Most image generation models rely on uniform tokenization, allocating the exact same computational budget to equally-sized image patches. This static paradigm cannot adapt to different resource constraints at inference time, and yields suboptimal quality-cost tradeoff by devoting the same effort to both plain backgroun...
Ozgur Kara, Yujia Chen, Daniel Watson et al.· 0 citations
Diffusion models have become the dominant family of generative models in the visual domain. However, their widespread public availability enables misuse at scale, motivating a rapidly growing body of research on adversarial attacks and defenses. This survey provides, to our knowledge, the first unified review of this l...
Ozgur Kara, Tarik Can Ozden, Furkan Horoz et al.· 0 citations
Learning Reference Coordinate Frames for Perspective Taking is introduced, a framework that trains VLMs to construct and use explicit reference frames for viewpoint-dependent reasoning and consistently improves over its backbone and achieves strong performance against existing open-source methods.
Bang Xiao, Wen-Qi Jia, Ozgur Kara et al.· 0 citations
Kirin is introduced, a framework that reconstructs motion from video, learns motion priors at scale, and generates realistic motion that can be directly applied to animated assets that establishes a new foundation for large-scale, text and image conditioned animal motion generation and animation.
Brian Nlong Zhao, Zhuo-Yang Pan, J. Rehg et al.· 1 citation
This work introduces RIG-BENCH, a novel comprehensive benchmark that systematically evaluates Reasoning-driven Image Generation (RIG) across four cognitively demanding domains: Concept-based, Transformation-based, Pattern&Structure, and Scenario-based.
ConvDeck is introduced, a multi-agent pipeline for conversational paper-to-slide generation that distributes interaction across the pipeline through stage-specific loops, allowing users to iteratively refine both the presentation outline and the final slide deck at the stages where each kind of decision is made.
Tarik Can Ozden, VS Sachidanand, Furkan Horoz et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
