Fragility

Ask about this topic

Momentum

12 papers in the last four weeks, up 100% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28
View on map

Latest papers 62

All topics
CardsList

  1. Frozen Scenes, Shifting Winners: Configuration Fragility in Text-to-3D Evaluation

    Sep 30, 2026Anson Y. Lam, Shuqing Li, Michael R. Lyu3D Generative ModelsImage-Text Alignment

    Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong, China

  2. How Much Can Reliability Drift Under a Fixed Confidence Distribution?

    Sep 30, 2026Wenhao Liang, Lin Yue, Wei Emma Zhang +3Confidence IntervalsFragility

    Adelaide University

  3. Selective Channel Restoration for Backdoored Vision-Language Models

    Sep 29, 2026Shuming Liu, Zhifang Zhang, Suqin Yuan +3Model-Agnostic DefensePost-Training

    Southeast University · The University of Queensland · University of Sydney +1

  4. Does the Unsafe Gradient Survive a Conversation? On the Fragility of Gradient-Based Jailbreak Detection in Multi-Turn Dialogue

    Sep 29, 2026Omar Sheta, Rinku Deuja, Hadi Masoudi +1Large Language Model SafetyJailbreaks

    University of Louisville Louisville, Kentucky, USA

  5. Fine Until Fine-Tuned: Repeated Solutions Make Reasoning Fragile

    Sep 27, 2026Ely SheikhLarge Reasoning ModelsRepetition

    Aix-Marseille University

  6. A Four-Stage Decomposition of Word-Problem Solving and Mechanistic Fragility in LLM Math Reasoning

    Sep 15, 2026Zhongdi Qu, Carla P. GomesMath ProblemsLLM Reasoning Strategies

    Cornell University

  7. Temperature Fragility and the Conditional Benefits of Truncation Sampling

    Sep 14, 2026Francesco La RosaTruncationMmlu-Pro

    University of Edinburgh

  8. Control Architecture for Safe Grasping of Fragile Objects Using a Coarse Position-Controlled Gripper

    Sep 14, 2026Marko Pavlic, Moritz Geier, Timo Markert +1Robotic GraspingGripper

    Machine Vision and Perception Group, Chair of Robotics, Artificial Intelligence and Real-time Systems, Technical University of Munich, Munich, Germany · Resense GmbH, Klingenberg, Germany · Semantic Information Systems Group, Osnabrück University, Osnabrück, Germany

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

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

    Shandong University

  10. When Noise Fabricates Bias: The Fragility of LLM-as-a-Judge Bias Measurement under Noisy Text

    Sep 10, 2026DongHyun Ryu, Jaehyeok Lee, YeongJun Hwang +1Large Language Model BiasLlm-As-A-Judge

    Sungkyunkwan University, Suwon, South Korea

  11. Interpreting Object-Dependent Concept Brittleness in Text-to-Image Diffusion Models

    Sep 9, 2026Yifan Yuan, Xiangyu Liu, Hongming Shan +5Text-To-Image Diffusion ModelsDiffusion Models

  12. FreqBLiMP: Frequency-Controlled Minimal Pairs Reveal Robustness and Fragility of LLMs Under Lexical Rarity

    Sep 7, 2026Tyrone White, Yuki AraseImplicit Association TestLinguistics

    School of Computing, Institute of Science Tokyo Tokyo, Japan

  13. When Safety Routing Breaks: Understanding Alignment Fragility under Benign Fine-Tuning

    Sep 1, 2026Yitong Guo, Xiaoyi Chen, Siyuan Zhang +2FragilityModel Fine-Tuning

    Indiana University Bloomington · Tsinghua University · Nanyang Technological University

  14. The Fragility of Jailbreak Robustness Across Operational States

    Aug 31, 2026Yuna Park, Hwang Youn Kim, Yujin Kim +3Jailbreak AttacksAttack-Success Rate

    Yonsei University · Korea Institute of Science and Technology (KIST) · Korea University +1

  15. Rules or Character? Scaling Laws for AI Safety Design

    Aug 13, 2026Satoshi Takahashi, Nobuji Kouno, Masaaki Komatsu +1Artificial Intelligence SafetyFragility

    AI Medical Engineering Team, RIKEN Center for Advanced Intelligence Project, Tokyo, Japan · Division of Medical AI Research and Development, National Cancer Center Research Institute, Tokyo, Japan

  16. Decomposition of Evidence, Contradiction, and Fragility in Perturbation Responses

    Aug 13, 2026Lei YouFragilityContradiction

    Technical University of Denmark

  17. Localizing Safety Alignment: MLP Layers and Mid-Network Blocks Encode Refusal Behavior in Large Language Models

    Aug 12, 2026Mingyu Zong, Sampad Mohanty, Bhaskar KrishnamachariSafety AlignmentLarge Language Model Alignment

