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.
Mm-cot: a benchmark for probing visual chain-of-thought reasoning in multimodal models
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
LLMs show human-like forgetting rates that can be harnessed through probabilistic memory prompting to improve long-horizon reasoning.
citing papers explorer
-
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.
-
Forgetting as a Feature: Cognitive Alignment of Large Language Models
LLMs show human-like forgetting rates that can be harnessed through probabilistic memory prompting to improve long-horizon reasoning.