An inference-time unlearning method uses token entropy to detect when RL-trained multimodal reasoning models are about to recite private facts in their chain of thought, then redirects decoding with a visual anchor.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
LEMUR: Latent Entropy-aware Multimodal Unlearning via Visual-anchored Reasoning Redirection
An inference-time unlearning method uses token entropy to detect when RL-trained multimodal reasoning models are about to recite private facts in their chain of thought, then redirects decoding with a visual anchor.