Concept Erasure

Ask about this topic

Momentum

17 papers in the last four weeks, up 70% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28
View on map

Latest papers 91

All topics
CardsList

  1. Continual Concept Erasure in Diffusion Models by Suppressing Cross-Edit Interference

    Oct 1, 2026Yongliang Wu, Haori Lu, Jinqi Luo +3Concept ErasureText-To-Image Diffusion Models

    University of Illinois Urbana-Champaign · University of Pennsylvania · National University of Singapore

  2. RASteer: Retain-Aware Activation Steering for Concept Erasure in Diffusion Models

    Oct 1, 2026Yongliang Wu, Haori Lu, Yulun Wu +3Concept ErasureText-To-Image Diffusion Models

    University of Illinois Urbana-Champaign · University of Pennsylvania · National University of Singapore

  3. TRACE: Trajectory Return Attribution and Contrastive Erasure for Multi-Turn Safety

    Oct 1, 2026Fengpeng Li, Kemou Li, Qizhou Wang +3Large Language Model SafetyAttack-Success Rate

    PRADA Lab, King Abdullah University of Science and Technology · State Key Laboratory of Internet of Things for Smart City, University of Macau · Imperfect Information Learning Team, RIKEN Center for Advanced Intelligence Project +1

  4. STAGE: Subspace-Targeted Affine Generative Erasure for Text-to-3D Models

    Oct 1, 2026Karol Dziekan, Przemysław Spurek, Dawid Malarz3D Generative ModelsHigh-Fidelity 3D Generation

    Jagiellonian University · IDEAS Research Institute

  5. Faithful Dual-constrained Erasure for Robust LLM Safety Alignment

    Sep 30, 2026Jiaqing Li, Shide Zhou, Zhibo Zhang +3Large Language Model UnlearningLarge Language Model Safety

    Huazhong University of Science and Technology · Hubei University

  6. Weeding Out Bad Seeds: Initial-Noise-Robust Unlearning for Text-to-Image Diffusion Models

    Sep 29, 2026Arian Komaei Koma, Seyed Amir Kasaei, Aida Aryafar +6Text-To-Image Diffusion ModelsDiffusion Models

    Sharif University of Technology · Hong Kong University of Science and Technology

  7. Motion Concept Unlearning in Video Diffusion Models

    Sep 29, 2026Ping Liu, Chi ZhangText-To-Video Diffusion ModelsVideo Diffusion Models

    Computer Science and Engineering University of Nevada, Reno Reno, NV, USA · Department of Mathematics National University of Singapore Singapore

  8. eval-unlearn: Benchmarking unlearning in Text-to-Image Diffusion Models

    Sep 28, 2026Mansi, Nikhil Raghavan, Zixia Huang +4Text-To-Image Diffusion ModelsText-To-Image

    Imperial College London

  9. You Can't Have It Both Ways: Concept Entanglement Limits Diffusion Model Unlearning

    Sep 28, 2026Yian Wang, Ali Ebrahimpour-Boroojeny, Hari Sundaram +1Text-To-Image Diffusion ModelsConcept Erasure

    University of Illinois Urbana-Champaign Urbana, IL, USA

  10. Concept Score Relearning: A Unified Cross-Architecture Attack on Concept Erasure

    Sep 27, 2026Hong Xi Tae, Jiaming Zhang, Wenwen He +2Concept ErasureText-To-Image Diffusion Models

    College of Computing and Data Science, Nanyang Technological University, Singapore

  11. Encoded but Not Decoded: Layer-Localized Evidence for a Three-Level Gap in LLM Syntax

    Sep 24, 2026Zhenyan Lu, He Wang, Xiaohui HuangSyntactic StructureScale Gap

    College of International Studies, National University of Defense Technology, Nanjing, China

  12. Hidden not Deleted: How Networks Suppress Entangled Features

    Sep 23, 2026Akash Samanta, Manish Pratap Singh, Debasis ChaudhuriConcept ErasureEntanglement

