Papers with Code 아카이브
Machine Unlearning
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 0
- 보존된 평가 기록
- 0
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/optml-group/advunlearn
공식 코드Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models
https://github.com/optml-group/mu-coreset
공식 코드LLM Unlearning Reveals a Stronger-Than-Expected Coreset Effect in Current Benchmarks
https://github.com/optml-group/unlearn-ilu
공식 코드Invariance Makes LLM Unlearning Resilient Even to Unanticipated Downstream Fine-Tuning
https://github.com/optml-group/unlearn-saliency
공식 코드https://github.com/optml-group/unlearn-sparse
공식 코드https://github.com/optml-group/unlearn-trace
공식 코드Unlearning Isn't Invisible: Detecting Unlearning Traces in LLMs from Model Outputs
https://github.com/optml-group/unlearn-worstcase
공식 코드Challenging Forgets: Unveiling the Worst-Case Forget Sets in Machine Unlearning
https://github.com/optml-group/unlearncanvas
공식 코드UnlearnCanvas: Stylized Image Dataset for Enhanced Machine Unlearning Evaluation in Diffusion Models
https://github.com/optml-group/vlm-safety-mu
공식 코드Safety Mirage: How Spurious Correlations Undermine VLM Safety Fine-tuning
https://github.com/reds-lab/restricted_gradient_diversity_unlearning
공식 코드Boosting Alignment for Post-Unlearning Text-to-Image Generative Models
https://github.com/royalbeff/evaluating_machine_unlearning_via_epistemic_uncertainty
공식 코드https://github.com/ryliu68/igmu
공식 코드https://github.com/s-huu/jog_llm_memory
공식 코드Jogging the Memory of Unlearned LLMs Through Targeted Relearning Attacks
https://github.com/safolab-wisc/fiubench
공식 코드Benchmarking Vision Language Model Unlearning via Fictitious Facial Identity Dataset
https://github.com/sail-sg/closer-look-llm-unlearning
공식 코드A Closer Look at Machine Unlearning for Large Language Models
https://github.com/sangamesh-kodge/class_forgetting
공식 코드Deep Unlearning: Fast and Efficient Gradient-free Approach to Class Forgetting
https://github.com/sangamesh-kodge/sap
공식 코드SAP: Corrective Machine Unlearning with Scaled Activation Projection for Label Noise Robustness
https://github.com/shaofeishen768/camu
공식 코드https://github.com/shaofeishen768/laf
공식 코드Label-Agnostic Forgetting: A Supervision-Free Unlearning in Deep Models
https://github.com/shash42/evaluating-inexact-unlearning
공식 코드Towards Adversarial Evaluations for Inexact Machine Unlearning
https://github.com/shreya1313/llm-unlearning
공식 코드https://github.com/shurongwang/DynFrs
공식 코드DynFrs: An Efficient Framework for Machine Unlearning in Random Forest
https://github.com/slhleosun/aligned-but-blind
공식 코드Aligned but Blind: Alignment Increases Implicit Bias by Reducing Awareness of Race
https://github.com/stair-lab/certified-unlearning-neural-networks-icml-2025
공식 코드https://github.com/stanleykywu/model-updates
공식 코드How to Combine Membership-Inference Attacks on Multiple Updated Models
https://github.com/tamlhp/awesome-machine-unlearning
공식 코드https://github.com/tdemin16/group-robust_machine_unlearning
공식 코드https://github.com/thupchnsky/mufc
공식 코드https://github.com/thupchnsky/sgc_unlearn
공식 코드https://github.com/tianyu139/tangent-model-composition
공식 코드https://github.com/tomyamkum/OneShotMU-with-MNCode
공식 코드https://github.com/vikram2000b/Fast-Machine-Unlearning
공식 코드https://github.com/vikram2000b/bad-teaching-unlearning
공식 코드Can Bad Teaching Induce Forgetting? Unlearning in Deep Networks using an Incompetent Teacher
https://github.com/vlgiitr/lora-unlearn
공식 코드https://github.com/vsingh-group/LCODEC-deep-unlearning
공식 코드Deep Unlearning via Randomized Conditionally Independent Hessians
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.