Inference-Time Machine Unlearning via Gated Activation Redirection
Fuente:
arXiv
Saved in:
| Main Authors: | Turani, Vinícius Conte, Parraga, Otávio, Abitante, João Vitor Boer, Arguello, Kristen K., Pasquali, Joana, Barros, Ramiro N., Calmon, Flavio du Pin, Mattjie, Christian, Barros, Rodrigo C., Kupssinskü, Lucas S. |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
Low-Rank Adapters Initialization via Gradient Surgery for Continual Learning
by: Pasquali, Joana, et al.
Published: (2026)
by: Pasquali, Joana, et al.
Published: (2026)
Quantization-Robust LLM Unlearning via Low-Rank Adaptation
by: Abitante, João Vitor Boer, et al.
Published: (2026)
by: Abitante, João Vitor Boer, et al.
Published: (2026)
Inference Time Debiasing Concepts in Diffusion Models
by: Kupssinskü, Lucas S., et al.
Published: (2025)
by: Kupssinskü, Lucas S., et al.
Published: (2025)
Inference-Time Reward Hacking in Large Language Models
by: Khalaf, Hadi, et al.
Published: (2025)
by: Khalaf, Hadi, et al.
Published: (2025)
LLM Unlearning via Neural Activation Redirection
by: Shen, William F., et al.
Published: (2025)
by: Shen, William F., et al.
Published: (2025)
A Framework for Benchmarking Fairness-Utility Trade-offs in Text-to-Image Models via Pareto Frontiers
by: Bochernitsan, Marco N., et al.
Published: (2025)
by: Bochernitsan, Marco N., et al.
Published: (2025)
Attack-Aware Noise Calibration for Differential Privacy
by: Kulynych, Bogdan, et al.
Published: (2024)
by: Kulynych, Bogdan, et al.
Published: (2024)
Optimal conversion from Rényi Differential Privacy to $f$-Differential Privacy
by: Riess, Anneliese, et al.
Published: (2026)
by: Riess, Anneliese, et al.
Published: (2026)
Debiasing Methods for Fairer Neural Models in Vision and Language Research: A Survey
by: Parraga, Otávio, et al.
Published: (2022)
by: Parraga, Otávio, et al.
Published: (2022)
Fair Machine Unlearning: Data Removal while Mitigating Disparities
by: Oesterling, Alex, et al.
Published: (2023)
by: Oesterling, Alex, et al.
Published: (2023)
Bayesian Attention Mechanism: A Probabilistic Framework for Positional Encoding and Context Length Extrapolation
by: Bianchessi, Arthur S., et al.
Published: (2025)
by: Bianchessi, Arthur S., et al.
Published: (2025)
Laparotomía, laparoscopia diagnóstica, laparoscopia operatoria: análisis de costos
by: Ramiro Argüello Argüello
Published: (2000)
by: Ramiro Argüello Argüello
Published: (2000)
Histerectomía total por laparoscopia: la nueva opción
by: Ramiro Argüello Argüello
Published: (2001)
by: Ramiro Argüello Argüello
Published: (2001)
HISTERECTOMÍA TOTAL POR LAPAROSCOPIA EN 202 PACIENTES
by: Ramiro Argüello Argüello
Published: (2003)
by: Ramiro Argüello Argüello
Published: (2003)
Complicaciones en 748 histerectomías por laparoscopia utilizando un manipulador uterino con resaltador vaginal
by: Ramiro Argüello-Argüello
Published: (2012)
by: Ramiro Argüello-Argüello
Published: (2012)
Robust AI Evaluation through Maximal Lotteries
by: Khalaf, Hadi, et al.
Published: (2026)
by: Khalaf, Hadi, et al.
Published: (2026)
Predictive Churn with the Set of Good Models
by: Watson-Daniels, Jamelle, et al.
Published: (2024)
by: Watson-Daniels, Jamelle, et al.
Published: (2024)
Literatura, memória e identidade em ‘Infância’, de Graciliano Ramos
by: Cátia Silene Kupssinskü
Published: (2018)
by: Cátia Silene Kupssinskü
Published: (2018)
AI Alignment at Your Discretion
by: Buyl, Maarten, et al.
Published: (2025)
by: Buyl, Maarten, et al.
