Visualization's design knowledge-effectiveness rankings, encoding guidelines, color models, preattentive processing rules -- derives from six decades of psychophysical studies of human vision. Yet vision-language models (VLMs) increasingly consume ch... read more
Logit Lens has been proposed for visualizing tokens that contribute most to LLM answers. Recently, Logit Lens was also shown to be applicable in autoregressive Vision-Language Models (VLMs), where it illustrates the conceptual content of image tokens... read more
Unified multimodal large language models (MLLMs) integrate image understanding and generation in a single framework, with the visual tokenizer acting as the sole interface that maps visual inputs into tokens for downstream tasks. However, existing sh... read more
Commonsense reasoning in multimodal contexts remains a foundational challenge in artificial intelligence. We introduce Multimodal UNcommonsense(MUN), a benchmark designed to evaluate models' ability to handle scenarios that deviate from typical visua... read more
Diffusion-based image compression methods have achieved notable progress, delivering high perceptual quality at low bitrates. However, their practical deployment is hindered by significant inference latency and heavy computational overhead, primarily... read more
Large vision-language models (VLMs) are vulnerable to transfer-based adversarial perturbations, enabling attackers to optimize on surrogate models and manipulate black-box VLM outputs. Prior targeted transfer attacks often overfit surrogate-specific ... read more
Camera-based visible light positioning (VLP) is a promising technique for accurate and low-cost indoor camera pose estimation (CPE). To reduce the number of required light-emitting diodes (LEDs), advanced methods commonly exploit LED shape features f... read more
3D hand pose estimation that involves accurate estimation of 3D human hand keypoint locations is crucial for many human-computer interaction applications such as augmented reality. However, this task poses significant challenges due to self-occlusion... read more
Spherical surface parameterization is a fundamental tool in geometry processing and imaging science. For a genus-0 closed surface, many efficient algorithms can map the surface to the sphere; consequently, a broad class of task-driven genus-0 mapping... read more
Join thousands of healthcare professionals staying informed about the latest AI breakthroughs in medicine. Get curated insights delivered to your inbox.