Shortcut Learning

Follow this topic Ask about this topic

Momentum

12 papers in the last four weeks, up 33% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 65

All topics

Removing Timing Shortcuts Improves Non-Invasive Brain-to-Text
Sep 30, 2026Dulhan Jayalath, Oiwi Parker JonesNeural Recordings Decoding
Neural Processing Lab (PNPL) Department of Engineering Science, University of Oxford
PCaPaint: Prostate Cancer Inpainting by Mitigating Shortcut Learning
Sep 29, 2026Levente Lippenszky, Hongxu Yang, Marcell Dömötör +2Prostate Magnetic Resonance Imaging Tumor Segmentation
GE HealthCare
DeShortcut-Align: Decoupling Spurious Shortcuts for Robust Safety Alignment in Large Reasoning Models
Sep 28, 2026Qirui Liu, Yichen Sun, Yan Wang +4Safety Alignment Large Language Model Alignment
The State Key Laboratory of Blockchain and Data Security, Zhejiang University · Ant Group · Chongqing Ant Consumer Finance Co., Ltd
Uncovering shortcut learning in audio classifiers by discovering recurring concepts in temporal explanations
Sep 27, 2026Cecilia Bolaños, Luciana Ferrer, Magdalena FuentesShortcut Learning Classifier
Departamento de Computación, FCEyN, UBA · ICC, CONICET-UBA, Buenos Aires, Argentina · Music and Audio Research Lab, New York University, USA +1
Unmasking Shortcut Learning in IoT Intrusion Detection: A Forensic, Multi-Paradigm Evaluation of Feature Dependence and Data Leakage
Sep 23, 2026Uday Shankar Roy, Mahbuba Jahan MinuIntrusion Detection Internet Of Thing
Computer Science and Engineering Khulna University of Engineering & Technology Khulna, Bangladesh
BindCLIP: One Balanced Coupling For Compositional Vision Language Scoring
Sep 20, 2026Liuyang Song, Yi Zhang, Zhongyi Deng +2Vision-Language Foundation Models Frozen Encoder
Peking University · Dongguan University of Technology · Sichuan Agricultural University
Bad Genius: Counterfactual-Guided Harness Evolution Beyond Task-Specific Shortcuts
Sep 16, 2026Guojun Zhu, Xunheng Huang, Peng Yin +3Agentic Evaluations Adversarial Evaluation
School of Mathematical Sciences, University of Chinese Academy of Sciences, China · Department of Statistics & Data Science, National University of Singapore, Singapore · Institute of Automation, Chinese Academy of Sciences, China
Spurious Tool Use: When RL Agents Learn the Wrong Reason to Act
Sep 14, 2026Yiwei Yang, Haoxiang Zhang, Bingbing Wen +6Large Language Model Agents Controlling Tool Use
University of Washington · University of California San Diego · Stanford University
Breaking the Vision-Action Shortcut: Latent Interface Training for Generalizable Robotics Foundation Models
Sep 14, 2026Jianman Lin, Shailesh Shailesh, Zhongyi Luo +1Action Generation End-Effector Pose
School of Future Technology, South China University of Technology, Guangzhou, China · National University of Singapore, Singapore · Nanyang Technological University, Singapore
Are You Learning Biological Signal or Shortcuts? Auditing and Mitigating Bias in Protein-Protein Interaction Datasets
Sep 9, 2026Judith Bernett, Anton Spannagl, Joel Ås +2Negative Results Shortcut Learning
Department Artificial Intelligence in Biomedical Engineering Friedrich-Alexander-Universität Erlangen-Nürnberg · TUM School of Life Sciences Technical University of Munich · Department of Experimental Oncology IEO European Institute of Oncology IRCCS
Prevalence calibration as shortcut mitigation
Sep 7, 2026Mohamed Amine Kina, Eike PetersenShortcut Learning Prevalence
Universität Bremen, Bremen, Germany · Fraunhofer Institute for Digital Medicine MEVIS, Bremen, Germany
Mitigating Shortcut Learning: Texture-Penalized Prototype Networks
Sep 7, 2026Akshay Anilkumar Girija, Elena Hoemann, Frank Köster +1Convolutional Neural Networks Texture
AI Engineering Department Institute for AI Safety and Security Ulm, Germany · AI Engineering Department Institute for AI Safety and Security Sankt Augustin, Germany · Institute for AI Safety and Security Braunschweig, Germany
MedQA-MM: Shortcuts Behind Medical Visual Reasoning
Sep 3, 2026Benlu Wang, Yifan Zhang, Jiaqing Yu +7Medical Visual Question Answering Multimodal Clinical Data
University of Massachusetts Amherst · 4Yale University · University of Massachusetts Lowell +6
HarnessEvolve: Learning from Reference Trajectories for Reliable Agent Self-Evolution
Sep 1, 2026Wen Jiang, Mingmin Chu, Yimeng Tian +6Self-Evolving Agents Self-Evolution
