Forgetting

Follow this topic Ask about this topic

Momentum

19 papers in the last four weeks, up 217% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 123

All topics

SIEVE: Selective attention-value Suppression for Vision-Language Models Unlearning
Oct 1, 2026Si Qi Goh, Cap Dang Xuan Kiet, Tat-Jen Cham +1Exact Unlearning Forgetting
Digital Trust Centre, Nanyang Technological University, Singapore · College of Computing and Data Science, Nanyang Technological University, Singapore
Replay on Demand: An Emergent Curriculum for Balancing Adaptation and Forgetting in Continued Pretraining
Sep 30, 2026Lukas Thede, Shengzhuang Chen, Stefan Winzeck +3Replay Pretraining
University of Tübingen, Tübingen AI Center · Helmholtz Munich · Munich Center for Machine Learning (MCML) +3
Learning Under Forgetting: Statistical Support-Selective Retention in Stochastic Training Dynamics
Sep 30, 2026Fujie Gao, Zuyue Zhang, Gang SunDense Associative Memory Synaptic Plasticity
Restoring without Forgetting: Filter-Level Continual Image Restoration via Parameter-Space Integrated Gradients
Sep 29, 2026Xin Feng, Jin Zhao, Yizhen Zhang +3Image Restoration Catastrophic Forgetting
School of Informatics, University of Edinburgh · Baidu Inc. · Tsinghua University +1
Normative Loss Landscape Navigation: A Trajectory-Based Approach to Mitigating Forgetting in Incremental Learning
Sep 28, 2026Isabelle Aguilar, Zayn Andre Zainal, Luis Fernando Herbozo Contreras +2Class-Incremental Learning Continual Learning
UNBIND: UNlearning By INference-time Directional Steering for Code LLMs
Sep 28, 2026Zhengyang Shan, Jiayun Xin, Yanjun Lin +7Large Language Model Unlearning Exact Unlearning
Department of Computer Science and Technology Shandong University Qingdao, China
TULIP: Targeted LLM Unlearning at Layers Identified Per-Input
Sep 28, 2026Yejin Kim, William F. Shen, Seokwon Jung +2Large Language Model Unlearning Hidden States
Korea Advanced Institute of Science & Technology (KAIST) · University of Cambridge · Sookmyung Women’s University
Making LLMs Truly Forget: Deep Unlearning by Searching, Selecting, and Severing Knowledge Paths
Sep 28, 2026Jialu Wang, Peizhi Niu, Haoteng Yin +3Large Language Model Unlearning Forgetting
Tongji University · University of Illinois Urbana-Champaign · Purdue University +1
Learning Dynamics of Continual Learning: A Unified View of Data Attribution, Forgetting, and Plasticity Loss
Sep 27, 2026Yi Ren, Wenlong Deng, Guanzhe Hong +2Continual Learning Learning Dynamics
OATML · University of Oxford · UBC +1
ManiEdit: Sequential Unstructured Knowledge Editing for Language Models from a Manifold Perspective
Sep 27, 2026Rui Liu, Chenheng Zhang, Haoxuan Li +1Multimodal Knowledge Editing Edit
State Key Lab of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University · Institute for Artificial Intelligence, Peking University
Forget who you Forgot: Speaker Unlearning to Prevent Re-Identification in Zero-Shot Text-to-Speech
Sep 23, 2026Hyoeun Kim, Yujun Lee, Kyuhong ShimFlow-Matching Text-To-Speech Speaker
Sungkyunkwan University, Republic of Korea
Damnatio Memoriae: Adversarially and Selectively Forgetting Identities in the Embedding Space of Face Recognition Models
Sep 22, 2026Ünsal Öztürk, Vedrana Krivokuća Hahn, Sushil Bhattacharjee +1Face Recognition Model Catastrophic Forgetting
Idiap Research Institute, Martigny, Switzerland · UNIL, Lausanne, Switzerland
GUARD: Natural Forgetting in Large Reasoning Models via Guided Answer-Reasoning Distillation
Sep 18, 2026Zeyu Yan, Guanghao Zhou, Minghui Qiu +2Large Language Model Unlearning Large Reasoning Models
East China Normal University, Shanghai, China · Unaffiliated
Test-Time Unlearning via Sparse Autoencoder
Sep 14, 2026Pingzhi Li, Jinhao Duan, Vaishnav Tadiparthi +6Forgetting Attacker Large Language Model
University of North Carolina at Chapel Hill · 2Honda Research Institute · 3Michigan State University
Investigating catastrophic forgetting in sound event classification
Sep 12, 2026Riccardo Casciotti, Annamaria MesarosClass-Incremental Learning Catastrophic Forgetting
Signal Processing Research Center Tampere University Tampere, Finland
Forgetting Only What Matters: Layer-Selective Unlearning toward Robust LLMs
Sep 9, 2026Ravi Ranjan, Olivera Kotevska, Agoritsa PolyzouLarge Language Model Unlearning Large Language Model Quantization
Florida International University (FIU), Miami, FL, USA · Oak Ridge National Laboratory (ORNL), Oak Ridge, TN, USA
What Should an Agent Forget? Separating What Is Stored from What Is Used
Sep 9, 2026Yuhang Li, Yuchen LiConversational Memory Forgetting
East China Normal University Shanghai, China
What Eviction Destroys: A Restore-Counterfactual Audit of Forgetting in Agent Memory
Sep 8, 2026Chen ShenEviction Forgetting
Megagon Labs
Popular Knowledge Propagates More Errors in LLM Knowledge Updating
Sep 8, 2026Yuji Zhang, Weibing Wang, Cheng Qian +5Facts Forgetting
University of Illinois Urbana-Champaign · City University of New York · Massachusetts Institute of Technology +1
Confess What You Know: Forget-Set Misalignment with Model Knowledge in LLM Unlearning
