相关论文: Deep Non-Monotonic Reasoning for Visual Abstract R…

Humans solving algorithmic (or) reasoning problems typically exhibit solution times that grow as a function of problem difficulty. Adaptive recurrent neural networks have been shown to exhibit this property for various language-processing…

Vision-language models benefit from high-resolution images, but the increase in visual-token count incurs high compute overhead. Humans resolve this tension via foveation: a coarse view guides "where to look", while selectively acquired…

Visual abstract reasoning is core to image processing. We present Valen, a unified probability-highlighting baseline that excels on both RPM (progression) and Bongard-Logo (clustering) tasks. Analysing its internals, we find solvers…

As future superhuman models become increasingly complex, accurately supervising their behavior may exceed human capabilities. Recent works have demonstrated that in such scenarios, weak models can effectively supervise strong models, a…

Reasoning is an important ability that we learn from a very early age. Yet, reasoning is extremely hard for algorithms. Despite impressive recent progress that has been reported on tasks that necessitate reasoning, such as visual question…

Understanding the physical world - governed by laws of motion, spatial relations, and causality - poses a fundamental challenge for multimodal large language models (MLLMs). While recent advances such as OpenAI o3 and GPT-4o demonstrate…

Recent advancements in multimodal large language models have driven breakthroughs in visual question answering. Yet, a critical gap persists, `conceptualization'-the ability to recognize and reason about the same concept despite variations…

While Vision-Language Models (VLMs) can solve complex tasks through agentic reasoning, their capabilities remain largely constrained to text-oriented chain-of-thought or isolated tool invocation. They fail to exhibit the human-like…

Learning abstractions directly from data is a core challenge in robotics. Humans naturally operate at an abstract level, reasoning over high-level subgoals while delegating execution to low-level motor skills -- an ability that enables…

The ability to hypothesise, develop abstract concepts based on concrete observations and apply these hypotheses to justify future actions has been paramount in human development. An existing line of research in outfitting intelligent…

Automated mathematical reasoning is a challenging problem that requires an agent to learn algebraic patterns that contain long-range dependencies. Two particular tasks that test this type of reasoning are (1) mathematical equation…

Human reasoning is grounded in an ability to identify highly abstract commonalities governing superficially dissimilar visual inputs. Recent efforts to develop algorithms with this capacity have largely focused on approaches that require…

Evaluating the performance of visual language models (VLMs) in graphic reasoning tasks has become an important research topic. However, VLMs still show obvious deficiencies in simulating human-level graphic reasoning capabilities,…

Audio-Visual Question Answering (AVQA) is a challenging multimodal reasoning task requiring intelligent systems to answer natural language queries based on paired audio-video inputs accurately. However, existing AVQA approaches often suffer…

Deep neural networks continue to advance the state-of-the-art of image recognition tasks with various methods. However, applications of these methods to multimodality remain limited. We present Multimodal Residual Networks (MRN) for the…

"Thinking with images" has emerged as an effective paradigm for advancing visual reasoning, extending beyond text-only chains of thought by injecting visual evidence into intermediate reasoning steps. However, existing methods fall short of…

Visual planning represents a crucial facet of human intelligence, especially in tasks that require complex spatial reasoning and navigation. Yet, in machine learning, this inherently visual problem is often tackled through a verbal-centric…

Deep learning is computationally intensive, with significant efforts focused on reducing arithmetic complexity, particularly regarding energy consumption dominated by data movement. While existing literature emphasizes inference, training…

Visual understanding goes well beyond object recognition. With one glance at an image, we can effortlessly imagine the world beyond the pixels: for instance, we can infer people's actions, goals, and mental states. While this task is easy…

Bridging the semantic gap between image and question is an important step to improve the accuracy of the Visual Question Answering (VQA) task. However, most of the existing VQA methods focus on attention mechanisms or visual relations for…