ICT AI Competence Center, Huawei Technologies, Shanghai, China
BAITBENCH: Measuring Agent Reward Hacking with Optional Shortcuts Planted in ML Tasks
Aug 31, 2026Pradyumna Shyama Prasad, Meiri Anto, Leon Eshuijs +3Agentic Benchmarks Exploitation
National University of Singapore · MIT · Vrije Universiteit Amsterdam +3
GUIDE: Guiding Internal Evidence with Language Instructions
Aug 31, 2026Soyeon Caren Han, Hyunsuk Chung, Jinwoo Kim +2Multimodal Model Guidance
School of Computing and Information Systems, The University of Melbourne, Melbourne, Australia · Department of Computer Science and Engineering, Korea University, Seoul, Republic of Korea · Brain Science Institute, Korea Institute of Science and Technology, Seoul, Republic of Korea +1
ICON Decomposition: Auditing deep neural networks for shortcuts by decomposing layer-wise representations using concepts
Aug 26, 2026Roshan Prakash Rane, Marco Simnacher, Manuel Pfeuffer +7Explainability Shortcut Learning
Hertie Institute for AI in Brain Health, University of Tübingen, Tübingen, Germany. · Department of Psychiatry and Neurosciences, Charité - Universitätsmedizin Berlin, Berlin, Germany. · Department of Psychology, Humboldt-Universität zu Berlin, Berlin, Germany. +5
Intervention, Not Shared Latents: Blocking Visual Shortcuts in Audio-Video Generation
Aug 14, 2026Jian Xu, Delu Zeng, John PaisleyAudio-Video Generation Shortcut Learning
RIKEN iTHEMS · RIKEN AIP · South China University of Technology +1
Look What the Probes Dragged In! Real-World Chest X-ray Shortcuts in MedCLIP
Aug 12, 2026Nikolette Pedersen, Regitze Sydendal, Veronika Cheplygina +1Chest X-Ray Shortcut Learning
Pattern Recognition Revisited Lab (PURRlab) IT University of Copenhagen, Denmark
UNMASK: Discovering and Causally Verifying Spurious Shortcuts in Text Classifiers
Aug 10, 2026Chidaksh Ravuru, Shashank SrivastavaLarge Language Model Classification Spurious Correlations
Department of Computer Science University of North Carolina, Chapel Hill
UNSPECIFIC: General Constraint Synthesis for Breaking Copy-and-Paste Shortcut in LLM Instruction Following
Aug 10, 2026Jeet Sharma, Balpreet Kaur, Jeremiah Hong +2Instruction-Tuned Models Instruction
University of Massachusetts, Amherst, USA
Invisible Shortcuts: Why Vision Encoders Know Your Camera
Aug 5, 2026Vladan Stojnić, Ryan Ramos, Giorgos Kordopatis-Zilos +2Vision Encoders Encoders
VRG, FEE, Czech Technical University in Prague · The University of Osaka
When Refusal Looks Safe: The Refusal-Cue Shortcut in Safety Guard Models
Aug 4, 2026Yu Feng, Chunting Zang, Chen Shen +4Refusals Suppression
The University of Sydney · Alibaba Group · Jilin University +1
Right Answer, Wrong Method: Shortcut Hacking Misleads the Evaluation of LLM Reasoning on Frontier Science Benchmarks
Aug 3, 2026Xuan Ren, Weiqi Zhai, Tianle Pu +4Reasoning Benchmark Large Language Model Benchmarks
1Alibaba Group · 2Alibaba DAMO Academy
Recompute or Reuse? Diagnosing and Mitigating Textual Shortcuts in VLM Self-Reflection
Aug 3, 2026Wenxiao Fan, Jingling Fu, Fang Li +9Visual Evidence Shortcut Learning
School of Computer Science, Beijing Institute of Technology · Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University
Analysis of the Shortcut Learning and Clever Hans Effect in CNN based ECG Image Classification
Jul 27, 2026Abhay Kumar Pathak, Mrityunjay Chaubey, Manjari Gupta +1Electrocardiogram Classification Convolutional Neural Networks
Department of Computer Science, Institute of Science, Banaras Hindu University, Varanasi, India. · University of Petroleum and Energy Studies, Dehradun, India. · Department of Computer Science (IDI), Norwegian University of Science and Technology (NTNU), Gjøvik, Norway.
Alleviating Regional Shortcuts for Few-Shot Class-Incremental Learning
Jul 24, 2026Haichen Zhou, Yazhe Lyu, Yixiong Zou +2Class-Incremental Learning Few-Shot Learning
School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan 430074, China
Style over Substance: A Shortcut Audit of Emotion-Description Preference Evaluation
Jul 20, 2026Jiabing Yang, Yixiang Chen, Yuan Xu +6Emotion Recognition Multimodal Evaluation
University of Chinese Academy of Sciences Institute of Automation, Chinese Academy of Sciences Beijing, China
Controlling Implicit Shortcut Reliance in L2 Spoken English Auto-markers
