Collapse

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 178

All topics
CardsList

  1. No Model Required: Text Entropy Rate Filtering Mitigates Iterative Fine-Tuning Collapse

    Oct 1, 2026Lewis MitchellCollapseToken-Level Entropy

    Adelaide Data Science Centre School of Mathematical Sciences Adelaide University Adelaide SA 5005, Australia

  2. Feature Selective Model Collapse in Diffusion Models: Total Replacement versus Fixed-Budget Training

    Oct 1, 2026Hanna Malet, Gabriel TuriniciDiffusion ModelsCollapse

    CEREMADE CNRS Université Paris Dauphine - PSL Paris 75116 FRANCE · Cornell University Ithaca, NY, USA

  3. Collapse, Not Invariance: Diagnosing Auxiliary Objectives in Speech Anti-Spoofing

    Sep 30, 2026Ksenia Lysikova, Kirill Borodin, Maxim Maslov +1SpoofingCross-Entropy Losses

    Lab260, Yerevan, Armenia · BitmanagerAI, Dubai, UAE · MTUCI, Moscow, Russia

  4. Divide and Collapse: MAPF-Collapse via Exact Decomposition into Independent Sub-Instances

    Sep 30, 2026Oren SalzmanMulti-Agent Path FindingClassical Planning

    Technion – Israel Institute of Technology

  5. Understanding as No-Arbitrage: Bounded Dutch Books as a Definition and Training Objective for Language Models

    Sep 30, 2026Daniel DragonevskiyNext-Token PredictionAdversarial Robustness

  6. Rethinking Generative Image Compression at Extremely Low Bitrates

    Sep 30, 2026Tianyu Zhang, Zhaoyang Jia, Houqiang Li +1Generative Image CompressionUltra-Low Bitrates

    University of Science and Technology of China

  7. ReSAIL: Mitigating Collapse in Iterative Agent Self-Distillation

    Sep 30, 2026Shengjie Jin, Hengbo Xu, Zelong Sun +2Self-Improving AgentsRecursive Self-Improvement

    Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China

  8. Jacobian Rank Collapse in Decision-Focused Learning

    Sep 30, 2026Aojie Yuan, Haiyue Zhang, Zijian SuJacobianStochastic Gradient Descent

    University of Southern California · University of Michigan

  9. Beyond Mode Collapse: Generating Diverse Synthetic Expert Conversations via Generative Flow Networks

    Sep 29, 2026Sumit Asthana, Michael Ion, Kevyn Collins ThompsonGenerative Flow NetworksSynthetic Data

    University of Michigan Ann Arbor, MI, USA

  10. Learning to Harvest Without Collapse in a Regenerative Commons: A Lagrangian Framework

    Sep 29, 2026Jose Tupayachi, Xueping Li, Soham DasLagrangian MethodsFeasibility

    Oak Ridge National Laboratory Department of Industrial and Systems Engineering, University of Tennessee, Knoxville · Department of Industrial and Systems Engineering, University of Tennessee, Knoxville

  11. λλ-JEPA Spectral Anti-Collapse Regularization for Self-Supervised Learning

    Sep 28, 2026Berker Demirel, Clémentine Dominé, Valentino Maiorca +3Self-Supervised LearningRegularization

    Institute of Science and Technology Austria (ISTA) Am Campus 1, 3400 Klosterneuburg, Austria

  12. Measuring Collapse and Correction in Homogeneous-Panel LLM Debate

    Sep 28, 2026Xin Li, Mengbing Liu, Chau YuenDebateLarge Language Model Decisions

    Nanyang Technological University

  13. EOPSA: Efficient On-Policy Self-Distilled Safety Alignment

    Sep 28, 2026Qirui Liu, Yichen Sun, Yan Wang +5Safety AlignmentCollapse

    The State Key Laboratory of Blockchain and Data Security, Zhejiang University · Ant Group

  14. JIVE: Jacobian-Informed Volume Expansion for Diverse Generative Sampling

    Sep 27, 2026Guangxun Zhang, Brian Cai, Boxuan Zhang +2DiversityJacobian

    New York University · Stony Brook University · Rutgers University

  15. Does Adversarial Training Improve Generalization in Multi-View VLAs? Revealing and Mitigating View Collapse

    Sep 27, 2026Futa Waseda, Shuhei Kurita, Isao EchizenDiffusion-Based Vision-Language-ActionsVision-Language Model Adaptation

    National Institute of Informatics Tokyo, Japan

  16. LastOPD: Taming Collapse in Latent On-Policy Distillation

    Sep 23, 2026Jie Yang, Zhengyu Fang, Zelin Xu +7Uni-OpdTeacher

    University of Illinois at Chicago · Visa Research · Case Western Reserve University +2

