The paper identifies a failure mode called spatial lexical bias in MLLMs, where adding a spatial word to options biases the model's choice, and demonstrates that this failure originates primarily from…

The paper deconstructs latent visual reasoning tokens into components and finds that the performance gains are primarily due to boundary markers and attention patterns, not the tokens' ability to enco…

The paper proposes CSMR, a cognitive scheduling framework that allows a language model to dynamically decide when to acquire task-relevant visual evidence, significantly improving multimodal reasoning…

The paper introduces StemBind, a diagnostic benchmark that separates perception, rule induction, and answer selection in abstract visual reasoning, revealing that the primary failure point for MLLMs i…

The paper proposes Reasoning-Conditioned Direct Preference Optimization (RC-DPO) to effectively mitigate hallucinations in multimodal large reasoning models by explicitly conditioning the preference o…

The paper introduces EASE, a method that enhances multimodal Reinforcement Learning with Verifiable Rewards (RLVR) by providing spatial attention supervision anchored to visual evidence, significantly…

This paper evaluates the reliability of using Large Language Models (LLMs) as automated judges to assess the quality of other LLMs, finding a high correlation with human judgment when suitable prompts…

This paper introduces a new evaluation framework, SpatialUncertain, demonstrating that current Vision-Language Models (VLMs) are prone to overconfident and incorrect answers to spatial questions when…

The paper proposes EAGLE, a novel evidence-aligned multi-agent framework, demonstrating that requiring shared visual evidence among agents is crucial for achieving reliable and trustworthy consensus i…

The paper introduces VIABLE, the first benchmark for evaluating Vision-Language Models (VLMs) as judges for Visually Impaired Assistance (VIA), finding that current models are largely unreliable and p…

The paper introduces an Item Response Theory (IRT)-based indicator that effectively identifies likely mislabeled items in existing LLM benchmarks, revealing systematic errors in labeling and model spe…

This paper introduces Imaginative Perception Tokens (IPT) to improve spatial reasoning in vision language models.

The paper proposes using Vision-Language Models (VLMs) as 'teachers' to guide Video Generation Models (VGMs) during test-time optimization, significantly improving video reasoning capabilities.

The paper introduces Responsible Contrastive Soft Prompting (RCSP), a parameter-efficient method using soft prompts to improve LLM reliability by simultaneously suppressing hallucinations, encouraging…

The paper introduces MOV-Bench, a challenging benchmark for multi-hop audio-visual reasoning, and proposes AOP-Agent, an agentic framework that significantly improves open-source Omni-LLMs' ability to…

The paper introduces a novel framework to quantify faithful confidence expression (FC) in Large Reasoning Models (LRMs), finding that FC remains a significant and challenging reliability target for th…

The paper introduces 'reward bias substitution,' demonstrating that single-axis mitigations of reward model biases merely shift optimization pressure to correlated proxies, and proposes augmenting eva…

The paper proposes AsyMoE, a novel Mixture of Experts architecture for Large Vision-Language Models that explicitly models the inherent asymmetry between visual and linguistic modalities, achieving si…

VCap introduces a novel Witness-Adjudicator reward mechanism that provides highly precise, factually grounded feedback for visual captioning, enabling state-of-the-art performance in RL-trained multim…

The paper argues that benchmarking Vision-Language Models (VLMs) for urban perception must treat human disagreement and non-response as key measurement outcomes, rather than assuming perfect consensus…