Corrupted Inputs

Ask about this topic

Momentum

5 papers in the last four weeks, level with the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28
View on map

Latest papers 42

All topics
CardsList

  1. Spontaneous Context Restoration: How Language Models Recover from Corrupted Inputs

    Sep 28, 2026Pranjal Garg, Jacob BeckCorrupted InputsLanguage Model Computes

    Independent Researcher

  2. Repair Before You Fuse: Frozen-Host Adaptation for Corrupted-but-Present Sensors

    Sep 28, 2026Gia-Huy Thai, Quang-Thinh Ly, Anh-Minh Phan +1Corrupted InputsLight Detection And Ranging Data

    University of Science, VNU-HCM, Ho Chi Minh City 700000, Vietnam · Michigan State University, East Lansing, MI 48824, USA · Center for Environmental Intelligence, VinUniversity, Hanoi 100000, Vietnam +1

  3. Training-Adaptive Convolutional Sparse Coding via Information Bottleneck for Robust Visual Representation

    Sep 16, 2026Meng'en Qin, Yinchen Liu, Mingxuan Cui +1Information BottleneckSparsity

    Faculty of Computer Science and Artificial Intelligence, Shenzhen University of Advanced Technology, Shenzhen, China · School of Mathematical Sciences, University of Electronic Science and Technology of China, Chengdu, China · School of Mathematics, Shandong University, Jinan, China

  4. Evidence-Aligned Local Composition of Discrete Experts for Sequence Restoration

    Sep 14, 2026Mohammad Panahazari, Usman A. Khan, Shuchin AeronRestorationExpert Demonstrations

    Department of Electrical and Computer Engineering, Tufts University, Medford, Massachusetts · Boston College, Chestnut Hill, Massachusetts

  5. RoboDrop: Curating VLA Post-Training Data via Local Gradient Compatibility

    Sep 9, 2026Runze Xu, Yuanfan Xu, Cuijie Xu +4Large-Scale Robot Demonstration DatasetsRobocasa

    Tsinghua University · Striding AI

  6. Local Chord Corruption Is Not Recognizer Replay: Structure-Matched Calibration for Chord-Conditioned Generation

    Sep 3, 2026Weiwen HuangSheet MusicAccompaniment

    Shenzhen University

  7. TrainSDC: Characterizing and Mitigating Silent Data Corruption in Large Language Model Training

    Aug 31, 2026Zhipeng Xia, Haotian Xu, Siyu Yun +4Large Language Model TrainingCorrupted Inputs

    Zhejiang University · Huawei

  8. KItCAT: Knowledge Injection via Input Corruption for Auto-regressive Training

    Aug 31, 2026Meghanadh Pulivarthi, Kushagra Bhushan, Vineet Kumar +5Next-Token PredictionCorrupted Inputs

    IBM · Work done while at IBM. Currently at Amazon Books

  9. Quantifying and Mitigating Korean Jamo-Level Typographical Vulnerabilities in Large Language Models

    Aug 31, 2026Seojin Lee, Hwanhee LeeGrammatical Error CorrectionLarge Language Models Fail

    Chung-Ang University, Seoul, Korea

  10. Is this Citation on Point?

    Aug 12, 2026Apurv VermaCitationsText Corpora

    Bloomberg, New York, NY, USA.

  11. Corrupting Attention: Evasion-Based Adversarial Attacks on Encoder Attention in Detection Transformers

    Aug 7, 2026Ridma Jayasundara, Shaheer Mohamed, Tharindu Fernando +6Detection TransformerBlack-Box Adversarial Attacks

    Signal Processing, Artificial Intelligence and Vision Technologies Group (SAIVT), Queensland University of Technology · Institute of High-Performance Computing, Agency for Science, Technology and Research, Singapore · School of Computing, National University of Singapore +1

  12. Relational Response Fields: A General Theory of Black-Box LLM Response Consistency and Recovery

    Aug 5, 2026Song ZichenLarge Language Model ReliabilityResponses

    Sungkyunkwan University

  13. VESTIGE: A Knowledge-Guided Masking Strategy for Corruption-Aware Fine-Tuning of Genomic Transformers, Validated on Ancient DNA Reconstruction

    Jul 30, 2026Angshuman Chakravertty, Rahul MaheshwariGenome-Wide Association StudyCorrupted Inputs

    School of Technology Management & Engineering, SVKM’s Narsee Monjee Institute of Management Studies (NMIMS) Deemed-to-be-University, Jadcherla, Hyderabad 509301, Telangana, India, Hyderabad, India · School of Pharmacy and Technology Management, SVKM's Narsee Monjee Institute of Management Studies (NMIMS) Deemed-to-be-University, Hyderabad, Jadcheral-509301, Telangana, India · School of Pharmacy and Technology Management, SVKM's Narsee Monjee Institute of Management Studies (NMIMS) Deemed-to-University, Hyderabad, Jadcheral-509301, Telangana, India

