Suppression

Ask about this topic

Momentum

5 papers in the last four weeks, down 17% on the four weeks before. 0.1% of all new papers.

Jul 6Week of Sep 21
View on map

Latest papers 65

All topics
CardsList

  1. The Safety Operator: Modulating the Expression of Safety Instructions via Spectral Optimization

    Sep 29, 2026Benoit Dherin, Michael Munn, Xavier Gonzalvo +14Safety ClaimsInstruction Tuning

    Google Research · Cambridge University · Google DeepMind +2

  2. Trigger Sound Suppression for Misophonia

    Sep 28, 2026Vaishnavi Vidyasagar, Jasmine Zhang, Mahima Uliyar +4SuppressionHear

    University of Washington · Duke Center for Misophonia and Emotion Regulation

  3. TSGate: Timestep-Aware Gated Attention for Diffusion Transformers

    Sep 28, 2026Boyu Zhang, Yifan Liu, Shuxia Lin +3Diffusion TransformersVideo Generation

    Alibaba Token Hub, Alibaba Group · Southeast University

  4. Rethinking Token Reweighting for SFT: Suppress, Reverse, and Extrapolate Learned Features

    Sep 27, 2026Cunchun Li, Haonan He, Yifan Gao +4Supervised FinetuningReweighting

    Shanghai AI Laboratory · University of Science and Technology of China · Fudan University +2

  5. TAM-Chain: Multi-Scale Thyroid Cytology Classification via Absorbing Markov Chains and Shannon Entropy Uncertainty Quantification for False-Negative Suppression and Domain-Shift Adaptation

    Sep 23, 2026Hai Pham NgocCancer DetectionFalse-Negative Rate

    Faculty of Mathematics, Mechanics and Informatics, VNU University of Science

  6. Enhanced Knowledge Distillation for Detection Transformer via Teacher Prediction Refinement

    Sep 17, 2026Yitong Xing, Yuhao Cheng, Yanping Li +1Rt-DetrDetection Transformer

    School of Computer Science, Shanghai Jiao Tong University, Shanghai 200240, China

  7. ADGNet: Asymmetric Dual-text Guided Network for Infrared Small Target Detection

    Sep 1, 2026Tongtong Wang, Mingzhu Xu, Chenglong Yu +3Infrared Small Target DetectionInfrared

    Shandong University · Jinan, China · Harbin Institute of Technology, Shenzhen +1

  8. Slow to See, Slow to Suppress: Understanding the Effects of Modality in Context-Memory Conflicts

    Aug 31, 2026Athulith Paraselli, Etha Tianze Hua, Ellie PavlickModalitiesFactual Recall

    Brown University

  9. Located but Not Releasable: Silent Gate Inversion and Bounded Linear Release

    Aug 12, 2026Xining XunReleaseSuppression

    Tsingjiao Information Science (Beijing) Co., Ltd.

  10. Is SwiGLU's Open Positive Tail Necessary? Evidence from Closed-Tail Gating with MemGLU

    Aug 7, 2026Yuting Ge, Pengju Yang, Mingkai NieSuppressionClosure

    Department of Electrical Engineering City University of Hong Kong · Beihang University · National University of Singapore

  11. Are Visual Place Recognition Models Recognizing Places or Conditions? Distractor-Augmented Evaluation and Condition Suppression

    Aug 7, 2026Beomsu Kim, Minwoo Jung, Giseop KimVisual Place RecognitionSimilarity and Metrics

    Department of Robotics and Mechatronics Engineering, DGIST, Daegu, Republic of Korea · Department of Mechanical Engineering, Seoul National University, Seoul, Republic of Korea

  12. Suppress and Diversify: Refining Robust Pathways for Corruption Robustness

    Aug 7, 2026Jiangang Yang, Wenhui Shi, Xiaoran Xu +4Robustness VerificationAdversarial Corruption

    Institute of Microelectronics, Chinese Academy of Sciences, Beijing, China · University of Chinese Science, Beijing, China