    Department of Computer Science University of Southern California Los Angeles, CA 90007

  18. Attention-Path Fragility as an Uncertainty Signal in Large Language Models

    Aug 11, 2026Minsoo Kim, Sungyoung Ji, Kisung Moon +1Large Language Model UncertaintySemantic Entropy

    POSCO Holdings Future Technology Research Institute 440, Teheran-ro, Gangnam-gu, Seoul, Republic of Korea

  19. When Efficiency Becomes Fragility: Exploiting Dynamic Routing Vulnerabilities in Adaptive UAV Tracking

    Aug 4, 2026Shaofeng Liang, Runwei Guan, Wenshuo Chen +7Unmanned Aerial Vehicle DetectionMulti-Object Tracking

    The Hong Kong University of Science and Technology (Guangzhou) · Wuhan University · Institute of Deep Perception Technology (JITRI)

  20. GoT-CD: Graph-of-Thoughts Causal Discovery and the Fragility of Post-hoc Path-Specific Fairness Audits

    Aug 3, 2026Nitish Nagesh, Elahe Khatibi, Thomas Dean Hughes +3Fairness AuditsAlgorithmic Fairness

    Department of Computer Science, University of California, Irvine, Irvine, CA, USA · University of Orléans, Orléans, France

  21. Deep Learning CNN and Recurrence Analysis for Alpha Gamma EEG Biomarkers in Fragile X Syndrome

    Aug 1, 2026Zag ElSayed, Payton Siekierski, Jack Yanchen Liu +1Seizure DetectionElectroencephalography

    School of Information Technology (SoIT), University of Cincinnati, Ohio, USA · Division of Child and Adolescent Psychiatry Cincinnati Children’s Hospital Medical Center, Ohio, USA

  22. Fragility of Value under Imperfect Alignment

    Jul 30, 2026Winter CrossArtificial Intelligence AlignmentHuman Values

    Dovetail Research

  23. Attacking Graph Foundation Models Through Their Shared Representation

    Jul 20, 2026Pankaj Kumar, Subhankar MishraGraph Foundation ModelWhite-Box Spectral-Subspace-Guided Attack

    1National Institute of Science Education and Research · 2An OCC of Homi Bhabha National Institute

  24. First-Order Predictable but Pairwise Fragile: Local Task Adaptation in Trained Transformers

    Jul 18, 2026Irina Piontkovskaia, Sergey NikolenkoTransformer ArchitecturesEfficient Task Adaptation

    1DAIMLD, Moscow, Russia · 2St. Petersburg Department of the Steklov Institute of Mathematics, St. Petersburg, Russia · 3St. Petersburg State University

  25. Grokking Is Conditional and Fragile: A Fully-Tractable, Multi-Seed Study at 12K Parameters

    Jul 6, 2026Yoshiyuki OotaniGrokkingLarge Language Model Training

    Independent Researcher

  26. The Good, the Bad, and the Brittle: Benchmarking Robustness and Generalisation of Histopathology Foundation Models

    Jul 5, 2026Dhyey Yajnik, Amina Asif, Fayyaz MinhasPathology Foundation ModelsComputational Pathology

    Predictive Systems in Biomedicine Lab, Tissue Image Analytics Centre, Department of Computer Science, University of Warwick, United Kingdom

  27. Can Agents Generalize to the Open World? Unveiling the Fragility of Static Training in Tool Use

    Jul 1, 2026Song-Lin Lv, Weiming Wu, Rui Zhu +2Open-WorldSupervised Finetuning

    School of Intelligence Science and Technology, Nanjing University, Nanjing, China · National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China

  28. Learning Generalizable Skill Policy with Data-Efficient Unsupervised RL

    Jul 1, 2026Jongchan Park, Seungjun Oh, Seungho Baek +1Unsupervised Skill DiscoveryGoal-Conditioned Value Function

    Department of Artificial Intelligence, Sungkyunkwan University, Suwon, Republic of Korea · Department of Computer Science and Engineering, Sungkyunkwan University, Suwon, Republic of Korea

  29. Self-Study Reconsidered: The Hidden Fragility of Learning from Self-Generated QA

    Jun 30, 2026Ekaterina Alimaskina, Denis Shveykin, Gleb Molodtsov +3Faithful Question GenerationQuestion