  14. Conformal Changepoint Localization and Root Cause Analysis with Corrupted Observations

    Jul 29, 2026Seunghun Yu, Meiyi Zhu, Petar Popovski +2Change-Point DetectionConformal Inference

    Department of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon 34141, South Korea · Department of Engineering, King’s College London, WC2R 2LS, London, U.K. · Department of Electronic Systems, Aalborg University, 9220 Aalborg, Denmark +2

  15. Point-Selection Fine-Tuning Framework for Robust Point Cloud Classification

    Jul 22, 2026Da Li, Chang Ma, Dongfu YinPoint CloudsInteractive 3D Segmentation

    Guangdong Laboratory of Artificial Intelligence and Digital Economy (Shenzhen), Shenzhen, China · Shenzhen University, Shenzhen, China

  16. The Knowing-Saying Gap: When Probes See Errors that Confidence Misses

    Jul 21, 2026Jyotin Goel, Ipshita Bandyopadhyay, Justin ShenkCorrectnessReasoning Gaps

  17. DARA: Degradation-Aware Low-Rank Residual Adaptation with Original-to-Corrupted Distillation for Corruption-Robust Animal Re-Identification

    Jul 18, 2026Cynthia Xie, Talia XuAnimal Re-IdentificationRe-Identification

    The University of Auckland Auckland, New Zealand

  18. MemPoison: Uncovering Persistent Memory Threats and Structural Blind Spots in LLM Agents

    Jul 16, 2026Jifeng Gao, Kang Xia, Yi Zhang +5PoisoningLarge Language Model Agents

    State Key Laboratory for Novel Software Technology, Nanjing University, China · NARI Group Corporation/State Grid Electric Power Research Institute, China

  19. Interleaved Noise Injection Improves Clean, Corrupted, and OOD Performance

    Jul 16, 2026Matt L. Wiemann, Peter Melchior, Andrew K. SaydjariData AugmentationRegularization

    Princeton University

  20. LQG solution for POMDP without estimating states: A minimum variance approach

    Jul 13, 2026Ranjan Sarkar, Prabhat K. MishraLinear Quadratic RegulatorState Estimation

    Department of Artificial Intelligence at Indian Institute of Technology Kharagpur, West Bengal, India

  21. Active Learning on Adversarially Corrupted Graphs

    Jul 6, 2026Marco Bressan, Nicolò Cesa-Bianchi, Tommaso d`Orsi +2Bounded AdversaryActive Learning

    Università degli Studi di Milano, Italy · Bocconi University, Italy · Google Research

  22. Obey, Diverge, Collapse: Blind Obedience to Incorrect Instructions Drives Code LLMs to Irrecoverable Code Semantic Collapse

    Jul 5, 2026Raj Jaiswal, Anany Singh Divy, Savar Bhasin +3Large Language Models FailInstruction-Tuned Models

    IIIT Delhi · Microsoft Research India · IIT Kanpur

  23. The Multipath Blind Spot: KK-Agnostic Robust Calibration for Sparse-Anchor Metric Depth from Frozen Foundations

    Jul 5, 2026Sohag Roy, Rajesh Misra, Swami Shastravidyananda +1Camera IntrinsicsSparse Spatial Anchors

    Department of Computer Science, Ramakrishna Mission Vivekananda Educational and Research Institute (RKMVERI), Belur, Howrah, West Bengal 711202, India

  24. Pathways of Visual Information Flow in Vision-Language Models

    Jul 3, 2026Israfel Salazar, Stella Frank, Dan Oneata +2PathwaysCorrupted Inputs

    University of Copenhagen · 2Technical University of Denmark · 3POLITEHNICA Bucharest +1

  25. Fixed-Set Robustness in Programming by Example: Example Corruption and Semantic Partition Recovery

    Jul 1, 2026Yuan Si, Jialu ZhangAutomated Program RepairCorrupted Inputs

    University of Waterloo, Waterloo, Canada

  26. SPECSIA: Stylization Dataset for Novel-View Enhancement in Drawing-based 3D Animation

    Jul 1, 2026Kyuwon Kim, Sunjae Yoon, Chang D. YooNovel View SynthesisLarge-Scale Image Datasets

    School of Electrical Engineering, KAIST, Daejeon, Republic of Korea · Department of AI, Chung-Ang University, Seoul, Republic of Korea

  27. Diff-Based Code Corruption using LLMs for Large-Scale Bugfix Benchmarking

    Jun 27, 2026Balázs Szalontai, Ábel Szauter, Balázs Márton +3Large Language Model BenchmarksReal-World Cloud Fault Injection Dataset