Jul 17, 2026Shilin Gao, Mark J. F. Gales, Kate M. KnillLinguistics Shortcut Learning
ALTA Institute, Machine Intelligence Laboratory, Cambridge University Engineering Department Cambridge, UK
Genre Bias or Aesthetic Perception? Identifying and Mitigating Shortcut Learning in Music Evaluation
Jul 15, 2026Yizhou Zhang, Wangjin Zhou, Yi Zhao +3Aesthetics Model Evaluation
Graduate School of Informatics, Kyoto University, Japan · WXG, Tencent, China
A Shortcut to Statistically Steady-State Turbulence with Flow Matching
Jul 14, 2026Gianluca Galletti, Gerald Gutenbrunner, William Hornsby +5Turbulent Flows Generative Models
Institute for Machine Learning, JKU Linz · United Kingdom Atomic Energy Authority, Culham campus · Mistral AI
Artificial Foveated Perception for Mitigating Shortcut Learning in Robotic Foundation Models
Jul 12, 2026Xiatao Sun, Yuan Zhuang, Mateo Sanchez Lopez Negrete +9Robotic Perception Recent Vision Foundation Models
1Yale University · University of Connecticut · 3Peking University +2
Association Restoration Test: Revealing Restorable Shortcuts after Unlearning
Jul 7, 2026Amy Lu, Changxiu JiShortcut Learning Unlearning Method
Department of Computer Science, Stanford University
Shortcut Learning in Legal Judgment Prediction: Empirical Evidence from the UK Employment Tribunal
Jul 5, 2026Joe Watson, Joana Ribeiro de Faria, Marcus Tomalin +6Large Language Model Forecasting Clinical Prediction
Faculty of Law, University of Cambridge, Cambridge, United Kingdom · The Psychometrics Centre, Cambridge Judge Business School, University of Cambridge, Cambridge, United Kingdom · Faculty of English, University of Cambridge, Cambridge, United Kingdom +3
The Moving Eye: Enhancing VLA Spatial Generalization via Hybrid Dynamic Data Collection
Jul 2, 2026Jincheng Tang, Yilong Zhu, Zhengyuan Xie +2Diffusion-Based Vision-Language-Actions Large-Scale Robot Demonstration Datasets
Lion Rock AI Lab, China Merchants Research Institute of Advanced Technology. · The Hong Kong University of Science and Technology. · Nankai University.
Dataset Biases and Shortcut Learning in Motion-Based AI-Generated Video Detection
Jul 1, 2026Joren Michels, Lode Jorissen, Nick MichielsAi-Generated Video Detection Shortcut Learning
Digital Future Lab, Flanders Make, Hasselt University
Modal CEGAR-tableaux with RECAR and resolution-based SAT-shortcuts
Jun 30, 2026Rajeev Goré, Cormac KikkertSatisfiability Theorem Proving
Faculty of Information Technology, Monash University, Australia · Cormac Kikkert Research
SGD Provably Prioritizes a Shortcut Spurious Feature in the XOR Model
Jun 29, 2026Tyler LaBonte, Vidya MuthukumarFeature Learning Rectified Linear Unit Networks
H. Milton Stewart School of Industrial and Systems Engineering, Georgia Institute of Technology · School of Electrical and Computer Engineering, Georgia Institute of Technology
To Reason or to Fabricate: Reasoning Without Shortcuts via Hint-Anchored Pairwise Aggregation
Jun 28, 2026Jiuheng Lin, Chen Zhang, Yansong FengReasoning Skills Shortcut Learning
Wangxuan Institute of Computer Technology, Peking University
Dismantling Pathological Shortcuts: A Causal Framework for Faithful LVLM Decoding
Jun 25, 2026Liu Yu, Can Chen, Ping Kuang +3Recent Vision-Language Models Large Language Model Hallucination
School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, Sichuan, China · School of Computer Science, University of Auckland, Auckland, New Zealand
Cross-View Variance Correlation in Path-Traced Stereo:A Hidden Shortcut in Synthetic Training Data
Jun 24, 2026Po-Ting LinStereo Vision Cross-View
Independent Researcher · Taiwan,Tainan
Breaking Shortcut Learning for Cross-Trial EEG-Guided Target Speech Extraction via Two-Stage Training
Jun 23, 2026Wonchul Shin, Inyong Choi, Kyogu LeeTarget Speaker Extraction Electroencephalography
Department of Intelligence and Information, Seoul National University, Republic of Korea · Department of Communication Sciences and Disorders, University of Iowa, United States · Interdisciplinary Program in Artificial Intelligence, Seoul National University, Republic of Korea +1
The Watermark Shortcut: How Provenance Marking Sabotages Audio Deepfake Detection
Jun 22, 2026Nicolas M. Müller, Pascal DebusEnvironmental Sound Deepfake Detection Multi-Bit Watermarking
Fraunhofer AISEC, Germany · Resemble AI