  13. Suppression Sticks, Locality Is Fragile: A Closed-Loop Target-and-Control Audit of Task-Vector Negation in VLA Policies

    Aug 5, 2026Shaoguang Wang, Weiyu Guo, Rushi Dai +3Closed LoopSuppression

    The Hong Kong University of Science and Technology (Guangzhou) · AI2 Robotics · The Hong Kong University of Science and Technology

  14. When Refusal Looks Safe: The Refusal-Cue Shortcut in Safety Guard Models

    Aug 4, 2026Yu Feng, Chunting Zang, Chen Shen +4RefusalsSuppression

    The University of Sydney · Alibaba Group · Jilin University +1

  15. DRONEAUDIONET: Noise Suppression for Drone Audition-based Search and Rescue

    Aug 1, 2026Chitralekha Gupta, Soundarya Ramesh, Yifei Luo +1Absolute Noise-To-Clean MappingAutonomous Drones

    School of Computing, National University of Singapore

  16. Would You Walk to the Car Wash? Revealing the Salience Bias of Large Language Models in Commonsense Reasoning

    Jul 30, 2026Zheng Wu, Chenhao Xue, Shijie Zheng +3LLM Reasoning StrategiesTask Framing

    School of Computer Science, Shanghai Jiao Tong University · ByteDance Inc

  17. Minimizing Targeted Activations: Input-Only Suppression of Evaluation-Awareness Latents in Large Language Models

    Jul 28, 2026Deepanshu Mody, Samarth Agarwal, Utkarsh Mittal +1Model ActivationsLarge Language Model Safety

    Center for Data Science, New York University

  18. LU-500: A Logo Benchmark for Concept Unlearning

    Jul 27, 2026Keyu Li, Jin Gao, Jialing Zhang +1Visual RepresentationsSuppression

    Shanghai Jiao Tong University Shanghai, China

  19. The Gate Always Closes: On Injecting Auxiliary Signals into Frozen Vision-Language Models

    Jul 25, 2026Moshiur Farazi, Sameera Ramasinghe, Bekir Sait Ciftler +2Frozen Vision-Language ModelsSuppression

    University of Doha for Science and Technology, Doha, Qatar · Pluralis Research, Australia · North South University, Dhaka, Bangladesh

  20. What Models Express, Suppress, and Resist: Auditing Open-Weight LLMs with Persona Vectors

    Jul 14, 2026Winston Zeng, Ali Emami, Jinho ChoiPersonalityDesiderata

    Emory University

  21. Statistical Non-linear Reconstruction Loss for Image Anomaly Detection

    Jul 14, 2026Nguyen Minh Tri, Hoang Khuong Duy, Huynh Cong Viet NguOutliersSuppression

    AIC-Lab, FPT University

  22. HPG-Diff: Hierarchical physics-guided diffusion with differentiable connectivity constraints for topology optimization

    Jul 8, 2026Jinbo Yang, Mingyue Yuan, Boyuan Zhang +2Topology OptimizationPhysics-Guided Diffusion

    School of Mechanical Engineering, Beijing Institute of Technology, Beijing, 100081, China · Computer Science and Engineering, University of New South Wales, Sydney, 2052, Australia · College of Intelligence and Computing, Tianjin University, Tianjin, 300072, China +1

  23. Learning to Suppress SPAD-based LiDAR Flare

    Jul 3, 2026Xuanya Zhu, Linghao ShenSingle-Photon Avalanche DiodeSuppression

    Centre for Vision, Speech and Signal Processing, University of Surrey, UK · Advanced Technology Center, Sony (China) Ltd., China

  24. LASER: A Corrective Lens for LVLMs via Visual Attention Preservation and Sink Suppression

    Jul 2, 2026Bowen Yuan, Zijian Wang, Yadan Luo +2Recent Vision-Language ModelsLens