Sep 1, 2026Miso Kim, Georu Lee, Seungwon Jeong +1Large Language Model Unlearning Forgetting
Dongguk University-Seoul
Where Identity Lives: Localized, Retain-Free Identity Unlearning in Multimodal Large Language Models
Aug 31, 2026Kangwook Ko, Jaehyuk Jang, Wonjun Lee +2Unlearning Method Multimodal Large Language Models
KAIST
Forget or Fine-tune? A Comparative Study of Machine Unlearning Strategies for Noisy Label Correction
Aug 30, 2026João L. P. Santana, Filipe R. CordeiroNoisy Labels Machine Unlearning
Department of Computing Universidade Federal Rural de Pernambuco, Brazil
Beyond Forgetting: Diagnosing and Harnessing Shared Reasoning in Continual RLVR
Aug 19, 2026Lirui Luo, Guoxi Zhang, Hongming Xu +3Reinforcement Learning With Verifiable Reward Icr-Rl
State Key Lab of General AI, School of Intelligence Science and Technology, Peking University · State Key Laboratory of General Artificial Intelligence, BIGAI · Beijing Institute of Technology +1
What to Preserve, Where to Adapt: A Depth-Wise Analysis of Forgetting in Continual Gynecological Image Segmentation
Aug 13, 2026Amal Saqib, Tausifa Jan Saleem, Numan Saeed +1Catastrophic Forgetting Continual Learning
Mohamed bin Zayed University of Artificial Intelligence (MBZUAI), Abu Dhabi, UAE
Uniform Herding: Exemplar Replay with Representation Refresh
Aug 13, 2026Krishna SubediRetraining Replay
Neryva
Catastrophic Forgetting in Continual Reinforcement Learning
Aug 9, 2026Emma GrahamCatastrophic Forgetting Forgetting
UCL · Machine Learning MSc · [cs.LG]
Stockmark-Nemotron-3-Nano-Omni-JapanDocReader: Structured Document Parsing via Capability Injection and Forgetting Control
Aug 7, 2026Shi Chen, Hayato Aida, Makoto Morinaga +2Document Parsing Multimodal Documents
Stockmark Inc.
STAIL: Semantic Text-Anchored Incremental Learning for Medical Imaging via Large Language Models
Aug 6, 2026Songpan Gao, Yajie Zhang, Guanxing Chen +9Medical Images Class-Incremental Learning
Remember-R1: Mitigating Long-Context Visual Forgetting through Reinforcement Learning
Aug 2, 2026Jianmin Chen, Jiaqi Tang, Wei Wei +9Latent Visual Reasoning Visual Memory
Hong Kong University of Science and Technology Hong Kong, China · Northwestern Polytechnical University Xi’an, China · Zhejiang University Hangzhou, China
Lethe: How Hard Is It to Forget? A Benchmark for Federated Unlearning in Medical Imaging
Aug 2, 2026Shengchao Chen, Ting ShuMedical Imaging Forgetting
University of Technology Sydney · Shenzhen University
Toward Fine-Grained Forgetting:Attribute Unlearning for Multimodal Large Language Models
Aug 2, 2026Junkai Lin, Junkai Chen, Siqi Hou +5Large Language Model Unlearning Multimodal Large Language Models
Institute of Automation, Chinese Academy of Sciences · The Chinese University of Hong Kong · The Australian National University +3
When Unlearning Fails: Reliable Data Deletion under Post-Training in Agent Networks
Jul 30, 2026Zihao Ding, Jun Huang, Liang DongUnlearning Method Federated Learning
Electrical Engr & Computer Science · South Dakota State University · Brookings, USA +3
The Art of Not Forgetting A Local Learning Architecture for Continual Learning
Jul 29, 2026Ashmith Atmuri, Yashaswini Rao BhogarajulaCatastrophic Forgetting Replay-Based Continual Learning
Arkadhi Research
ForgetBench: Benchmarking Forgetting Dynamics of Long-Term Parametric Memory in Language Models
Jul 29, 2026Ruxi Gu, Zhenliang Zhang, Wei WangLarge Language Model Memory Catastrophic Forgetting
Department of Automation, University of Science and Technology of China, Hefei, China · State Key Laboratory of General Artificial Intelligence, BIGAI, Beijing, China · School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, China.
Not Forgotten: Implementation and Evaluation of a Personalized Episodic Memory for the Humanoid Robot Head Kim
Jul 27, 2026Steve Aschenbrenner, Marcel Heisler, Thomas Sievers +1Episodic Memory Human-Robot Interaction
Stuttgart Media University, Germany · University of Lübeck
The World Model Remembers, the Actor Forgets: Dream Rehearsal for Continual Model-Based RL
Jul 22, 2026Gurp NijjerModel-Based Reinforcement Learning Latent World Models
Quantegra Research, Canada
Code Division Modulation Layers Against Forgetting and Inference in Continual Gait Identification
Jul 21, 2026Simone MilaniReplay-Based Continual Learning Continual Learning
Department of Information Engineering, University of Padova, Padova, Italy
Traceback Translators Against Forgetting in Continual Fake Speech Detection
Jul 14, 2026Enrico Gottardis, Mattia Tamiazzo, Simone MilaniAudio Deepfake Detection Forgetting
Department of Information Engineering · University of Padova · Padova, Italy
Forgetful Attention: A Trainable Support-Vector Memory with Certified Selection and Exact Unlearning
Jul 13, 2026Vishwajith RameshLinear Attention Forgetting
Vy Labs, Inc.
Forgetting Our Way to Shared Meaning: Effects of Forgetting on Conceptual Alignment in a Non-Partnership Coordination Game
Jul 13, 2026Landon Liu, Mary Kelly, Alan TsangEmergence Forgetting
Department of Philosophy, Carnegie Mellon University · Department of Cognitive Science, Carleton University · Department of Computer Science, Carleton University
