AMVL applies bidirectional KL calibration to align answer-agnostic prior with answer-conditioned posterior in variational multimodal reasoning, reducing leakage and yielding +10.83 average gain on BLINK benchmark.
Refocus: Visual editing as a chain of thought for structured image understanding
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Visual latents in MLLMs are systematically silenced by autoregressive training but can be unsilenced at inference via query-guided contrastive alignment followed by a confidence-progression reward.
citing papers explorer
-
Multimodal Continuous Reasoning via Asymmetric Mutual Variational Learning
AMVL applies bidirectional KL calibration to align answer-agnostic prior with answer-conditioned posterior in variational multimodal reasoning, reducing leakage and yielding +10.83 average gain on BLINK benchmark.
-
Visual Latents Know More Than They Say: Unsilencing Latent Reasoning in MLLMs
Visual latents in MLLMs are systematically silenced by autoregressive training but can be unsilenced at inference via query-guided contrastive alignment followed by a confidence-progression reward.