Related papers: Thinking with Gaze: Sequential Eye-Tracking as Vis…
Vision-language models (VLMs) show promise in drafting radiology reports, yet they frequently suffer from logical inconsistencies, generating diagnostic impressions unsupported by their own perceptual findings or missing logically entailed…
Vision-language models (VLMs) excel at multimodal understanding, yet their text-only decoding forces them to verbalize visual reasoning, limiting performance on tasks that demand visual imagination. Recent attempts train VLMs to render…
Visualizing gaze data is an effective way for the quick interpretation of eye tracking results. This paper presents a study investigation benefits and limitations of visual gaze analysis among eye tracking professionals and researchers. The…
Existing deep learning methods for radiology report generation enhance diagnostic efficiency but often overlook physician-informed medical priors. This leads to a suboptimal alignment between the structured explanations and disease…
Recent advances in Multimodal Large Language Models (MLLMs) have significantly improved performance on tasks such as visual grounding and visual question answering. However, the reasoning processes of these models remain largely opaque;…
Obtaining large-scale radiology reports can be difficult for medical images due to various reasons, limiting the effectiveness of contrastive pre-training in the medical image domain and underscoring the need for alternative methods. In…
Recent Large Vision-Language Models (LVLMs) demonstrate remarkable capabilities in image understanding and natural language generation. However, current approaches focus predominantly on global image understanding, struggling to simulate…
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…
Recent advances in vision-language models (VLMs) emphasize long chain-of-thought reasoning; yet, we find that their performance on visual tasks is primarily limited by a lack of visual perception as opposed to reasoning itself. In this…
Vision-Language Models (VLMs) have recently gained attention due to their competitive performance on multiple downstream tasks, achieved by following user-input instructions. However, VLMs still exhibit several limitations in visual…
Gaze following requires both scene understanding and gaze reasoning to localize the gaze target of an in-scene person. Recently, vision foundation models (VFMs) have demonstrated strong performance on this task, enabling simpler…
Medical vision--language models (VLMs) have shown strong potential for medical visual question answering (VQA), yet their reasoning remains largely text-centric: images are encoded once as static context, and subsequent inference is…
Vision-language models (VLMs) are powerful but remain opaque black boxes. We introduce the first framework for transparent circuit tracing in VLMs to systematically analyze multimodal reasoning. By utilizing transcoders, attribution graphs,…
Visual attention serves as the primary mechanism through which MLLMs interpret visual information; however, its limited localization capability often leads to hallucinations. We observe that although MLLMs can accurately extract visual…
Vision-Language Models (VLMs) are expected to be capable of reasoning with commonsense knowledge as human beings. One example is that humans can reason where and when an image is taken based on their knowledge. This makes us wonder if,…
Contextual cues related to a person's pose and interactions with objects and other people in the scene can provide valuable information for gaze following. While existing methods have focused on dedicated cue extraction methods, in this…
Despite advances in Vision-Language-Action (VLA) models, robotic manipulation struggles with fine-grained tasks because current models lack mechanisms for active visual attention allocation. Human gaze naturally encodes intent, planning,…
Recent advancements in Computer Assisted Diagnosis have shown promising performance in medical imaging tasks, particularly in chest X-ray analysis. However, the interaction between these models and radiologists has been primarily limited to…
Following the gaze of people inside videos is an important signal for understanding people and their actions. In this paper, we present an approach for following gaze across views by predicting where a particular person is looking…
Technical progress in hardware and software enables us to record gaze data in everyday situations and over long time spans. Among a multitude of research opportunities, this technology enables visualization researchers to catch a glimpse…