Related papers: Inferring and Executing Programs for Visual Reason…

We present CausalVLR (Causal Visual-Linguistic Reasoning), an open-source toolbox containing a rich set of state-of-the-art causal relation discovery and causal inference methods for various visual-linguistic reasoning tasks, such as VQA,…

Humans continue to outperform modern AI systems in their ability to flexibly parse and understand complex visual scenes. Here, we present a novel module for visual reasoning, the Guided Attention Model for (visual) Reasoning (GAMR), which…

Despite substantial progress in applying neural networks (NN) to a wide variety of areas, they still largely suffer from a lack of transparency and interpretability. While recent developments in explainable artificial intelligence attempt…

Video reasoning constitutes a comprehensive assessment of a model's capabilities, as it demands robust perceptual and interpretive skills, thereby serving as a means to explore the boundaries of model performance. While recent research has…

Neural algorithmic reasoning studies the problem of learning algorithms with neural networks, especially with graph architectures. A recent proposal, XLVIN, reaps the benefits of using a graph neural network that simulates the value…

Deep learning (DL) based computer vision (CV) models are generally considered as black boxes due to poor interpretability. This limitation impedes efficient diagnoses or predictions of system failure, thereby precluding the widespread…

Through its affordances, immersive virtual reality (VR) offers a means to apply embodied and external cognition from the physical realm to solving analytical problems that are typically only conceptual. We present an example of executing a…

Reasoning is a hallmark of human intelligence, enabling adaptive decision-making in complex and unfamiliar scenarios. In contrast, machine intelligence remains bound to training data, lacking the ability to dynamically refine solutions at…

Reinforcement Learning with Verifiable Rewards (RLVR) improves reasoning in large language models but treats all correct solutions equally, potentially reinforcing flawed traces that get correct answers by chance. We observe that better…

Vision-language models (VLMs) show promise for autonomous driving but often lack transparent reasoning capabilities that are critical for safety. We investigate whether explicitly modeling reasoning during fine-tuning enhances VLM…

A fundamental component of human vision is our ability to parse complex visual scenes and judge the relations between their constituent objects. AI benchmarks for visual reasoning have driven rapid progress in recent years with…

Recent releases such as o3 highlight human-like "thinking with images" reasoning that combines tool use with stepwise verification, yet most open-source approaches still rely on text-only chains, rigid visual schemas, or single-step…

Despite the remarkable progress of Vision-Language Models (VLMs) in adopting "Thinking-with-Images" capabilities, accurately evaluating the authenticity of their reasoning process remains a critical challenge. Existing benchmarks mainly…

Multimodal Large Language Models (MLLMs) achieve strong multimodal reasoning performance, yet we identify a recurring failure mode in long-form generation: as outputs grow longer, models progressively drift away from image evidence and fall…

We propose a new interpretability method for neural networks, which is based on a novel mathematico-philosophical theory of reasons. Our method computes a vector for each neuron, called its reasons vector. We then can compute how strongly…

Despite strong performance of Multimodal Large Language Models (MLLMs) on multimodal tasks, predicting whether and why an image is persuasive remains challenging. We first show that prompting MLLMs to reason before prediction does not…

Vision Language Models exhibit impressive performance for various tasks, yet they often lack the sophisticated situational reasoning required for complex decision-making. This paper shows that VLMs can achieve surprisingly strong…

Multimodal Large Language Models (MLLMs) frequently hallucinate due to their reliance on fragile, linear reasoning and weak visual grounding. We propose Visual Attention Reasoning (VAR), a reinforcement learning framework that reformulates…

AI systems' ability to explain their reasoning is critical to their utility and trustworthiness. Deep neural networks have enabled significant progress on many challenging problems such as visual question answering (VQA). However, most of…

Recent "Thinking with Video" approaches use Video Generation Models (VGMs) for visual reasoning by producing temporally coherent Chain-of-Frames as reasoning artifacts. Even strong VGMs, however, exhibit two recurring failure modes on…