Activation Replay boosts multimodal reasoning in post-trained LMMs by replaying low-entropy activations from base models to RLVR counterparts at test time via visual token manipulation.
Sft or rl? an early investigation into training r1-like reasoning large vision-language models, 2025
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Boosting Reasoning in Large Multimodal Models via Activation Replay
Activation Replay boosts multimodal reasoning in post-trained LMMs by replaying low-entropy activations from base models to RLVR counterparts at test time via visual token manipulation.