相关论文: Evaluating Self-Correcting Vision Agents Through Q…

Recent progress in Vision Language Models (VLMs) has raised the question of whether they can reliably perform nonverbal reasoning. To this end, we introduce VRIQ (Visual Reasoning IQ), a novel benchmark designed to assess and analyze the…

Although large language models (LLMs) have transformed AI, they still make mistakes and can explore unproductive reasoning paths. Self-correction capability is essential for deploying LLMs in safety-critical applications. We uncover a…

Reasoning Vision-Language Models (VLMs) have shown promising performance on complex multimodal tasks. However, they still face significant challenges: they are highly sensitive to reasoning errors, require large volumes of annotated data or…

Building on recent advances in language-based reasoning models, we explore multimodal reasoning that integrates vision and text. Existing multimodal benchmarks primarily test visual extraction combined with text-based reasoning, lacking…

Autonomous agent systems powered by Large Language Models (LLMs) have demonstrated promising capabilities in automating complex tasks. However, current evaluations largely rely on success rates without systematically analyzing the…

Multimodal large language models (MLLMs) that integrate visual and textual reasoning leverage chain-of-thought (CoT) prompting to tackle complex visual tasks, yet continue to exhibit visual hallucinations and an over-reliance on textual…

Visual reasoning is a core component of human intelligence and a critical capability for advanced multimodal models. Yet current reasoning evaluations of multimodal large language models (MLLMs) often rely on text descriptions and allow…

Vision-language agents have achieved remarkable progress in a variety of multimodal reasoning tasks; however, their learning remains constrained by the limitations of human-annotated supervision. Recent self-rewarding approaches attempt to…

Recent advances in Vision-Language Models (VLMs) have improved performance in multi-modal learning, raising the question of whether these models truly understand the content they process. Crucially, can VLMs detect when a reasoning process…

The ability of large vision-language models (LVLMs) to critique and correct their reasoning is an essential building block towards their self-improvement. However, a systematic analysis of such capabilities in LVLMs is still lacking. We…

Recently, some studies have integrated Multimodal Large Language Models into robotic manipulation, constructing vision-language-action models (VLAs) to interpret multimodal information and predict SE(3) poses. While VLAs have shown…

Vision-Language-Action (VLA) models achieve over 95% success on standard benchmarks. However, through systematic experiments, we find that current state-of-the-art VLA models largely ignore language instructions. Prior work lacks: (1)…

Vision-language Models (VLMs), despite achieving strong performance on multimodal benchmarks, often misinterpret straightforward visual concepts that humans identify effortlessly, such as counting, spatial reasoning, and viewpoint…

Current work on robot failure detection and correction typically operate in a post hoc manner, analyzing errors and applying corrections only after failures occur. This work introduces CycleVLA, a system that equips Vision-Language-Action…

Vision-Language Models (VLMs) have achieved impressive performance across a wide range of multimodal tasks, yet they often exhibit inconsistent behavior when faced with semantically equivalent inputs, undermining their reliability and…

Recent advancements in Multimodal Large Language Models (MLLMs) have demonstrated impressive performance on standard visual reasoning benchmarks. However, there is growing concern that these models rely excessively on linguistic shortcuts…

Autonomous agents based on Large Language Models (LLMs) are increasingly being utilized in complex software systems. However, reliability remains a significant challenge due to unpredictable failures such as hallucinations, execution…

Recent advancements in Vision Language Models (VLMs) have expanded their capabilities to interactive agent tasks, yet existing benchmarks remain limited to single-agent or text-only environments. In contrast, real-world scenarios often…

Recent Vision-Language-Action (VLA) models report impressive success rates on standard robotic benchmarks, fueling optimism about general-purpose physical intelligence. However, recent evidence suggests a systematic misalignment between…

While vision-language-action (VLA) models for embodied agents integrate perception, reasoning, and control, they remain constrained by two critical weaknesses: first, during grasping tasks, the action tokens generated by the language model…