Lens purifies visual evidence in MLLMs via question-conditioned latent noise masking with a LET token, yielding 2.4-6.4 point gains on VQA and grounding tasks.
Its policy update follows the released GRPO setting and optimizes visual understanding or grounding outputs through verifiable rewards
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Latent Noise Mask for Reducing Visual Redundancy in Multimodal Large Language Models
Lens purifies visual evidence in MLLMs via question-conditioned latent noise masking with a LET token, yielding 2.4-6.4 point gains on VQA and grounding tasks.