    Techno India University Salt Lake, Kolkata, India · DRDO Young Scientist Laboratory - CT Chennai, India

  13. When AI Generates Covariates: Causal Typing and Estimand Drift in Sequential Experiments

    Sep 15, 2026Takes Fujita, Nobutaka HattoriCausal InferencesCovariates

    VRI · Department of Neurology, Juntendo University School of Medicine

  14. Semantic-Aware Neural Video Codec for Error-Resilient Low-Latency Transmission

    Sep 14, 2026Matin Mortaheb, Homa Esfahanizadeh, Jinfeng Du +1Video CompressionFine-Grained Video Understanding

    Nokia Bell Labs, Murray Hill, NJ 07974, USA

  15. GRIN+: Towards Fast Yet Effective Machine Unlearning for Imbalanced Medical Data

    Sep 14, 2026Minghui Huang, Junxiao WangMachine UnlearningImbalanced Classification

    Guangzhou University, China

  16. GRACE: Adaptive Concept Erasure with Geometry-Guided Retention in Diffusion Models

    Sep 14, 2026Qinghui Gong, Yihuai Liang, Yuanlun Xie +3Concept ErasureText-To-Image Diffusion Models

    School of Information Science and Technology, Southwest Jiaotong University, Chengdu 611756, China · School of Electronic Information and Electrical Engineering, Chengdu University, Chengdu, China · Key Laboratory of Intelligent Control and Optimization for Industrial Equipment of Ministry of Education, Dalian University of Technology, Dalian, China +1

  17. MUtE: A Dual Framework for Concept Erasure and Counterfactual Interventions

    Sep 11, 2026Antoine SaillenfestConcept Erasure

    onepoint, 29 rue des Sablons, 75116 Paris (France)

  18. EraseSAE: Surgical Concept Erasure in Text-to-Video Diffusion Models via Sparse Autoencoders

    Sep 3, 2026Xinghao Wang, Dong Li, Wei Yu +5Concept ErasureText-To-Video Diffusion Models

    University of Science and Technology of China, Hefei, China · HiDream.ai Inc. · Anhui Province Key Laboratory of Digital Security, China

  19. Gaussian Core LoRA: Distribution-Aware Dynamic Adaptation for Broad Concept Erasure

    Sep 1, 2026Qinghui Gong, Xunlei Chen, Yu-Xuan Zhang +2Concept ErasureAdversarial Prompts

    Southwest Jiaotong University · University of Electronic Science and Technology of China

  20. PredErase: Training-Free Object-and-Effect Removal with Predictive Latent Guidance

    Sep 1, 2026Waikit Xiu, Qiang Lu, Junbiao Chen +1Video Object RemovalConcept Erasure

    1The University of Hong Kong · 2Sun Yat-sen University

  21. Continual Test-Time Adaptation via Entropy Sensitivity-Guidance in Strict Online Setting

    Aug 30, 2026Chandler Timm C. Doloriel, Yunbei Zhang, Muhammad Salman Siddiqui +4Test-Time AdaptationConcept Erasure

    Faculty of Science and Technology (REALTEK), Norwegian University of Life Sciences (NMBU) · Tulane University

  22. Semantic Steering for Controllable Generation: Tuning-Free Concept Erasure in Multimodal Diffusion Transformers

    Aug 13, 2026Qiao Li, Xiaomeng Fu, Yuanshu Zhao +3Diffusion TransformersConcept Erasure

    Institute of Information Engineering, Chinese Academy of Sciences Beijing, China · School of Cyber Security, University of Chinese Academy of Sciences Beijing, China

  23. Erase but Preserve: Controllable Removal of Copyrighted Animation Characters via Optimized Semantic Anchors

    Aug 13, 2026Qiao Li, Xiaomeng Fu, Wangjia Yu +4Text-To-Image Diffusion ModelsConcept Erasure