  17. Uncertainty-Gated Exploration Noise Suppresses Task Collapse in Online RL Fine-Tuning of a Flow-Matching Vision-Language-Action Policy

    Sep 23, 2026Mehmet Turan Yardımcı, Yunus Emre ÇoğurcuFlow-Matching Vision-Language-ActionReinforcement Fine-Tuning

    Karlsruhe Institute of Technology · Çukurova University

  18. Clarification Is Not Correction: LLMs Fail to Let Go

    Sep 21, 2026Jianzhe Lin, Xiaolin Li, Fei Wang +3Large Language Models FailClarification

    MetaAI

  19. Collapse, Not Complexity: Failure-Conditioned Decomposition Repair for End-to-End Document Parsing

    Sep 20, 2026Xingyu Lin, Dehui DuDocument ParsingCollapse

    Software Engineering Institute, East China Normal University Shanghai, China

  20. Preventing Model Collapse: A Fisher-Rao Perspective on the Dynamics of Training with Synthetic Data

    Sep 16, 2026Matteo Marchi, João Pedro Silvestre, Bahman Gharesifard +1Large Language Model TrainingCollapse

    Electrical and Computer Engineering Department, University of California at Los Angeles, Los Angeles, CA 90095 USA · Department of Mathematics and Statistics at Queens University, Kingston, ON, Canada

  21. Performance, Efficiency and Collapse -- Advantages and Challenges in Offline Post-training of Code LLMs

    Sep 14, 2026Abhinav Anand, Sanjana Reddy Pachika, Shweta Verma +1Reinforcement Learning Post-TrainingLarge Language Model Training

    TU Darmstadt · Hessian Center for Artificial Intelligence, Darmstadt, Germany · National Research Center for Applied Cybersecurity ATHENE

  22. Break Step: Recursive Training Resonates with Replayed Sampling Noise

    Sep 10, 2026Yangze Liu, Zhongyi HanCollapseLarge Language Model Training

    Shandong University

  23. A Dominant Supplier Slows Recursive Drift More Than It Steers It

    Sep 10, 2026Yangze Liu, Zhongyi HanCollapseEcosystems

    Shandong University

  24. Think Wider: Mitigating Latent Rank Collapse in Implicit Chain-of-Thought Reasoning

    Sep 7, 2026Yuwen Hao, Menglin YangEfficient Latent ReasoningChain-of-Thought Reasoning

    The Hong Kong University of Science and Technology (Guangzhou)

  25. Stable-MM-R1: Anchoring Multimodal Reasoning Dynamics via Entropy-Guided Stratification

    Sep 7, 2026Yimeng Ye, Shuang Chen, Wenxuan Huang +8Large Language Model Reinforcement LearningMultimodal Reasoning

    Columbia University · CUHK · THU +1

  26. SCoCaT: Success Conditioned Constrained Reinforcement Learning for Spacecraft Docking

    Sep 5, 2026Aman Arora, Ricard Marsal I Castan, Matteo El-Hariry +1Safety ConstraintsSpacecraft

    SnT - Interdisciplinary Centre for Security, Reliability and Trust University of Luxembourg, Luxembourg

  27. The Dynamics of Continuous Mixture Collapse in Language Models

    Sep 2, 2026Ali BackourLarge Language Models FailLatent States

    Massachusetts Institute of Technology Cambridge, MA 02139

  28. Dyn-3D: Unveiling and Resolving Ego-Motion Ambiguity in Vision-Language Models

    Sep 1, 2026Jiayu Ding, Zhuodong Liu, Lei Zhang +63D Spatial Reasoning3D Motion

    InkMind Team

  29. Fractal dimension predicts quantum kernel collapse in angle-encoded data

    Aug 31, 2026Ana Paula AppelQuantum KernelsFractal Dimension

  30. Collapsibility of Performance Metrics in Clinical Predictive AI

    Aug 31, 2026João Matos, Ben Van Calster, Richard D. Riley +2Performance MetricAlgorithmic Fairness

    Centre for Statistics in Medicine, University of Oxford · KU Leuven · University of Birmingham +1

  31. One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL

    Aug 12, 2026Simon Yu, Nicholas Tomlin, Marwa Abdulhai +7Multi-Agent SimulationsSimulation-Based Reinforcement Learning