    BRAIn Lab · Yandex Research

  30. A Gravitational Interpretation of Safety Reversion under Fine-Tuning

    Jun 26, 2026Samuele Poppi, Nils LukasContinual Fine-TuningEmergent Misalignment

    Mohamed bin Zayed University of Artificial Intelligence (MBZUAI), UAE

  31. The Geometry of Refusal: Linear Instability in Safety-Aligned LLMs

    Jun 21, 2026Shivam Ratnakar, Kartikeya VatsLarge Language Model SafetyRefusals

    University of Southern California · Independent Researcher

  32. Skin-Deep: A Geometric Diagnostic for Alignment Fragility in Large Language Model Representations

    Jun 21, 2026Dongyub Jude Lee, Jungseob Lee, Seungyoon Lee +5RefusalsFragility

    Zoom Communications · Korea University · Yonsei University +1

  33. Optimal Order of Multi-Agent and General Many-Body Systems

    Jun 18, 2026Jake J. XiaModel-Based Multi-Agent SystemsCollective Behaviors

    Harvard Management Company · Research Affiliate at Massachusetts Institute of Technology

  34. Bridging Data Gaps in Structural Fragility Modeling through Transfer Learning: Methodology and Case Studies

    Jun 17, 2026Narges Saeednejad, Jamie Ellen PadgettFragilityTransfer Learning

    Department of Civil and Environmental Engineering, Rice University, Houston, TX, USA · Ken Kennedy Institute, Rice University, Houston, TX, USA

  35. Sycophancy as Material Failure under Pushback Loading: A Multi-Axis Characterization Across Three Loading Cases and up to Seventeen Material Charges

    Jun 15, 2026Ferdinand M. SchesslSycophancyDebate

  36. One Goal, Many Commands: Characterizing Denylist Fragility in AI Agents

    Jun 14, 2026Chuyang Chen, Zhiqiang LinArtificial Intelligence AgentsFragility

    The Ohio State University

  37. Cognitive Debt: AI as Intellectual Leverage and the Dynamics of Systemic Fragility

    Jun 13, 2026Shuchen MengCognitive LoadCognitive Science

    New York University

  38. The Perceived Fragility of Explanations in Audio Models: Manipulation of Attribution with Unchanged Predictions

    Jun 12, 2026Piotr Kitłowski, Dominik Wiącek, Mateusz ModrzejewskiAudio Deepfake DetectionExplainable AI Methods

    Faculty of Electronics and Information Technology, Warsaw University of Technology, Warsaw, Poland.

  39. Acquisition state behaves as a structured, measurable variable governing lung-nodule AI: kernel-driven measurement instability and noise-driven detection fragility, invisible to DICOM metadata

    Jun 11, 2026Daniel SolimanLung-Nodule Artificial IntelligenceAcquisition

  40. The Mathematics of AI Winters: The mathematical Taxonomy of Paradigm Fragility in AI Winter

    Jun 10, 2026Miquel Noguer i Alonso, David Pacheco AznarArtificial Intelligence ResearchArtificial Intelligence Systems

    AIFI

  41. When Probing Accuracy Saturates, Fragility Resolves: A Complementary Metric for LLM Pre-Training Analysis

    Jun 9, 2026Orion Reblitz-RichardsonFragilityComplementarity

    Distiller Labs.

  42. Learning Explicit Behavioral Models with Adaptive Questions and World-Model Probes

    Jun 5, 2026Hikaru Shindo, Yu Deng, Teng Cao +5Behavioral Foundation ModelsWorld Models

    1Artificial Intelligence and Machine Learning Lab, Technical University of Darmstadt, Germany · Department of Computer Science, Technical University of Darmstadt, Germany · 2Hessian Center for Artificial Intelligence (hessian.AI), Germany +3

  43. Testing LLM Arithmetic Reasoning Generalization with Automatic Numeric-Remapping Attacks

    Jun 2, 2026Malia Barker, Bishal Lakha, Edoardo Serra +1Mathematical Reasoning BenchmarksLLM Reasoning Strategies

    Department of Computer Science, Boise State University, Boise, ID, USA · University of L'Aquila, L'Aquila, Italy

  44. Linear Ensembles Wash Away Watermarks: On the Fragility of Distributional Perturbations in LLMs

    May 28, 2026Zhihao Wu, Gracia Gong, Qinglin Zhu +2Large Language Model WatermarksWatermarks

    Department of Informatics, King’s College London, UK · Department of Mathematics, Imperial College London, UK · Department of Statistics, University of Warwick, UK.

