PPU-Bench is a real-world benchmark exposing forget-retain trade-offs in MLLM unlearning and motivating Boundary-Aware Optimization to enforce intra-subject factual boundaries.
Continual learning and private unlearning
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
baseline 1
citation-polarity summary
years
2026 4roles
baseline 1polarities
baseline 1representative citing papers
Transformer circuits show free evolution during SFT, rendering static mechanistic localization inadequate for future parameter updates due to inherent temporal latency.
Existing continual unlearning methods fail to maintain forgetting, retained knowledge, and utility over 100 sequential privacy-deletion tasks in multimodal document models.
A contrastive visual forgetting technique constrained to the null space of retained knowledge enables targeted unlearning of visual concepts in MLLMs while preserving non-target visual and all textual knowledge.
citing papers explorer
-
PPU-Bench:Real World Benchmark for Personalized Partial Unlearning in Vision Language Models
PPU-Bench is a real-world benchmark exposing forget-retain trade-offs in MLLM unlearning and motivating Boundary-Aware Optimization to enforce intra-subject factual boundaries.
-
Navigating by Old Maps: The Pitfalls of Static Mechanistic Localization in LLM Post-Training
Transformer circuits show free evolution during SFT, rendering static mechanistic localization inadequate for future parameter updates due to inherent temporal latency.
-
ICU-Bench:Benchmarking Continual Unlearning in Multimodal Large Language Models
Existing continual unlearning methods fail to maintain forgetting, retained knowledge, and utility over 100 sequential privacy-deletion tasks in multimodal document models.
-
Null Space Constrained Contrastive Visual Forgetting for MLLM Unlearning
A contrastive visual forgetting technique constrained to the null space of retained knowledge enables targeted unlearning of visual concepts in MLLMs while preserving non-target visual and all textual knowledge.