    Institute of Information Engineering, Chinese Academy of Sciences, School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China · Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China

  24. Reading the Gate, Not the Interference: Output-Side Interference Measurement Does Not Track Merge Collapse

    Aug 12, 2026Chencheng ZhuCross-Task InterferenceMatched Fp16 Intermediate

    UNSW Sydney

  25. PEAK: Precise and Persistent Concept Erasure via k-Sparse Autoencoders

    Aug 11, 2026Man Jiang, Ouxiang Li, Weibao Xue +4Concept ErasureText-To-Image Diffusion Models

    Hefei University of Technology · University of Science and Technology of China · University of Macau

  26. Iterative Erasure Count Is Not an Affine-Invariant Concept Dimension

    Aug 11, 2026Tingan Jin, Shuhang Dong, Haosong Li +1Intrinsic DimensionalityConcept Erasure

    UCLA · Independent Researcher · Cal Poly Pomona

  27. Did the Grid Erase the Event? EndoClock for Auditing Medical World-Model Pipelines

    Aug 10, 2026Yarin Udi, Tom Sharon-Shahak, Roee Masad +1Medical World ModelClocks

    Diastole Medical R&D

  28. OBLIVION: Workflow-Level Operational Skill Unlearning for Deployed Agents

    Aug 8, 2026Zhengyang Shan, Xu Qian, Jiayun Xin +3SkillsRemediation

    Shandong University

  29. FlowErase-OPD: Multi-Concept Erasure via Anchored On-Policy Distillation in Flow Matching Models

    Aug 7, 2026Yi Sun, Yimin Zhou, Xinhao Zhong +3Concept ErasureText-To-Image Diffusion Models

    Harbin Institute of Technology, Shenzhen · Tsinghua Shenzhen International Graduate School, Tsinghua University · Peng Cheng Laboratory

  30. SCOPE: Entanglement Frontier Escape for Source-Free Class Unlearning

    Aug 3, 2026Junhao Cai, Dohun Kim, Sung Il Choi +4Exact UnlearningConcept Erasure

    Korea University, Seoul, Republic of Korea

  31. QR-Erase: Efficient Subspace-Based Machine Unlearning with Layer Localization

    Aug 2, 2026Tyler Lizzo, Larry HeckMachine UnlearningSubspace

    Georgia Institute of Technology

  32. From Semantics to Readout: Mechanistic Understanding of Audio Tokens after Fine-Tuning for Temporal Audio Grounding

    Jul 28, 2026Yujian Ma, Jinqiu Sang, Ruizhe Li +2Large Audio Language ModelsAudio Tokenizers

    1Shanghai Institute of Artificial Intelligence for Education, East China Normal University, China · School of Computer Science and Technology, East China Normal University, China · School of Computer Science, University of Birmingham, UK +1

  33. To Erase, or Not to Erase: Robust Training-Free Concept Erasure with Preservation aware Adaptive Ranked Subspace Expansion

    Jul 26, 2026Shaswati Saha, Rajasekhar Anguluri, Manas GaurConcept ErasureText-To-Image Diffusion Models

    University of Maryland Baltimore County, USA

  34. Mark, Don't Erase: Token Inoculation for Dual-Use Knowledge in LLMs

    Jul 21, 2026Seunghyun Lee, Dongyoon Han, Sangdoo YunInference-Time DefensePoisoning

    NAVER AI Lab

  35. Stress Testing Concept Erasure with Large Language Model Agents

    Jul 20, 2026Yuyang Xue, Feng Chen, Zhihua Liu +4Concept ErasureStress Testing

    School of Engineering, University of Edinburgh · The University of Manchester · The University of Melbourne

  36. AEC-DS: Adaptive Erasure Coding with PDP-Triggered Reputation and QoS-Aware Migration for Decentralized Storage

    Jul 20, 2026Shuaiwen Li, Weihang Yu, Ke Wang +1Decentralized Autonomous OrganizationModel Auditing