  45. Minimal Prompt Perturbations Lead to Code Vulnerabilities: Prompt Fragility and Hidden-State Signals in Coding LLMs

    May 28, 2026Alexander Sternfeld, Andrei Kucharavy, Ljiljana DolamicVulnerable CodeAi-Assisted Programming Tasks

    IEM, HES-SO, Le Foyer, Techno-Pôle 1, Sierre, Switzerland · Cyber-Defence Campus, armasuisse Science and Technology, Thun, Switzerland

  46. The Fragility of Chain-of-Thought Monitoring Across Typologically Diverse Languages

    May 27, 2026Eric Onyame, Runtao Zhou, Kowshik Thopalli +2Chain-of-Thought ReasoningSingle-Token Output Distributions

    University of Virginia · Lawrence Livermore National Laboratory

  47. When Context Flips, Safety Breaks: Diagnosing Brittle Safety in Aligned Language Models

    May 27, 2026Dasol Choi, Alex KwonLarge Language Model SafetySafety Benchmarks

    AIM Intelligence · Independent Researcher

  48. Unveiling the Fragility of Vision-Language Models: Multi-Modal Adversarial Synergy via Texture-Constrained Perturbations and Cross-Modal Optimization

    May 26, 2026Xiang Fang, Wanlong Fang, Changshuo WangRecent Vision-Language ModelsCross-Modal Attention

    School of Software Engineering, Huazhong University of Science and Technology · Nanyang Technological University, Singapore · University College London

  49. Algorithmic Fragility and Persona Bias in LLM-Generated Autistic Communication

    May 26, 2026Naba Rizvi, Mohammed Rizvi, Harper Strickland +2Large Language Models FailFragility

    University of California · Georgia Institute of Technology · Cardiff University

  50. Paraphrase Brittleness in Production Retrieval-Augmented Commercial Recommendation: Reproducibility Below the Rerun-Stability Baseline

    May 22, 2026Will Jack, Noah Lehman, Keller Maloney +1Brand-As-MemoryRecommendation

    Unusual

  51. Generalization or Memorization? Brittleness Testing for Chess-Trained Language Models

    May 17, 2026Ethan TangChessModel Checkpoints

    School of Computing and Augmented Intelligence · Arizona State University · Tempe, AZ 85281

  52. Adversarial Fragility and Language Vulnerability in Clinical AI: A Systematic Audit of Diagnostic Collapse Under Imperceptible Perturbations and Cross-Lingual Drift in Low-Resource Healthcare Settings

    May 16, 2026Anthonio Oladimeji Gabriel, Ahmad Rufai YusufCross-Lingual ConsistencyCross-Architecture Generalization

    Centre for Clinical Intelligence & Safety, Ìyàwó, Nigeria · Tomorrow University of Applied Sciences, Germany

  53. On the Fragility of Data Attribution When Learning Is Distributed

    May 15, 2026Xian Gao, Bo Hui, Min-Te Sun +1IncentivesFragility

    Department of Computer Science and Software Engineering, Auburn University, Auburn, Alabama, USA · Department of Computer Science, University of Tulsa, Tulsa, Oklahoma, USA · Department of Computer Science and Information Engineering, National Central University, Taoyuan, Taiwan

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

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

    Lexsi Labs

  55. Sycophancy is an Educational Safety Risk: Why LLM Tutors Need Sycophancy Benchmarks

    May 14, 2026Enkelejda Kasneci, Gjergji KasneciEpistemic AsymmetryTutors

    Technical University of Munich, Munich, Germany · Munich Center for Machine Learning, Munich, Germany

  56. FragileFlow: Spectral Control of Correct-but-Fragile Predictions for Foundation Model Robustness

    May 9, 2026Zhuoyun Li, Boxuan Wang, Jinwei Hu +2FragilityLoss Function

    School of Computer Science and Informatics, University of Liverpool, UK

  57. Constraint Decay: The Fragility of LLM Agents in Backend Code Generation

    May 7, 2026Francesco Dente, Dario Satriani, Paolo PapottiCode GenerationLarge Language Model Agents

    EURECOM, France · University of Basilicata, Italy

  58. Minimum Specification Perturbation: Robustness as Distance-to-Falsification in Causal Inference

    May 2, 2026Hoang Dang, Luan Pham, Minh NguyenCausal InferencesFalsehood

    Independent Researcher · RMIT University, Australia · Florida Atlantic University, USA

  59. StyleShield: Exposing the Fragility of AIGC Detectors through Continuous Controllable Style Transfer

    Apr 30, 2026Guantian ZhengAi-Generated Content DetectionPhotorealistic Style Transfer

  60. On the explainability of max-plus neural networks

    Apr 27, 2026Ikhlas Enaieh, Olivier Fercoq, García ÁngelExplainabilityNeural Network

    S2A, LTCI · LTCI, T´el´ecom Paris · Institut Polytechnique de Paris +5