    The University of Queensland

  25. Early Cue Precision Shapes Visual Shortcut Learning in Controlled Cue-Manipulation Benchmarks

    Jun 29, 2026Chanho Park, Woochan Lee, Janyeong Oh +4TextureSuppression

    Gwangju Institute of Science and Technology, Gwangju, Republic of Korea

  26. Constraint Tax in Open-Weight LLMs: An Empirical Study of Tool Calling Suppression Under Structured Output Constraints

    Jun 24, 2026Fangzheng Li, Aimin Zhang, Chen LvTool InvocationCall

    1Focus AI Center, Focus Technology Co., Ltd. · 2Nanjing University of Science and Technology

  27. Cage-based Texture Transfer with Geometric Filtering

    Jun 23, 2026Rose Mei Zhou, Lynnette Hui Xian Ng, Adrian Xuan Wei Lim +2TexturePhotorealistic Style Transfer

    Roblox, USA · CMU, USA

  28. When Helpfulness Overrides Causal Caution: Context-Dependent Suppression and Recovery in LLMs

    Jun 23, 2026Hiroshi OkumuraLarge Language Models FailLLM Reasoning Strategies

    Mitsubishi Research Institute, Inc. · Kobe University

  29. Selective Capability Unlearning in End-to-End Spoken Language Understanding

    Jun 23, 2026Akanksha Singh, Vinod Kumar KurmiSpeech Language ModelsSuppression

    Indian Institute of Science Education and Research Bhopal, India

  30. Evaluation of EEG Foundation Models for Event-Based Burst-Suppression Detection in ICU

    Jun 18, 2026Elisa Vasta, Thorir Mar Ingolfsson, Andrea Cossettini +4Electroencephalography Foundation ModelsElectroencephalography

    Neurocritical Care Unit, Institute for Intensive Care Medicine and Department of Neurosurgery, University Hospital Zürich and University of Zürich, Zürich, Switzerland · Integrated Systems Laboratory, ETH Zürich, Zürich, Switzerland · DEI, University of Bologna, Bologna, Italy

  31. SAE Interventions are Unreliable: Post-Intervention Recovery of Suppressed Behavior

    Jun 16, 2026Mingyue Cui, Linghui Shen, Xingyi YangSparse Autoencoder FeaturesLatent Feature Interventions

    The Hong Kong Polytechnic University

  32. Budget-Aware Adaptive Adversarial Patches for Black-Box Object Detection

    Jun 16, 2026Pedram MohajerAnsari, Amir Salarpour, David Fernandez +1Black-Box Adversarial AttacksObject Detection

    School of Computing, Clemson University, USA

  33. When to Write and When to Suppress: Route-Specialized Dual Adapters for Memory-Assisted Knowledge Editing

    Jun 12, 2026Baijia Zhang, Yining HuangMultimodal Knowledge EditingPeak Memory

    Xinjiang University · Meta Emergence Laboratory

  34. Spectro-Temporal Interference Confounds Phase Encoding in Spatial Audio Foundation Models

    Jun 12, 2026Yuxuan Chen, Haoyuan Yu, Peize HeSound Source LocalizationSpatial Audio

    The Chinese University of Hong Kong, Shenzhen · Jilin University · Hunan University +1

  35. Null-Space Constrained Low-Rank Adaptation for Response-Specified Large Language Model Unlearning

    Jun 9, 2026Bocheng Ju, Jianhua Wang, Chengliang Liu +1Large Language Model UnlearningExact Unlearning

    Beijing Key Laboratory of Security and Privacy in Intelligent Transportation, Beijing Jiaotong University, P.R.China · College of Computer Science and Technology, Taiyuan University of Technology, Taiyuan, China, 030024 · Institute of Computing Technologies, China Academy of Railway Sciences Corporation Limited, Beijing 100081, China

  36. The Injection Paradox: Brand-Level Suppression in Safety-Trained LLM Recommendations via RAG Context Injection

    Jun 8, 2026Hyunseok PaengLarge Language Model SafetyRetrieval-Augmented Generation Pipelines

    Independent Researcher.

