Related papers: Reasoning under Vision: Understanding Visual-Spati…

Thinking Large Language Models (LLMs) generate explicit intermediate reasoning traces before final answers, potentially improving transparency, interpretability, and solution accuracy for code generation. However, the quality of these…

Despite impressive advancements in Visual-Language Models (VLMs) for multi-modal tasks, their reliance on RGB inputs limits precise spatial understanding. Existing methods for integrating spatial cues, such as point clouds or depth, either…

Vision language models (VLMs) can simultaneously reason about images and texts to tackle many tasks, from visual question answering to image captioning. This paper focuses on map parsing, a novel task that is unexplored within the VLM…

Vision-Language Models (VLMs) have transformed tasks requiring visual and reasoning abilities, such as image retrieval and Visual Question Answering (VQA). Despite their success, VLMs face significant challenges with tasks involving…

We present a framework for perspective-aware reasoning in vision-language models (VLMs) through mental imagery simulation. Perspective-taking, the ability to perceive an environment or situation from an alternative viewpoint, is a key…

Significant research efforts have been made to scale and improve vision-language model (VLM) training approaches. Yet, with an ever-growing number of benchmarks, researchers are tasked with the heavy burden of implementing each protocol,…

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…

Why do Vision Language Models (VLMs), despite success on standard benchmarks, often fail to match human performance on surprisingly simple visual reasoning tasks? While the underlying computational principles are still debated, we…

We propose MIRA, a new benchmark designed to evaluate models in scenarios where generating intermediate visual images is essential for successful reasoning. Unlike traditional CoT methods that rely solely on text, tasks in MIRA require…

Vision-language models (VLMs) work well in tasks ranging from image captioning to visual question answering (VQA), yet they struggle with spatial reasoning, a key skill for understanding our physical world that humans excel at. We find that…

Combining multiple perceptual inputs and performing combinatorial reasoning in complex scenarios is a sophisticated cognitive function in humans. With advancements in multi-modal large language models, recent benchmarks tend to evaluate…

Reasoning-augmented vision language models (VLMs) generate explicit chains of thought that promise greater capability and transparency but also introduce new failure modes: models may reach correct answers via visually unfaithful…

With the current surge in spatial reasoning explorations, researchers have made significant progress in understanding indoor scenes, but still struggle with diverse applications such as robotics and autonomous driving. This paper aims to…

Data visualizations are powerful tools for communicating patterns in quantitative data. Yet understanding any data visualization is no small feat -- succeeding requires jointly making sense of visual, numerical, and linguistic inputs…

Advancements in large language models (LLMs) have demonstrated their potential in facilitating high-level reasoning, logical reasoning and robotics planning. Recently, LLMs have also been able to generate reward functions for low-level…

Vision language models (VLMs) can flexibly address various vision tasks through text interactions. Although successful in semantic understanding, state-of-the-art VLMs including GPT-5 still struggle in understanding 3D from 2D inputs. On…

Current large vision-language models (LVLMs) typically employ a connector module to link visual features with text embeddings of large language models (LLMs) and use end-to-end training to achieve multi-modal understanding in a unified…

Large Language Models (LLMs) demonstrate enhanced capabilities and reliability by reasoning more, evolving from Chain-of-Thought prompting to product-level solutions like OpenAI o1. Despite various efforts to improve LLM reasoning,…

We propose cognitive prompting as a novel approach to guide problem-solving in large language models (LLMs) through structured, human-like cognitive operations, such as goal clarification, decomposition, filtering, abstraction, and pattern…

Reasoning benchmarks such as the Abstraction and Reasoning Corpus (ARC) and ARC-AGI are widely used to assess progress in artificial intelligence and are often interpreted as probes of core, so-called ``fluid'' reasoning abilities. Despite…