    Zhejiang University Hangzhou, China · Central University of Finance and Economics Beijing, China · Binjiang Institute of Zhejiang University Hangzhou, China

  37. Introspective Attention Modulation for Safe Text-to-Image Generation

    Jul 16, 2026Basim Azam, Hossein Rahmani, Naveed AkhtarText-To-Image Diffusion ModelsText-To-Image

    The University of Melbourne, Australia · Lancaster University, United Kingdom

  38. Uni-AdaVD: Universal Concept Erasure for Visual Generation via Orthogonal Value Decomposition

    Jul 16, 2026Qifan Zhou, Yuan Wang, Yanbin Hao +4Concept ErasureVisual Generation

    School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China · School of Cyber Science and Technology, University of Science and Technology of China, Hefei, China · School of Artificial Intelligence and Data Science, University of Science and Technology of China, Hefei, China +1

  39. AutoAnchor: Stable Diffusion Unlearning Using Cross-Attention as a Manifold Surrogate

    Jul 9, 2026Siyuan Wen, Jiahao Zeng, Ningning DingText-To-Image Diffusion ModelsCross-Attention

    Hong Kong University of Science and Technology (Guangzhou)

  40. TILDE: TILt-based Distributional Erasure for Concept Unlearning

    Jul 7, 2026Naveen George, Naoki Murata, Yuhta Takida +2Text-To-Image Diffusion ModelsConcept Erasure

    Indian Institute of Technology Hyderabad · Sony AI · Sony AI & Sony Group Corporation

  41. Erasing Without Collateral Damage: Precise Concept Removal in Diffusion Models

    Jul 6, 2026Parth Upman, Nishita Jain, Shreyank N GowdaConcept ErasureText-To-Image Diffusion Models

    School of Computer Science, University of Nottingham, Nottingham, NG8 1BB, UK · Department of Computing, Imperial College London, London, SW7 2AZ, UK

  42. MANCE: Manifold Aware Concept Erasure

    Jul 4, 2026Matan Avitan, Yoav Goldberg, Yanai ElazarConcept ErasureManifolds

    Bar-Ilan University · Allen Institute for Artificial Intelligence

  43. LACUNA: A Testbed for Evaluating Localization Precision for LLM Unlearning

    Jul 2, 2026Matteo Boglioni, Thibault Rousset, Siva Reddy +2Large Language Model UnlearningAttacker Large Language Model

    Mila – Quebec Artificial Intelligence Institute · McGill University · McGill-NLP/LACUNA

  44. A Mechanistic View of Authority Hierarchy in LLM Sycophancy

    Jul 1, 2026Emil Joswin, Srujananjali Medicherla, Priyanka Mary MammenSycophancyAuthority

    Independent Research · University of Massachusetts Amherst

  45. Look But Don't Touch with Sparse Autoencoders for Unlearning in Diffusion Models

    Jun 30, 2026Enrico Cassano, Riccardo Renzulli, Rayyan Ahmed +2Diffusion ModelsConcept Erasure

    University of Turin, Computer Science Department, Italy · LTCI, Télécom Paris, Institut Polytechnique de Paris, France

  46. ScaleErasure: Inference-Time Minimal Intervention for Precise Concept Erasure in Next-Scale Autoregressive Image Generation

    Jun 28, 2026Cong Wang, Haiyu Wu, Zhiwei Jiang +4Autoregressive Image GenerationConcept Erasure

    State Key Laboratory for Novel Software Technology, Nanjing University · National University of Singapore

  47. Obliviate: Erasing Concepts from Autoregressive Image Generation Models

    Jun 26, 2026Hossein Shakibania, Jonas Henry Grebe, Tobias Braun +4Autoregressive Image GenerationConcept Erasure

    TU Darmstadt, Germany · Multimodal AI Lab, TU Darmstadt, Germany · Zuse School ELIZA +1