    1Northeastern University · 2New York University · 3UC Berkeley +2

  32. Power law graph attention: exact generalization of scaled dot-product attention, empirical collapse at inference

    Aug 10, 2026Burc GokdenLinear AttentionInterleaved Graph Attention

    Fromthesky Research Labs LLC, Oregon, USA

  33. TAF-MED: Multi-Turn Safety Refusal Collapse in LLMs Under Declared Self-Treatment Intent

    Aug 10, 2026Waleed Jamil, Raphael SchmittLarge Language Model SafetyTreatment

    1Independent Researcher, Edinburgh, United Kingdom · School of Computation, Information and Technology, Technical University of Munich, Germany · Institute of General Practice, Faculty of Medicine and Medical Center, University of Freiburg, Germany

  34. AdapterMoE: A Two-Stage Hard-Routing Mixture-of-Experts Architecture for Multi-Crop Disease Recognition with Calibrated Rejection and Incremental Learning

    Aug 9, 2026Pin-Hsun Huang, Shaou-Gang MiaouLeaf Disease ClassificationClass-Incremental Learning

    Department of Electronic Engineering, Chung Yuan Christian University, Taoyuan, Taiwan

  35. Ground-Truth Neighborhood Regularization for Reinforcement Learning Post-Training of Time Series Foundation Models

    Aug 8, 2026Jianqi Zhang, Xingyu Zhang, Zeen Song +3Time Series Foundation ModelsReinforcement Learning Post-Training

    Institute of Software, Chinese Academy of Sciences, Beijing, China

  36. Post-Grokking Collapse at the Representation-Readout Interface in Muon-Trained Transformers

    Aug 7, 2026Ali Janati, Kaoutar El Maghraoui, Anass BelfatmiMuonGrokking

    Data Science Institute, Columbia University, New York, NY, USA · Department of Computer Science, Columbia University, New York, NY, USA · CentraleSupélec, Gif-sur-Yvette, France

  37. A Theory of Conditional Collapse under Low-Rank Weight-Space Ablations: I. The Single-Block Theory and Synthetic Validation

    Aug 4, 2026Abdallah KhemaisAblationCollapse

    ISITCOM, University of Sousse

  38. In-Context Collapse in Vision-Language Models and How to Mitigate it?

    Aug 3, 2026Mohammad RostamiVision-Language Foundation ModelsIn-Context Learning

    Amazon Generative AI Innovation Center∗, USA.

  39. ASTRA: Asynchronous Spatio-Temporal Reconstruction via Trajectory Alignment

    Aug 3, 2026Junyu Zhu, Hao Zhu, Xinzhuo Zhang +3Scene ReconstructionMotion Blur

    School of Electronic Science and Engineering, Nanjing University, Nanjing, 210023, China · College of Engineering, Computing and Cybernetics, Australian National University, Canberra, ACT 2601, Australia

  40. When Memory Becomes Authority: Benchmarking Authority Collapse at the Memory Consolidation Boundary

    Aug 3, 2026Qiuyang Zhan, Rui Zhang, Sheng Guo +2AuthorityAuthorization

    Tsinghua University · East China Normal University

  41. Semantic Alignment of AI Models: Concept Collapse, Checkpoint Dynamics, and Cross-Lingual Transfer

    Aug 3, 2026Tyler Ashoff, Jordan RoduLarge Language Model AlignmentCross-Lingual Transfer

    Department of Statistics, University of Virginia. · Department of Statistics, University of Virginia

  42. SAF-OPD: Stable Advantage Fusion for On-Policy Distillation

    Jul 31, 2026Yifan Ding, Xincheng Wei, Yoshua Y. Li +7Reinforcement Learning With Verifiable RewardReward Functions

    Shanghai University of Finance and Economics · Meituan, LongCat Team · The Chinese University of Hong Kong, Shenzhen +1

  43. Calibrated Partial Resets: Preventing Policy Collapse in Continual Reinforcement Learning

    Jul 27, 2026Luc McCutcheon, Evangelos Chatzaroulas, Saber FallahReplay-Based Continual LearningPlasticity

    Department of Mechanical Engineering, University of Surrey, United Kingdom · Department of Computing Science, University of Surrey, United Kingdom

  44. Denial of Deadline: Network-Driven Accuracy Collapse in Distributed Inference Pipelines

    Jul 27, 2026Jhonatan Tavori, Gur-Eyal Sela, Ion Stoica +1DeadlinesCollapse

    Columbia University · UC Berkeley

  45. Asymmetric Collapse in Model Merging: When Refusal Over- writes Recognition

    Jul 26, 2026Aarnav Choudhary, Matheus Fonseca Rocha, Jiwon Seo +2Continual Model MergingSafety Alignment