Published: (2025)
Estresse percebido em mulheres com síndrome metabólica: um estudo transversal
by: Vinicius Santos-Barros
Published: (2023)
by: Vinicius Santos-Barros
Published: (2023)
Ensino de Ciências em escolas multisseriadas do campo: uma análise dos Guias de Aprendizagem de Ciências do Programa Escola Ativa
by: Flávio Bezerra Barros
Published: (2009)
by: Flávio Bezerra Barros
Published: (2009)
OS CAÇADORES DO RIOZINHO DO ANFRÍSIO: SABERES E PRÁTICAS CULTURAIS ENTRE NARRATIVAS E IMAGENS
by: Flávio Bezerra Barros
Published: (2017)
by: Flávio Bezerra Barros
Published: (2017)
Sociabilidade, cultura e biodiversidade na Beira de Abaetetuba no Pará
by: Flávio Bezerra Barros
Published: (2009)
by: Flávio Bezerra Barros
Published: (2009)
Rede social de apoio às pessoas idosas estomizadas à luz da complexidade
by: Edaiane Joana Lima Barros
Published: (2008)
by: Edaiane Joana Lima Barros
Published: (2008)
ReTrack: Data Unlearning in Diffusion Models through Redirecting the Denoising Trajectory
by: Shi, Qitan, et al.
Published: (2025)
by: Shi, Qitan, et al.
Published: (2025)
SafeRedir: Prompt Embedding Redirection for Robust Unlearning in Image Generation Models
by: Liu, Renyang, et al.
Published: (2026)
by: Liu, Renyang, et al.
Published: (2026)
THE DISCURSIVE CONSTRUCTION OF TOXIC MASCULINITY: AN INVESTIGATION INTO ACCUSATORY METAPHORS
by: Calmon, Diego, et al.
Published: (2024)
by: Calmon, Diego, et al.
Published: (2024)
Controvérsias no diagnóstico e tratamento da trombose venosa profunda pela ecografia vascular
by: Marcio Vinicius Lins Barros
Published: (2012)
by: Marcio Vinicius Lins Barros
Published: (2012)
“Por quê olhar os animais?” Ética da alteridade e animalidade em John Berger
by: Mateus Vinícius Barros Uchôa
Published: (2022)
by: Mateus Vinícius Barros Uchôa
Published: (2022)
Kita-Alltag im Fokus – Deutschland im internationalen Vergleich
by: Bader, Samuel, et al.
Published: (2024)
by: Bader, Samuel, et al.
Published: (2024)
Mudanças recentes nas relações intersetoriais: um exame das atividades de serviço e industriais
by: Vinicius Cardoso de Barros Fornari
Published: (2017)
by: Vinicius Cardoso de Barros Fornari
Published: (2017)
Atividades inovativas em indústrias de “baixa e média-baixa” tecnologias: um exame dos mecanismos de difusão da inovação
by: Vinicius Cardoso de Barros Fornari
Published: (2014)
by: Vinicius Cardoso de Barros Fornari
Published: (2014)
Rigor in AI: Doing Rigorous AI Work Requires a Broader, Responsible AI-Informed Conception of Rigor
by: Olteanu, Alexandra, et al.
Published: (2025)
by: Olteanu, Alexandra, et al.
Published: (2025)
Prevalência, motivações e impactos do tabagismo na saúde oral de estudantes universitários: uma revisão da literatura.
by: Mattjie, et al.
Published: (2025)
by: Mattjie, et al.
Published: (2025)
Four Fundamental Constants of Nature from a Gated Cubic Recursion with Zero Free Parameters
by: Lima, Eliseu Spiller de Barros
Published: (2026)
by: Lima, Eliseu Spiller de Barros
Published: (2026)
Selective Explanations
by: Paes, Lucas Monteiro, et al.
Published: (2024)
by: Paes, Lucas Monteiro, et al.
Published: (2024)
Molecular phylogeny of the marine snail genus Haminoea (Gastropoda, Cephalaspidea): A framework to study marine diversity and speciation
by: Turani, Martina, et al.
Published: (2023)
by: Turani, Martina, et al.
Published: (2023)
Two-dimensional water waves with constant vorticity and general bottom topography
by: Pasquali, S.
Published: (2025)
by: Pasquali, S.
Published: (2025)
Analytical study of a generalized Dirichlet-Neumann operator for three-dimensional water waves with vorticity
by: Pasquali, S.
Published: (2025)
by: Pasquali, S.
Published: (2025)
Reliability and Effectiveness of Autonomous AI Agents in Supply Chain Management
by: Long, Carol Xuan, et al.
Published: (2026)
by: Long, Carol Xuan, et al.
Published: (2026)
Similar Items
-
Low-Rank Adapters Initialization via Gradient Surgery for Continual Learning
by: Pasquali, Joana, et al.
Published: (2026) -
Quantization-Robust LLM Unlearning via Low-Rank Adaptation
by: Abitante, João Vitor Boer, et al.
Published: (2026) -
Inference Time Debiasing Concepts in Diffusion Models
by: Kupssinskü, Lucas S., et al.
Published: (2025) -
Inference-Time Reward Hacking in Large Language Models
by: Khalaf, Hadi, et al.
Published: (2025) -
LLM Unlearning via Neural Activation Redirection
by: Shen, William F., et al.
Published: (2025)