  37. Multilingual Sentiment Aware Text Summarization A Reinforcement Learning Approach for Consistency Maintenance

    Jun 8, 2026Mikhail Krasitskii, Alexander Gelbukh, Olga Kolesnikova +1Large Language Model AlignmentSentiment

    Instituto Politécnico Nacional (IPN), Centro de Investigación en Computación (CIC), Mexico City, Mexico

  38. DeepMine-Mamba: Mitigating Information Dilution in Mamba-Based State Space Models for Document Image Binarization

    Jun 7, 2026Sheng-Wei Chan, Yung-Che Wang, Hsin-Jui Pan +2BinarizationMamba

    Department of Electrical and Computer Engineering, Tamkang University, No.151, Yingzhuan Rd., Tamsui Dist., New Taipei City, 251301, Taiwan

  39. Delayed Repression and Emergent Instability in Adaptive Multi-Agent Systems

    May 28, 2026Igor ItkinModel-Based Multi-Agent SystemsQ-Learning

    Independent Researcher, Tel Aviv, Israel

  40. Orthogonal Negative Guidance in Attention Feature Space for Text-to-Image Generation

    May 28, 2026Jungmin Ko, Jungwon Park, Jimyeong Kim +3SuppressionNegative Results

    Interdisciplinary Program in Artificial Intelligence, Seoul National University · Research Institute for Convergence Science, Seoul National University · Daegu Gyeongbuk Institute of Science and Technology +3

  41. The Attentional White Bear Effect in Transformer Language Models

    May 27, 2026Rebecca Ramnauth, Brian ScassellatiSuppressionTransformer Architectures

    Yale University New Haven, CT, USA

  42. Examining Agents' Bias Amplification versus Suppression in Multi-Agent Systems

    May 27, 2026Zejian Eric Wu, Zhongyi Jiang, Yuan Zhuang +1Algorithmic FairnessPosition Bias

    Oregon State University · Independent Researcher · Amazon +1

  43. Beyond Surrogate Gradients: Fully Differentiable Token Pruning for Vision-Language Models

    May 27, 2026Landi He, Mingde Yao, Shawn Young +1Visual Token PruningRecent Vision-Language Models

    Shenzhen University of Advanced Technology · CUHK MMLab, CPII under InnoHK

  44. MIRA: A Bilingual Benchmark for Medical Information Response Audit

    May 27, 2026Mengyu Xu, Qiaoxin Yang, Qianqian Wang +3Multilingual Healthcare Q&AMultilingual Benchmark

    The University of Chicago · The Chinese University of Hong Kong, Shenzhen · Jinzhou Medical University +3

  45. Where Does Toxicity Live? Mechanistic Localization and Targeted Suppression in Language Models

    May 27, 2026Himanshu Beniwal, Mayank SinghToxicityLarge Language Model Safety

    Indian Institute of Technology Gandhinagar

  46. Priors Persist Through Suppression: A Stroop Paradigm for Lexical Override

    May 25, 2026Han-yu WangPrimingTextual Priors

    The University of Hong Kong

  47. Localization then Neutralization: Gradient-guided Token Suppression against Visual Prompt Injection Attack

    May 24, 2026Dongpeng Zhang, Ke Ma, Yangbangyan Jiang +4Jailbreak AttacksSuppression

    School of Advanced Interdisciplinary Sciences, UCAS · School of Electronic, Electrical and Communication Engineering, UCAS · School of Computer Science and Technology, UCAS +4

  48. Universal Boosts, Specific Suppressors: Sparse Autoencoder Steering of Medical Vision-Language Models

    May 24, 2026Farhad Nooralahzadeh, Benjamin Gundersen, Nicolas Deperrois +7Medical Vision-Language ModelsImproving Sparse Autoencoders

    University of Zurich and University Hospital of Zurich, Switzerland · Zurich University of Applied Sciences, Switzerland · Kobe University, Japan +3

