Related papers: Lightweight Structured Multimodal Reasoning for Cl…
Contemporary Vision-Language Models (VLMs) achieve strong performance on a wide range of tasks by pairing a vision encoder with a pre-trained language model, fine-tuned for visual-text inputs. Yet despite these gains, it remains unclear how…
Understanding manipulation scenarios allows intelligent robots to plan for appropriate actions to complete a manipulation task successfully. It is essential for intelligent robots to semantically interpret manipulation knowledge by…
Complex Visual Question Answering (Complex VQA) tasks, which demand sophisticated multi-modal reasoning and external knowledge integration, present significant challenges for existing large vision-language models (LVLMs) often limited by…
Understanding camera dynamics is a fundamental pillar of video spatial intelligence. However, existing multimodal models predominantly treat this task as a black-box classification, often confusing physically distinct motions by relying on…
This study investigates the use of large language models (LLMs) for human behavior understanding by jointly leveraging motion and video data. We argue that integrating these complementary modalities is essential for capturing both…
Modern vision-language models (VLMs) deliver impressive predictive accuracy yet offer little insight into 'why' a decision is reached, frequently hallucinating facts, particularly when encountering out-of-distribution data. Neurosymbolic…
We introduce MERGE, a system for situational grounding of actors, objects, and events in dynamic human-robot group interactions. Effective collaboration in such settings requires consistent situational awareness, built on persistent…
The remarkable progress of Multimodal Large Language Models (MLLMs) has attracted increasing attention to extend them to physical entities like legged robot. This typically requires MLLMs to not only grasp multimodal understanding…
Despite recent progress in multimodal large language models (MLLMs), reliable visual question answering in aerial scenes remains challenging. In such scenes, task-critical evidence is often carried by small objects, explicit quantities,…
Currently, utilizing large language models to understand the 3D world is becoming popular. Yet existing 3D-aware LLMs act as black boxes: they output bounding boxes or textual answers without revealing how those decisions are made, and they…
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…
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…
Long-form video understanding remains challenging for Vision-Language Models (VLMs) due to the inherent tension between computational constraints and the need to capture information distributed across thousands of frames. Existing…
The ability to understand and reason about spatial relationships between objects in images is an important component of visual reasoning. This skill rests on the ability to recognize and localize objects of interest and determine their…
Multimodal Large Language Models (MLLMs) often struggle to accurately perceive fine-grained visual details, especially when targets are tiny or visually subtle. This challenge can be addressed through semantic-visual information fusion,…
Medical imaging provides critical evidence for clinical diagnosis, treatment planning, and surgical decisions, yet most existing imaging models are narrowly focused and require multiple specialized networks, limiting their generalization.…
Foundation models have indeed made a profound impact on various fields, emerging as pivotal components that significantly shape the capabilities of intelligent systems. In the context of intelligent vehicles, leveraging the power of…
Although most current large multimodal models (LMMs) can already understand photos of natural scenes and portraits, their understanding of abstract images, e.g., charts, maps, or layouts, and visual reasoning capabilities remains quite…
Visual-Language Navigation (VLN) is a fundamental challenge in robotic systems, with broad applications for the deployment of embodied agents in real-world environments. Despite recent advances, existing approaches are limited in long-range…
Retinal image analysis is crucial for diagnosing and treating eye diseases, yet generating accurate medical reports from images remains challenging due to variability in image quality and pathology, especially with limited labeled data.…