    UCLA · Algoverse · Purdue University +1

  46. Confidently Wrong: Exception Chain Collapse in Frontier LLM Rule Evaluation

    Jul 25, 2026Paul Simpson, John Kozak, Lisa DoakeFrontier ModelsLarge Language Model Evaluation

    Aethis (aethis.ai)

  47. Neptuna: A Comprehensive Machine Learning Framework for Benchmarking Complex Multiphase Flows

    Jul 24, 2026Harish Ramachandran, Björn Kimpel, Thomas Paula +3Surrogate ModelsMultiscale Dynamics

    Technical University of Munich

  48. Adversarial Prompts for Acceptance Collapse in Speculative Decoding

    Jul 23, 2026Run Wang, Chaoyi Zhou, Xi Liu +7Speculative DecodingAdversarial Prompts

    Clemson University · Wayne State University · University of Washington

  49. ElasticTTT: Prior-Preserving Test-Time Tuning for Video Editing

    Jul 23, 2026Yueyi Liu, Chi Zhang, Sen Cui +1Video EditingDiffusion-Based Image Editing

    College of AI, Tsinghua University1 · Beijing Academy of Artificial Intelligence2

  50. Temporal-Causal Unity as an Operational Framework for Collective Dynamics: Causal-Progress Clocks, Synchronization, and Polarization

    Jul 21, 2026Jian Liu, Dong SunCausalTemporal Dynamics

    Xintong Zhima (Beijing) Technology Co., Ltd., Beijing, China

  51. Competitive and Complementary Tools

    Jul 20, 2026David C. KrakauerControlling Tool UseCompetence

  52. Dynamic Defense Profiling Enables Cognitive Jailbreak of Text-to-Image Models

    Jul 20, 2026Dongdong Yang, Deyue Zhang, Zhao Liu +5Adversarial PromptsJailbreak Success Rates

    AI Security Lab, Beijing, China · School of Artificial Intelligence, Beihang University, Beijing, China

  53. Learning from Synthetic Data without Model Collapse in Iterative Instruction Tuning

    Jul 19, 2026Xiaonan Luo, Yue Huang, Kehan Guo +4Instruction TuningSynthetic Training Data

    University of Notre Dame · Vanderbilt University · University of Pennsylvania

  54. Regularize or Localize: When Training-Time KV-Cache Geometry Pays Under Quantization

    Jul 19, 2026Libo Sun, Po-Wei Harn, Zewei Zhang +2Key-Value Cache QuantizationRegularization

    Department of Computer Science and Software Engineering, Auburn University, Auburn, AL 36830, USA · Department of Information Management, National Central University, Taoyuan 320317, Taiwan

  55. Distribution-First Population Simulation: Collapse, Calibration, and Recall in Non-WEIRD LLM Persona Modeling

    Jul 17, 2026Gurkan OzkanArtificial Intelligence PersonasUser Simulation

    Istanbul Technical University

  56. The SIGReg Objective as Variational Free Energy: A Theoretical Active-Inference Account of JEPA World Models

    Jul 15, 2026Fabio Arnez, Alexandra Gomez-VillaJoint-Embedding Predictive ArchitecturesVariational

    Université Paris-Saclay, CEA, List F-91120, Palaiseau, France · Computer Vision Center Barcelona, Spain

  57. Diagnosing and Mitigating Thinking Collapse in On-Policy Self-Distillation

    Jul 12, 2026Keqin Peng, Chen Li, Yuanxin Ouyang +2Unsupervised On-Policy Self-DistillationCollapse

    Beihang University · Hong Kong Polytechnic University · Alibaba Group

  58. Deep Gaussian Processes on Directed Acyclic Graphs

    Jul 10, 2026Federico L. Perlino, Oliver Hamelijnck, Adam M. Johansen +1Directed Acyclic GraphGaussian Process

    Department of Statistics, University of Warwick · 2AI Team, Unilink Software Ltd · Department of Computer Science, University of Warwick

  59. Progression as Latent Drift: Generative Forecasting of Slow-Evolving Pathologies

    Jul 9, 2026Yuxiang Feng, Juncheng Wang, Chao Xu +7Magnetic Resonance ImagingCollapse

    Zhejiang University, Hangzhou, China · IROOTECH TECHNOLOGY, China · The Hong Kong Polytechnic University, Hong Kong, China +1

  60. Recursive Self-Improvement in AI: From Bounded Self-Refinement to Autonomous Research Loops

    Jul 8, 2026Mingguang Chen, Licheng Wang, Bo QuRecursive Self-ImprovementSelf-Evaluation

    University of California, Riverside (UCR) · AlphaAvatar · Illinois Institute of Technology (IIT)