When Does a Video-Language Model Stop Watching? Reward Strength Controls the Formation and Reversal of Visual Shortcuts in Multimodal RLVR
Jun 20, 2026Zekun XuReinforcement Learning With Verifiable Reward Video-Language Models
School of Computer Science, The University of Sydney, Sydney, Australia
From Shortcuts to Reasoning: Robust Post-Training of Theory of Mind with Reinforcement Learning
Jun 8, 2026Jike Zhong, Yuxiang Lai, Ming Li +5Theory-Of-Mind Reasoning Reinforcement Fine-Tuning
University of Southern California · 2Emory University · University of Maryland, College Park +4
DynaCF: Mitigating Shortcut Learning in Reward Models via Dynamic Counterfactual Sensitivity
Jun 8, 2026Fengyuan Liu, Yongliang Miao, Zirui He +3Progress Reward Modeling Preference Alignment Learning
The Chinese University of Hong Kong, Shenzhen · New Jersey Institute of Technology · Institute of Computing Technology, CAS
Twelve quick tips for designing AI-driven HPC workflows
Jun 5, 2026Jamie J. AlnasirHigh-Performance Computing Scientific Workflows
Department of Computer Science Royal Holloway University of London Egham, England, UK
Invariant Gradient Alignment for Robust Reasoning Distillation
Jun 3, 2026Zehua Cheng, Wei Dai, Jiahao SunLarge Language Model Training Gradient
University of Oxford, Oxford, UK
Low-Frequency Shortcuts in Texture-Driven Visual Learning
Jun 2, 2026Utku Şirin, Cathy Hou, David Alvarez-Melis +1Graph-Coherent Low-Frequency Ones Feature Learning
Harvard University
Suppressing Forgery-Specific Shortcuts for Generalizable Deepfake Detection
Jun 1, 2026Yihui Wang, Yonghui Yang, Jilong Liu +3Deepfake Detection Forgeries
Hefei University of Technology China · National University of Singapore Singapore
Shortcut to Nowhere: Demystifying Deep Spurious Regression
Jun 1, 2026Guanrong Xu, Jessica Li, Hao Wang +1Logistic Regression Deep Learning
University of California, Los Angeles · Rutgers University
Shortcuts in the Tail: Debiasing via Post-Hoc Spectral Compression of Fine-Tuning Updates
May 29, 2026Edward Sun, Dmitrii TroitskiiModel Fine-Tuning Shortcut Learning
Department of Computer Science, UCLA, Los Angeles, CA, USA · Independent.
The Confidence Shortcut: A Reasoning Failure Mode of Masked Diffusion Models
May 27, 2026Dueun Kim, Albert NoMasked Diffusion Language Models Constrained Decoding
Department of Artificial Intelligence, Yonsei University
Faithfulness as Information Flow: Evaluating and Training Faithful Chain-of-Thought Reasoning
May 22, 2026Jinghan Jia, Joe Benton, Eric EasleyExplanation Faithfulness Faithfulness
†Dept. CSE, Michigan State University · ⋆Anthropic Fellows Program · ‡Anthropic
Learning Spatiotemporal Sensitivity in Video LLMs via Counterfactual Reinforcement Learning
May 21, 2026Dazhao Du, Jian Liu, Jialong Qin +7Video-Language Models Spatio-Temporal Reasoning
Hong Kong University of Science and Technology · Tencent
Learning to Think in Physics: Breaking Shortcut Learning in Scientific Diffusion via Representation Alignment
May 20, 2026Haozhe Jia, Pengyu Yin, Wenshuo Chen +6Physics-Guided Diffusion Partial Differential Equations
The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China · Shandong University, Jinan, China · Data61/CSIRO, Australia +5
SpurAudio: A Benchmark for Studying Shortcut Learning in Few-Shot Audio Classification
May 13, 2026Giries Abu Ayoub, Morad Tukan, Loay MualemFew-Shot Learning Audio Understanding
Independent Researcher · University of Stuttgart, Germany · IMPRS-IS, Germany
Shortcut Solutions Learned by Transformers Impair Continual Compositional Reasoning
May 6, 2026William T. Redman, Erik C. Johnson, Brian RobinsonTransformer Architectures Replay-Based Continual Learning
Johns Hopkins Applied Physics Lab
Reproducing Complex Set-Compositional Information Retrieval
May 5, 2026Vincent Degenhart, Dewi Timman, Arjen P. de Vries +2Retrieval Layer Shortcut Learning
Radboud University · Nijmegen, NL
Deciphering Shortcut Learning from an Evolutionary Game Theory Perspective
May 4, 2026Xiayang Li, Kuo Gai, Shihua ZhangStochastic Gradient Descent Shortcut Learning
State Key Laboratory of Mathematical Sciences Academy of Mathematics and Systems Science School of Mathematical Sciences University of Chinese Academy of Science Beijing, 100049, China · Shanghai Institute for Mathematics and Interdisciplinary Sciences Shanghai, 200433, China

