Related papers: Hierarchical Visual Agent: Managing Contexts in Jo…

Large Language Models (LLMs) demonstrate enhanced capabilities and reliability by reasoning more, evolving from Chain-of-Thought prompting to product-level solutions like OpenAI o1. Despite various efforts to improve LLM reasoning,…

Automating operations research (OR) with large language models (LLMs) remains limited by hand-crafted reasoning--execution workflows. Complex OR tasks require adaptive coordination among problem interpretation, mathematical formulation,…

The rise of short-form video platforms and the emergence of multimodal large language models (MLLMs) have amplified the need for scalable, effective, zero-shot text-to-video retrieval systems. While recent advances in large-scale…

Radiology visual question answering (RVQA) provides precise answers to questions about chest X-ray images, alleviating radiologists' workload. While recent methods based on multimodal large language models (MLLMs) and retrieval-augmented…

Real-world visualization tasks involve complex, multi-modal requirements that extend beyond simple text-to-chart generation, requiring reference images, code examples, and iterative refinement. Current systems exhibit fundamental…

Images usually convey richer detail than text, but often include redundant information, which potentially downgrades multimodal reasoning performance. When faced with lengthy or complex messages, humans tend to employ abstract thinking to…

Recent advances in text-only large language models (LLMs), such as DeepSeek-R1, demonstrate remarkable reasoning ability. However, these models remain fragile or entirely incapable when extended to multi-modal tasks. Existing approaches…

This paper introduces a multi-agent framework for comprehensive highway scene understanding, designed around a mixture-of-experts strategy. In this framework, a large generic vision-language model (VLM), such as GPT-4o, is contextualized…

Continual Visual Question Answering (VQA) requires learning from non-stationary streams of visual inputs and questions while preserving past knowledge. Most prior methods adapt by updating a largely shared parameter set. This often leads to…

While Large Language Models (LLMs) have demonstrated impressive reasoning and planning abilities in textual domains and can effectively follow instructions for complex tasks, their ability to understand and manipulate spatial relationships…

Visual reasoning -- the ability to interpret the visual world -- is crucial for embodied agents that operate within three-dimensional scenes. Progress in AI has led to vision and language models capable of answering questions from images.…

Long-term memory is one of the key factors influencing the reasoning capabilities of Large Language Model Agents (LLM Agents). Incorporating a memory mechanism that effectively integrates past interactions can significantly enhance…

The advancement of multimodal large language models (MLLMs) has enabled impressive perception capabilities. However, their reasoning process often remains a "fast thinking" paradigm, reliant on end-to-end generation or explicit,…

Vision-Language Models (VLMs) often yield inconsistent descriptions of the same object across viewpoints, hindering the ability of embodied agents to construct consistent semantic representations over time. Previous methods resolved…

Building robust vision systems for high-stakes domains such as remote sensing requires stronger visual reasoning than what single-pass inference typically provides; yet, retraining large models is often computationally expensive and data…

Representing and understanding 3D environments in a structured manner is crucial for autonomous agents to navigate and reason about their surroundings. While traditional Simultaneous Localization and Mapping (SLAM) methods generate metric…

Chart generation aims to generate code to produce charts satisfying the desired visual properties, e.g., texts, layout, color, and type. It has great potential to empower the automatic professional report generation in financial analysis,…

Visual Language Models (VLMs) achieve promising results in medical reasoning but struggle with hallucinations, vague descriptions, inconsistent logic and poor localization. To address this, we propose a agent framework named Medical Visual…

Image-goal navigation steers an agent to a target location specified by an image in unseen environments. Existing methods primarily handle this task by learning an end-to-end navigation policy, which compares the similarities of target and…

Medical Visual Question Answering (Med-VQA) answers clinical questions using medical images, aiding diagnosis. Designing the MedVQA system holds profound importance in assisting clinical diagnosis and enhancing diagnostic accuracy. Building…