Related papers: Hidden in Plain Sight: Visual-to-Symbolic Analytic…
Automated discovery of physical laws from observational data in the real world is a grand challenge in AI. Current methods, relying on symbolic regression or LLMs, are limited to uni-modal data and overlook the rich, visual phenomenological…
While Multimodal Large Language Models (MLLMs) excel at general vision-language tasks, visuospatial cognition - reasoning about spatial layouts, relations, and dynamics - remains a significant challenge. Existing models often lack the…
A user pointing their phone at a supermarket shelf and asking "Which soda has the least sugar?" poses a difficult challenge for current visual Al assistants. Such queries require not only object recognition, but explicit set-based reasoning…
End-to-end Vision-language Models (VLMs) often answer visual questions by exploiting spurious correlations instead of causal visual evidence, and can become more shortcut-prone when fine-tuned. We introduce VISTA (Visual-Information…
Extracting interpretable equations from observational datasets to describe complex natural phenomena is one of the core goals of artificial intelligence. This field is known as symbolic regression (SR). In recent years, Transformer-based…
A hallmark of advanced artificial intelligence is the capacity to progress from passive visual perception to the strategic modification of visual information to facilitate complex reasoning. This advanced capability, however, remains…
Visual reasoning, particularly spatial reasoning, is a challenging cognitive task that requires understanding object relationships and their interactions within complex environments, especially in robotics domain. Existing vision_language…
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…
Our society increasingly depends on intelligent systems to solve complex problems, ranging from recommender systems suggesting the next movie to watch to AI models assisting in medical diagnoses for hospitalized patients. With the iterative…
Video-based spatial cognition is vital for robotics and embodied AI but challenges current Vision-Language Models (VLMs). This paper makes two key contributions. First, we introduce ViCA (Visuospatial Cognitive Assistant)-322K, a diverse…
Symbolic regression (SR) seeks to recover closed-form mathematical expressions that describe observed data. While existing methods have advanced the discovery of either explicit mappings (i.e., $y = f(\mathbf{x})$) or discovering implicit…
Latent reasoning enables reasoning over continuous hidden states rather than explicit tokens, avoiding the language bottleneck and inference overhead of chain-of-thought for medical VQA. However, existing methods suffer from modality…
Abstract reasoning is a cornerstone of human intelligence, and replicating it with artificial intelligence (AI) presents an ongoing challenge. This study focuses on efficiently solving Raven's progressive matrices (RPM), a visual test for…
This study investigates the use of symbolic computation in Matrix Structural Analysis (MSA) for continuous beams, leveraging the MATLAB Symbolic Math Toolbox. By employing symbolic MSA, analytical expressions for displacements, support…
Ambiguity resolution is a key challenge in multimodal machine translation (MMT), where models must genuinely leverage visual input to map an ambiguous expression to its intended meaning. Although prior work has proposed…
Automating scientific discovery has been a grand goal of Artificial Intelligence (AI) and will bring tremendous societal impact. Learning symbolic expressions from experimental data is a vital step in AI-driven scientific discovery. Despite…
We present our vision for developing an automated tool capable of translating visual properties observed in Machine Learning (ML) visualisations into Python assertions. The tool aims to streamline the process of manually verifying these…
Multi-view visual reasoning is essential for intelligent systems that must understand complex environments from sparse and discrete viewpoints, yet existing research has largely focused on single-image or temporally dense video settings. In…
The predominant approach to visual question answering (VQA) relies on encoding the image and question with a "black-box" neural encoder and decoding a single token as the answer like "yes" or "no". Despite this approach's strong…
Large Vision-Language Models (LVLMs) have achieved remarkable proficiency in explicit visual recognition, effectively describing what is directly visible in an image. However, a critical cognitive gap emerges when the visual input serves…