Creativity, honesty and designed forgetting emerge in small hyperbolic language models
Jul 10, 2026Kwan Soo Shin, In Seok Kang, Yunkyung MinSmall Large Language Models Creativity
PolymathMinds Lab, Seoul, Republic of Korea. · Department of Chemical Engineering, POSTECH, Pohang, and aSSIST University, Seoul, Republic of Korea. · Korean Educational Development Institute, Jincheon, Republic of Korea.
Forget Narrowly, Retain Broadly: Unlearning as an Asymmetric Generalization Problem
Jul 10, 2026Amit Peleg, Naman Deep Singh, Naama Pearl +2Large Language Model Unlearning Forgetting
Tübingen AI Center, University of Tübingen
Denser $\neq$ Better: Limits of On-Policy Self-Distillation for Continual Post-Training
Jul 2, 2026Meng Wang, Haohan Zhao, Wenzhuo Liu +7Unsupervised On-Policy Self-Distillation Replay-Based Continual Learning
Centre for Artificial Intelligence and Robotics, HKISI, CAS · Institute of Automation, CAS · University of Chinese Academy of Sciences +1
LASER: A Corrective Lens for LVLMs via Visual Attention Preservation and Sink Suppression
Jul 2, 2026Bowen Yuan, Zijian Wang, Yadan Luo +2Recent Vision-Language Models Lens
The University of Queensland
Auditing Forgetting in Limited Memory Language Models
Jul 1, 2026Arya Raeesi, Hanna RoedLarge Language Model Unlearning Large Language Model Memory
University of California, Berkeley, Berkeley, California, United States of America.
Neural Subspace Reallocation: Continual Learning as Retrieval-Based Subspace Memory Management
Jun 29, 2026Byeong Hoon YoonReplay-Based Continual Learning Continual Learning
Independent Researcher
Forget, Anticipate and Adapt: Test Time Training for Long Videos
Jun 25, 2026Rajat Modi, Sebastian Noel, Xin Liang +1Test-Time Training Video Temporal Grounding
Institute of Artificial Intelligence, University of Central Florida
Natural Ungrokking: Asymmetric Control of Which Rules Survive Pretraining
Jun 24, 2026Juliana Li, Diya SreedharReverse Pretraining
Harvard University, Cambridge, MA, USA.
Erased, but Not Gone: Output Forgetting Is Not True Forgetting
Jun 23, 2026Teresa Pui Yee Yong, Win Kent Ong, Chee Seng ChanForgetting Catastrophic Forgetting
Universiti Malaya, Kuala Lumpur, Malaysia · VinUniversity, Hanoi, Vietnam
Forget Without Compromise: Nexus Sampling for Streaming KV-Cache Eviction Under Fixed Budgets
Jun 22, 2026Duc Duong, Hoang Anh Duy Le, Jianwen Xie +2Key-Value Cache Eviction Forgetting
Department of Computer Science, Grinnell College · Department of Computer Science, Rice University · Lambda, Inc +1
Attention-Spectrum Regularization for Replay-Free Continual Multimodal LLMs
Jun 22, 2026Chuangxin Zhao, Canran Xiao, Siyuan Ma +5Multimodal Large Language Models Cross-Modal Attention
The Hong Kong University of Science and Technology (Guangzhou) · Sun Yat-sen University · Nanyang Technological University +2
Sparsity, Superposition, and Forgetting: A Mechanistic Study of Representation Retention in Continual Learning
Jun 18, 2026Jan Wasilewski, Jędrzej Kozal, Michał Woźniak +1Forgetting Continual Learning
Rochester Institute of Technology · Rochester NY, USA · Wrocław University of Science and Technology +1
To forget is to preserve: Machine Unlearning for 3D medical image segmentation
Jun 15, 2026Nitesh Kumar Singh, Akhilesh Singh, Arjun AroraMachine Unlearning Exact Unlearning
School of Computer Science UPES, University of Tomorrow Dehradun, India.
Auditing Machine Unlearning: A Systematic Research on Whether Models Truly Forget
Jun 15, 2026Dayong Ye, Tianqing Zhu, Ruiding Huang +5Machine Unlearning Unlearning Method
Control-Plane Placement Shapes Forgetting: An Architectural Study of Agent Memory Across Thirteen System Configurations
Jun 14, 2026Dongxu YangForgetting Deletion
DeepLethe
InstantForget: Update-Free Backdoor Unlearning with Inference-Time Feature Reset
Jun 14, 2026Zhenyu YuClean Label Backdoor Attack Inference-Time Defense
College of Computer Science and Artificial Intelligence Fudan University
When the Same Musical Knowledge Forgets Differently: A Clean Probe of Pathway-Dependent Forgetting
Jun 13, 2026Yu Liu, Zhiwei Yang, Wenxiao Zhang +8Forgetting Instrument
Institute of Information Engineering, CAS · School of Cyber Security, UCAS · The University of Western Australia +1
ForceForget: Reinforcement Concept Removal for Enhancing Safety in Text-to-Image Models
Jun 12, 2026Dong Han, Yong LiText-To-Image Generative Artificial Intelligence
Huawei Heisenberg Research Center, Huawei Technologies Düsseldorf GmbH, Düsseldorf, Germany · Computer Vison Group, Friedrich Schiller University Jena, Jena, Germany.
Learning What to Remember: A Cognitively Grounded Multi-Factor Value Model for Agentic Memory
Jun 11, 2026Zhibao Chen, Qian ChengAgentic Memory Forgetting
Huatai Securities, Nanjing, China
FOGO: Forgetting-aware Orthogonalization Optimizer
Jun 9, 2026Toan Nguyen, Yang Liu, Trung Le +2Adaptive Optimizers Continual Learning
School of Computer Science and Engineering University of New South Wales Sydney, Australia · Department of Data Science & AI Monash University Melbourne, Australia · DEVCOM Army Research Laboratory USA

