Related papers: One Self-Configurable Model to Solve Many Abstract…

Analogical reasoning derives information from known relations and generalizes this information to similar yet unfamiliar situations. One of the first generalized ways in which deep learning models were able to solve verbal analogies was…

Visual relationship detection aims to locate objects in images and recognize the relationships between objects. Traditional methods treat all observed relationships in an image equally, which causes a relatively poor performance in the…

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…

Universal image restoration aims to recover clean images from arbitrary real-world degradations using a single inference model. Despite significant progress, existing all-in-one restoration networks do not scale to multiple degradations. As…

We present ARCTraj, a dataset and methodological framework for modeling human reasoning through complex visual tasks in the Abstraction and Reasoning Corpus (ARC). While ARC has inspired extensive research on abstract reasoning, most…

In recent years, Automatic Speech Recognition (ASR) technology has approached human-level performance on conversational speech under relatively clean listening conditions. In more demanding situations involving distant microphones,…

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…

Foundational Vision Transformers (ViTs) have limited effectiveness in tasks requiring fine-grained spatial understanding, due to their fixed pre-training resolution and inherently coarse patch-level representations. These challenges are…

We introduce SCAR, a method for long-term auto-calibration refinement of aerial visual-inertial systems that exploits georeferenced satellite imagery as a persistent global reference. SCAR estimates both intrinsic and extrinsic parameters…

Recent reasoning-oriented LLMs have demonstrated strong performance on challenging tasks such as mathematics and science examinations. However, core cognitive faculties of human intelligence, such as abstract reasoning and generalization,…

Training large reasoning models (LRMs) with reinforcement learning in STEM domains is hindered by the scarcity of high-quality, diverse, and verifiable problem sets. Existing synthesis methods, such as Chain-of-Thought prompting, often…

Audio-Visual Speech Recognition (AVSR) seeks to model, and thereby exploit, the dynamic relationship between a human voice and the corresponding mouth movements. A recently proposed multimodal fusion strategy, AV Align, based on…

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…

Large language models (LLMs) have recently shown strong potential for Automated Program Repair (APR), yet most existing approaches remain unimodal and fail to leverage the rich diagnostic signals contained in visual artifacts such as…

Reinforcement learning with verifiable rewards (RLVR) has shown promise in enhancing the reasoning capabilities of large language models by learning directly from outcome-based rewards. Recent RLVR works that operate under the zero setting…

The task of zero-shot commonsense question answering evaluates models on their capacity to reason about general scenarios beyond those presented in specific datasets. Existing approaches for tackling this task leverage external knowledge…

Despite the remarkable success of large language models (LLMs), they still face bottlenecks while deploying in dynamic, real-world settings with primary challenges being concept drift and the high cost of gradient-based adaptation.…

Abstract visual reasoning (AVR) involves discovering shared concepts across images through analogy, akin to solving IQ test problems. Bongard Problems (BPs) remain a key challenge in AVR, requiring both visual reasoning and verbal…

Retrieval Augmented Generation (RAG) has emerged as a standard paradigm for enhancing the factual accuracy and contextual relevance of Large Language Models (LLMs) by integrating retrieval mechanisms. However, existing evaluation frameworks…

Visual commonsense reasoning (VCR) is a challenging multi-modal task, which requires high-level cognition and commonsense reasoning ability about the real world. In recent years, large-scale pre-training approaches have been developed and…