CATA enables persistent continual unlearning in VLMs by sign-aware aggregation of unlearning task vectors to suppress conflicts that could revive forgotten knowledge.
Stabilizing modality gap & lowering gradient norms improve zero-shot adversarial robustness of vlms
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 3verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
BiAxisAudit measures LLM bias on two axes—across-prompt sensitivity via factorial grids and within-response divergence via split coding—revealing that task format explains as much variance as model choice and that 63.6% of bias signals appear in only one layer.
ICED performs interpretable concept-level unlearning in VLMs by constructing a concept vocabulary via MLLM and decomposing visual representations for targeted optimization.
citing papers explorer
-
CATA: Continual Machine Unlearning via Conflict-Averse Task Arithmetic
CATA enables persistent continual unlearning in VLMs by sign-aware aggregation of unlearning task vectors to suppress conflicts that could revive forgotten knowledge.
-
BiAxisAudit: A Novel Framework to Evaluate LLM Bias Across Prompt Sensitivity and Response-Layer Divergence
BiAxisAudit measures LLM bias on two axes—across-prompt sensitivity via factorial grids and within-response divergence via split coding—revealing that task format explains as much variance as model choice and that 63.6% of bias signals appear in only one layer.
-
ICED: Concept-level Machine Unlearning via Interpretable Concept Decomposition
ICED performs interpretable concept-level unlearning in VLMs by constructing a concept vocabulary via MLLM and decomposing visual representations for targeted optimization.