Oct 1, 2026, cs.LGJ/K move · Enter open · S save

SIEVE: Selective attention-value Suppression for Vision-Language Models Unlearning

Si Qi Goh, Cap Dang Xuan Kiet, Tat-Jen Cham, Kwok-Yan Lam

Digital Trust Centre, Nanyang Technological University, Singapore · College of Computing and Data Science, Nanyang Technological University, Singapore

Exact Unlearning Forgetting Modalities

Open paper AskPDF arXiv

The ability of vision-language models (VLMs) to associate visual identities with biographical information creates a need for selective unlearning of personally identifiable information (PII) while preserving permitted knowledge about the same individual. This setting is challenging because both sensitive and retained information can share the same visual inputs and intermediate representations. We introduce SIEVE, a simple and effective framework for selective VLM unlearning. SIEVE directly regularizes attention-value representations while also controlling model outputs. SIEVE suppresses attention values for forget examples toward a constant zero, while preserving retain-example representations by matching them to a frozen reference model. These objectives are combined with sequence-level forget and retain supervision, enabling targeted forgetting without largely affecting retained knowledge. Extensive experiments show that SIEVE achieves state-of-the-art performance on unlearning with multiple model-modality settings, while maintaining competitive retained utility. Ablation studies further show that value suppression and negative cross-entropy contribute complementary forgetting signals, while reference-based value matching substantially reduces utility degradation. These results demonstrate that attention values provide an effective intervention point for selective multimodal unlearning when sensitive and retained knowledge are closely related.

Momentum

Related topics

Latest papers 123