    Eötvös Loránd University · Faculty of Informatics

  28. Sum-of-Squares Degree Barriers for the Reweighted-Hinge Method in Robust Halfspace Learning: A Christoffel-Function Characterization

    Jun 15, 2026Xiaoyu LiFinite-Sample CertificatesOutliers

    University of New South Wales

  29. Benchmarking Instance-Dependent Label Noise with Controlled Corruptions

    Jun 12, 2026Shadman Islam, Agustinus Kristiadi, Mostafa MilaniNoisy LabelsCorrupted Inputs

    Department of Computer Science, Western University, London, Ontario, Canada

  30. Small Data, Big Noise: Adversarial Training for Robust Parameter-Efficient Fine-Tuning

    Jun 9, 2026Eitan Cohen, Idan Simai, Uri ShahamParameter-Efficient Fine-Tuning MethodsAdversarial Training

    Bar-Ilan University · Ramat Gan, Israel

  31. AsyncPatch Diffusion: spatially-flexible image generation

    Jun 5, 2026Samuele Papa, Valentin De Bortoli, Guillaume Couairon +3Diffusion ModelsDenoising Trajectory

    Google DeepMind · University of Amsterdam · The Netherlands Cancer Institute

  32. Distributionally Robust Set Representation Learning Under Inference-Time Element Corruption

    May 28, 2026Yankai Chen, Hanrong Zhang, Bowei He +2Distributionally-Robust OptimizationRobust Optimization

    MBZUAI · McGill University · University of Illinois Chicago

  33. CiteCheck: Retrieval-Grounded Detection of LLM Citation Hallucinations in Scientific Text

    May 26, 2026Khashayar Khajavi, Shaghayegh Sadeghi, Rise Adhikari +1CitationsScientific Discovery

    FirstPrinciples · School of Computing Science, Simon Fraser University

  34. AgentHijack: Benchmarking Computer Use Agent Robustness to Common Environment Corruptions

    May 25, 2026Jingwei Sun, Jianing Zhu, Yuanyi Li +3Computer-Use AgentsHijacking

    TMLR Group, Hong Kong Baptist University · The University of Texas at Austin · Sydney AI Centre, The University of Sydney +1

  35. Cascade-KDE: Robust Time-Series Restoration under Out-of-Distribution Impulse Corruptions

    May 22, 2026Yuefeng Liu, Ning Yang, Ziyu YangOutliersImage Restoration

    School of Digital and Intelligent Industry (School of Cyber Science and Technology), Inner Mongolia University of Science and Technology, Baotou, China

  36. Discriminator-Guided Adaptive Diffusion for Source-Free Test-Time Adaptation under Image Corruptions

    Apr 26, 2026Francesco Olivato, Cigdem Beyan, Vittorio MurinoDomain AdaptationCorrupted Inputs

    Department of Computer Science, University of Verona, Verona, Italy · AI for Good (AIGO), Istituto Italiano di Tecnologia, Genova, Italy

  37. Bit-Flip Vulnerability of Shared KV-Cache Blocks in LLM Serving Systems

    Apr 19, 2026Yuji Yamamoto, Satoshi MatsuuraKv-Cache ManagementLarge Language Model Serving

    Institute of Science Tokyo, Tokyo, Japan

  38. Linear Regression under Missing or Corrupted Coordinates

    Sep 23, 2025Ilias Diakonikolas, Jelena Diakonikolas, Daniel M. Kane +2Corrupted InputsMissing Data

    University of Wisconsin-Madison · University of California, San Diego · University of California, Davis

  39. FairSAM: Fair Classification on Corrupted Image Data Through Sharpness-Aware Minimization

    Mar 29, 2025Yucong Dai, Jie Ji, Xiaolong Ma +1Image ClassificationAlgorithmic Fairness

    Clemson University

  40. Measuring the Robustness of Audio Deepfake Detection under Real-World Corruption

    Mar 21, 2025Xiang Li, Pin-Yu Chen, Wenqi WeiEnvironmental Sound Deepfake DetectionAudio Deepfake Detection

    Fordam University New York City, New York, USA · IBM Research Yorktown Heights, New York, USA · Fordham University New York City, New York, USA

  41. An Expectation-Maximization Algorithm for Training Clean Diffusion Models from Corrupted Observations

    Jul 1, 2024Weimin Bai, Yifei Wang, Wenzheng Chen +1Diffusion ModelsExpectation-Maximization

    Academy for Advanced Interdisciplinary Studies, Peking University · College of Future Technology, Peking University · National Biomedical Imaging Center, Peking University +3

  42. PVF:Understanding AI Vulnerability Against SDCs

    May 2, 2024Xun Jiao, Fred Lin, Harish D. Dixit +8Real-World Cloud Fault Injection DatasetCorrupted Inputs

    Meta Platforms, Inc