  49. The ASE-LSE Disagreement Landscape: An End-to-End Characterisation of Extremes and Structural Drivers

    May 21, 2026Minh Triet Pham, Ian GallagherGraph Edge SparsificationHeterogeneity

    School of Mathematics and Statistics The University of Melbourne, Australia

  50. Concept-Guided Noisy Negative Suppression for Zero-Shot Classification and Grounding of Chest X-Ray Findings

    May 19, 2026Chenyu Lian, Hong-Yu Zhou, Chun-Ka Wong +1Chest X-RayAdaptive Boundary Suppression

    The Center for Smart Health, School of Nursing, the Hong Kong Polytechnic University, Hong Kong, China · Research Institute for Smart Ageing, the Hong Kong Polytechnic University,2026 Hong Kong, China · School of Biomedical Engineering, Tsinghua Medicine, Tsinghua University, Beijing, China +1

  51. It Takes Two: Complementary Self-Distillation for Contextual Integrity in LLMs

    May 18, 2026Sangwoo Park, Woongyeong Yeo, Seanie Lee +6Privacy-Utility Trade-OffsSelf-Distillation Framework

    KAIST

  52. AdaEraser: Training-Free Object Removal via Adaptive Attention Suppression

    May 15, 2026Dingming LiuVideo Object RemovalRemoval

    School of Computer Science, Peking University.

  53. From raw data to neutrino candidates: a neural-network pipeline for Baikal-GVD

    May 11, 2026A. Matseiko, G. Plotnikov, I. KharukSuppression

    Institute for Nuclear Research of the Russian Academy of Sciences · Moscow Institute of Physics and Technology · Institute for Nuclear Research of the Russian Academy of Sciences, 60th October Anniversary Prospect 7a, Moscow, 117312, Russia +1

  54. NCO: A Versatile Plug-in for Handling Negative Constraints in Decoding

    May 11, 2026Hyundong Jin, Yo-Sub HanConstrained DecodingLarge Language Model Generation

    Yonsei University Seoul, Republic of Korea

  55. UNSEEN: A Cross-Stack LLM Unlearning Defense against AR-LLM Social Engineering Attacks

    Apr 25, 2026Tianlong Yu, Yang Yang, Xiao Luo +6Attacker Large Language ModelLLM Defense Mechanisms

    Hubei University, Wuhan, China · University of Southern California, Los Angeles, USA · Huazhong University of Science and Technology, Wuhan, China

  56. SpanVLA: Efficient Action Bridging and Learning from Negative-Recovery Samples for Vision-Language-Action Model

    Apr 21, 2026Zewei Zhou, Ruining Yang, Xuewei +8Diffusion-Based Vision-Language-ActionsBridging Language

    Tony · University of California, Los Angeles, USA · Motional, USA +1

  57. Towards Scalable Lifelong Knowledge Editing with Selective Knowledge Suppression

    Apr 21, 2026Dahyun Jung, Jaewook Lee, Heuiseok LimMultimodal Knowledge EditingEdit

    Department of Computer Science and Engineering, Korea University

  58. Co-Located Tests, Better AI Code: How Test Syntax Structure Affects Foundation Model Code Generation

    Apr 20, 2026Éric JacopinCode GenerationSyntax

    Cosmic AI

  59. Suppression Is Not Forgetting: Residual Recoverability in Visual Concept Unlearning for VLMs

    Apr 3, 2026Zhangyun Tan, Zeliang Zhang, Jiani Liu +4Large Language Model UnlearningSuppression

    University of Rochester

  60. An Interpretable, Controllable Time-Varying IIR Denoiser for On-Device Assistive Hearing

    Mar 3, 2026Riccardo Rota, Kiril Ratmanski, Jozef Coldenhoff +1Speech EnhancementNeural Audio

    Logitech Europe S.A., Switzerland · EPFL ( ´Ecole Polytechnique F´ed´erale de Lausanne), Switzerland