  48. Erase-then-Delta Attention: Decoupling Erase and Write Addresses in Delta-Rule Linear Attention

    Jun 25, 2026Xiao Li, Chengruidong Zhang, Hao Luo +15Kimi Delta AttentionRecurrent Model

    1Qwen Team · 2Nanjing University · 3Zhejiang University

  49. Co-occurring associated retained concepts in Diffusion Unlearning

    Jun 23, 2026Miso Kim, Georu Lee, Yunji Kim +3Concept ErasureChild Sexual Abuse Material

    Dongguk University-Seoul · Chung-Ang University · Korea Institute for Advanced Study

  50. Exposing the Illusion of Erasure in Knowledge Editing for LLMs

    Jun 22, 2026Advik Raj Basani, Anshuman ChhabraMultimodal Knowledge EditingConcept Erasure

    Birla Institute of Technology and Science, Goa · University of South Florida

  51. KVEraser: Learning to Steer KV Cache for Efficient Localized Context Erasing

    Jun 15, 2026Mufei Li, Shikun Liu, Dongqi Fu +5Kv-Cache ManagementKey-Value Cache

    Georgia Institute of Technology · Meta

  52. Post-Hoc Merging is Not Enough: Many-Shot Model Merging with Loss-Gap Balancing

    Jun 15, 2026Kyungjin Im, Miru Kim, Chanin Eom +1Continual Model MergingMulti--Task Learning

    Soongsil University, Republic of Korea · Department of Electrical and Computer Engineering, Sungkyunkwan University, Republic of Korea

  53. SACE: Concept Erasure at the Semantic Singularity in Visual Autoregressive Models

    Jun 14, 2026Siya Yang, Nanxiang Jiang, Zhaoxin Fan +1Visual Autoregressive ModelsConcept Erasure

    1Hefei University of Technology · 2Beihang University

  54. On Defining Erasure Harms for NLP

    Jun 14, 2026Yu Lu Liu, Arnav Goel, Jackie Chi Kit Cheung +3Concept ErasureHarms

    1Johns Hopkins University · 2Carnegie Mellon University · 3Mila – Québec Artificial Intelligence Institute +2

  55. Debiasing Without Protected Attributes: Latent Concept Erasure from Textual Profiles

    Jun 10, 2026Shun Shao, Zheng Zhao, Anna Korhonen +2DebiasingLarge Language Model Bias

    University of Cambridge · University of Edinburgh · University of Groningen +1

  56. TRACER: Token ReAssignment for Concept ERasure in Generative Recommendation

    Jun 5, 2026Ziheng Chen, Jiali Cheng, Zezhong Fan +4Large Language Model UnlearningConcept Erasure

    Stony Brook University · University of Massachusetts Lowell · Columbia University +3

  57. TOKI: A Bitemporal Operator Algebra for Contradiction Resolution in LLM-Agent Persistent Memory

    Jun 4, 2026Ziming WangContradictionConversational Memory

    The Hong Kong University of Science and Technology Hong Kong, Hong Kong SAR

  58. Catastrophic Forgetting as Accessibility Collapse: A Three-Level Framework for Knowledge Persistence in Continual Learning

    Jun 4, 2026Ayushman Trivedi, Bhavika MelwaniCatastrophic ForgettingContinual Learning

    Independent Researchers

  59. The Generator-Eraser Paradox: Community Guidelines for Responsible LLM-Assisted Dialect Resource Creation

    Jun 4, 2026Wajdi ZaghouaniDialectsLinguistics

    Northwestern University in Qatar

  60. Short paper: Models in the dark -- Rectification and erasure under GDPR in ML supply chains

    Jun 4, 2026Henrik Graßhoff, Malte Hansen, Meiko Jensen +1Trustworthy Artificial IntelligenceSupply Chain Optimization

    Karlstad University, Karlstad, Sweden