Learning When to Look: A Disentangled Curriculum for Strategic Perception in Multimodal Reasoning

A recent study has explored the integration of visual and textual information in Multimodal Large Language Models (MLLMs), revealing that visual-text fusion occurs at specific layers within these models rather than uniformly across the network. The research highlights a late-stage

A recent study has introduced a framework aimed at mitigating hallucination issues in Multimodal Large Language Models (MLLMs) during Reinforcement Learning (RL) optimization. The research identifies key factors contributing to hallucinations, including over-reliance on visual reasoning and insufficient exploration diversity. The proposed framework incorporates modules for caption feedback, diversity-aware sampling, and conflict regularization to enhance model reliability.

A new benchmark called KidVis has been introduced to evaluate the visual perceptual capabilities of Multimodal Large Language Models (MLLMs), specifically assessing their performance against that of 6-7 year old children across six atomic visual capabilities. The results reveal a significant performance gap, with human children scoring an average of 95.32 compared to GPT-5's score of 67.33.

A new method called PRISM has been introduced to optimize the selection of training data for Multimodal Large Language Models (MLLMs), addressing the redundancy in rapidly growing datasets that increases computational costs. This self-pruning intrinsic selection method aims to enhance efficiency without the need for extensive training or proxy-based inference techniques.

A recent study published on arXiv explores the integration of cognitive biases into reinforcement learning (RL) frameworks for financial decision-making, highlighting how human behavior influenced by biases like overconfidence and loss aversion can affect trading strategies. The research aims to demonstrate that RL models incorporating these biases can achieve better risk-adjusted returns compared to traditional models that assume rationality.

A recent study on differentially private policy optimization (DPPO) has been published, focusing on the sample complexity of policy optimization (PO) in reinforcement learning (RL). This research addresses privacy concerns in sensitive applications such as robotics and healthcare by formalizing a definition of differential privacy tailored to PO and analyzing the sample complexity of various PO algorithms under DP constraints.

A recent study introduced MoHoBench, a benchmark designed to assess the honesty of Multimodal Large Language Models (MLLMs) when confronted with unanswerable visual questions. This research highlights the need for a systematic evaluation of MLLMs' response behaviors, as their trustworthiness in generating content remains underexplored.