Sep 30, 2026, cs.LGJ/K move · Enter open · S save

Removing Timing Shortcuts Improves Non-Invasive Brain-to-Text

Dulhan Jayalath, Oiwi Parker Jones

Neural Processing Lab (PNPL) Department of Engineering Science, University of Oxford

Neural Recordings Decoding Shortcut Learning

Open paper AskPDF arXiv

We find that major reported improvements in decoding words from non-invasive brain recordings are largely reproducible without any brain data. In the influential work of d'Ascoli et al. (2025), time series of brain activity from subjects perceiving continuous speech are segmented into fixed-length windows starting at each word. A neural network then generates predictions for all of the words in a sentence together. Neighbouring windows partially overlap, implicitly revealing the interval between words. Since these intervals indicate the duration of the words spoken, and different words tend to have different durations - for example, "the" is much shorter than "supercalifragilisticexpialidocious" - the neural network can improve its predictions of words without relying on the underlying brain activity. Consistent with this, the method reaches 22.0% balanced accuracy on synthetic signals containing no brain information, compared with 22.3% on real brain recordings. To prevent the network from learning this shortcut, we make a single, simple change. Instead of jointly encoding all windows in a sentence, we process each independently. As a result, the neural network achieves better performance by learning underlying word-specific information from brain recordings. This makes two existing strategies become much more effective than before. Both aggregating predictions from distinct neural responses to the same word and using a pretrained LLM as a linguistic prior now substantially improve results. On our perceived speech benchmark, this simple recipe (SimpleB2T) achieves a word error rate of 36.6% with five observations per word, approaching past invasive speech decoding performance, albeit under different conditions. The results in this work expose an important shortcut in brain-to-text decoding and show that removing it leads to a simple and considerably more effective strategy.

Momentum

Related topics

Latest papers 65