Related papers: Deep Learning Methods for Abstract Visual Reasonin…

A fundamental challenge in artificial intelligence involves understanding the cognitive mechanisms underlying visual reasoning in sophisticated models like Vision-Language Models (VLMs). How do these models integrate visual perception with…

Improving the multi-step reasoning ability of Large Language Models (LLMs) is a critical yet challenging task. The dominant paradigm, outcome-supervised reinforcement learning (RLVR), rewards only correct final answers, often propagating…

The popularity of Deep Learning for real-world applications is ever-growing. With the introduction of high performance hardware, applications are no longer limited to image recognition. With the introduction of more complex problems comes…

Large Multimodal Models (LMMs) have recently demonstrated remarkable visual understanding performance on both vision-language and vision-centric tasks. However, they often fall short in integrating advanced, task-specific capabilities for…

The success of scene graphs for visual scene understanding has brought attention to the benefits of abstracting a visual input (e.g., image) into a structured representation, where entities (people and objects) are nodes connected by edges…

Abstract visual reasoning remains challenging as existing methods often prioritize either global context or local row-wise relations, failing to integrate both, and lack intermediate feature constraints, leading to incomplete rule capture…

Visual Grounding (VG) tasks, such as referring expression detection and segmentation tasks are important for linking visual entities to context, especially in complex reasoning tasks that require detailed query interpretation. This paper…

The Abstraction and Reasoning Corpus (ARC-AGI) presents a formidable challenge for AI systems. Despite the typically low performance on ARC, the deep learning paradigm remains the most effective known strategy for generating skillful…

Recent studies have demonstrated the effectiveness of Large Language Models (LLMs) as reasoning modules that can deconstruct complex tasks into more manageable sub-tasks, particularly when applied to visual reasoning tasks for images. In…

Over the past few years, deep learning techniques have achieved tremendous success in many visual understanding tasks such as object detection, image segmentation, and caption generation. Despite this thriving in computer vision and natural…

Visual relation detection (VRD) is the task of identifying the relationships between objects in a scene. VRD models trained solely on relation detection data struggle to generalize beyond the relations on which they are trained. While…

The ability to learn continually without forgetting the past tasks is a desired attribute for artificial learning systems. Existing approaches to enable such learning in artificial neural networks usually rely on network growth, importance…

While deep learning methods have achieved impressive success in many vision benchmarks, it remains difficult to understand and explain the representations and decisions of these models. Though vision models are typically trained on 2D…

It is expected that progress toward true artificial intelligence will be achieved through the emergence of a system that integrates representation learning and complex reasoning (LeCun et al. 2015). In response to this prediction, research…

We consider the abstract relational reasoning task, which is commonly used as an intelligence test. Since some patterns have spatial rationales, while others are only semantic, we propose a multi-scale architecture that processes each query…

Recent work on reinforcement learning with verifiable rewards (RLVR) has shown that large language models (LLMs) can be substantially improved using outcome-level verification signals, such as unit tests for code or exact-match checks for…

Deep reinforcement learning (RL) has been successfully applied to a variety of game-like environments. However, the application of deep RL to visual navigation with realistic environments is a challenging task. We propose a novel learning…

Neural networks are increasingly used in robotics as policies, state transition models, state estimation models, or all of the above. With these components being learned from data, it is important to be able to analyze what behaviors were…

The quantification of cognitive powers rests on identifying a behavioural task that depends on them. Such dependence cannot be assured, for the powers a task invokes cannot be experimentally controlled or constrained a priori, resulting in…

Deep learning has allowed a paradigm shift in pattern recognition, from using hand-crafted features together with statistical classifiers to using general-purpose learning procedures for learning data-driven representations, features, and…