemory: A Lightweight Learned Memory Reranker, a Negative Attribution Result, and a Research-Preview Conflict Editor

    May 27, 2026Taiheng PanConversational MemoryCross-Encoder

    School of Computing and Information Systems University of Melbourne

  32. Adversarial Error Correction for Visual Autoregressive Generation

    May 24, 2026Ligong Bi, Tao Huang, Jianyuan Guo +1Autoregressive Image GenerationVisual Autoregressive Models

    1Shanghai Jiao Tong University · 2City University of Hong Kong · 3The University of Sydney

  33. Lifted Schrödinger Bridges for Gaussian Mixture Endpoints: Projection Gaps and Path-Space Obstructions

    May 24, 2026Siddhartha Ganguly, George Rapakoulias, Panagiotis TsiotrasSchrödinger BridgesGaussian Mixture Models

    S. Ganguly, G. Rapakoulias, and P. Tsiotras are with  Daniel Guggenheim School of Aerospace, Georgia Institute of Technology, ½ Atlanta, USA.

  34. Less Data, Faster Training: repeating smaller datasets speeds up learning via sampling biases

    May 19, 2026Jingwen Liu, Ezra Edelman, Surbhi Goel +1Inductive BiasBiases

    Columbia University · University of Pennsylvania · Kempner Institute, Harvard University

  35. The MixCount Dataset: Bridging the Data Gap for Open-Vocabulary Object Counting

    May 18, 2026Corentin Dumery, Niki Amini-Naieni, Shervin Naini +1CountingVision Datasets

    EPFL · University of Oxford · Northwestern University

  36. BGG: Bridging the Geometric Gap between Cross-View images by Vision Foundation Model Adaptation for Geo-Localization

    May 11, 2026Wei Wang, Dou Quan, Ning Huyan +4Cross-View Geo-LocalizationCross-View

    Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education of China, Xidian University · Department of Automation, Tsinghua University, Beijing 100084, China · School of Telecommunications, Xidian University, Xi’an 710071, China

  37. Path-Dependent Denoising: A Non-Conservative Field Perspective on Order Collapse in Diffusion Language Models

    May 10, 2026Jeonseong KimDiffusion Language ModelsIterative Denoising Methods

  38. Cut-In Gap Acceptance Toward Autonomous vs. Human-Driven Vehicles: Evidence from the Waymo Open Motion Dataset

    May 2, 2026Abdulaziz Alhuraish, Yuhang Wang, Hao ZhouAutomated VehiclesWaymo Open Motion Dataset

    Department of Civil and Environmental Engineering University of South Florida, Tampa, FL, USA

  39. From Cursed to Competitive: Closing the ZO-FO Gap via Input-to-State Stability

    Apr 28, 2026Amir Ali Farzin, Philipp Braun, Iman ShamesZeroth-OrderLyapunov Function

    School of Engineering · Australian National University · Canberra, ACT 2601 +3

  40. Toward a Science of Intent: Closure Gaps and Delegation Envelopes for Open-World AI Agents

    Apr 27, 2026Maximiliano Armesto, Christophe KolbOpen-WorldDelegation

    Taller Technologies

  41. The Override Gap: A Magnitude Account of Knowledge Conflict Failure in Hypernetwork-Based Instant LLM Adaptation

    Apr 26, 2026Shuaizhi Cheng, Xiang Shi, Zhiwei Zhang +1Large Language Model AdaptationHypernetwork

    Harbin Institute of Technology · KigLand Machine Learning Lab · Imperial College London

  42. Why Colors Make Clustering Harder:Global Integrality Gaps, the Price of Fairness, and Color-Coupled Algorithms in Chromatic Correlation Clustering

    Apr 17, 2026Ibne Farabi Shihab, Sanjeda Akter, Anuj SharmaMaximum Independent SetConvex Relaxation

    Department of Computer Science, Iowa State University · Department of Civil, Construction & Environmental Engineering, Iowa State University

  43. Closing Gaps in Emissions Monitoring with Climate TRACE

    Nov 24, 2025Brittany V. Lancellotti, Jordan M. Malof, Aaron Davitt +32Greenhouse GasClimate

    Nicholas Institute for Energy Environment & Sustainability, Duke University, Durham, NC, USA. · Department of Electrical Engineering and Computer Science, University of Missouri, Columbia, MO, USA. · WattTime, Oakland, CA, USA. +7

  44. D-GAP: Improving Out-of-Domain Robustness via Dataset-Agnostic and Gradient-Guided Augmentation in Frequency and Pixel Spaces

    Nov 14, 2025Ruoqi Wang, Haitao Wang, Shaojie Guo +1Data AugmentationAugmentation

    HKUST(GZ) · SYSU · ECNU +1

  45. Reinforcement Learning Improves Traversal of Parametric Knowledge in LLMs

    Nov 8, 2025Renfei Zhang, Manasa Kaniselvan, Rylan Schaeffer abd Niloofar MireshghallahLLM Reasoning StrategiesFactual Recall

    Carnegie Mellon University · MIT · Stanford University