Speaker: Dr. Jiaming Song (Luma AI) Title: "Dream Machine: Emergent Capabilities from Video Foundation Models" Video: Click here to view Abstract:  Dream Machine is a new video generative foundation model developed by Luma AI. We will show how Dream Machine exhibits some emergent capabilities that relate to vision, such as depth, segmentation, light transport, dynamics, […]

Speaker: Dr. Aleksander Hołyński (Google) Title: How I Learned to Stop Worrying and Love the Data Monster Video: Click here to view Abstract:  Recent advances in visual generative models have led to the generation of high quality, diverse images and videos of nearly any imaginable concept, thanks to increasingly large models and huge training datasets. […]

Speaker: Dr. Haomiao Jiang (Roblox) Title: Photo-to-Avatar: Personalized Avatar Creation with Generative AI Video: Click here to view Abstract: Digital personalized avatars are essential for user identity in the metaverse, and their creation has become an exciting area of research with applications in gaming, digital twins, and more. With the rapid advancements in machine learning […]

Speaker: Dr. Robin Rombach (Black Forest Labs) Title:"From Latent Diffusion to FLUX and Beyond: Scaling Efficient Content Creation" Video: Click here to view Bio: Robin is the CEO and co-founder of Black Forest Labs.  After studying physics at the University of Heidelberg from 2013-2020, he started a PhD in computer science in the Computer Vision […]

Speaker: Dr. Nikhil Naik Title: "Diffusion Model Alignment with Direct Preference Optimization" Video: Click here to view Abstract: Large language models (LLMs) are fine-tuned using human comparison data with Reinforcement Learning from Human Feedback (RLHF) methods to make them better aligned with users' preferences. In contrast to LLMs, human preference learning has not been widely […]

Speaker: Dr. Kevin Zhou (UC Berkeley) Title: Computational 3D and 4D imaging at high spatiotemporal throughput Video: Click here to view Abstract: Conventional imaging systems have difficulties scaling to high spatiotemporal throughput, rendering it challenging or impossible to study complex and highly dynamic biological systems. In particular, due to physical limitations of hardware-only systems, it […]

Speaker: Berthy Feng (Caltech) Title: Diffusion Models as Data-driven and Physics-informed Priors for Bayesian Imaging Video: Click here to view Abstract:  Priors are essential for solving ill-posed imaging problems, affecting both the quality and uncertainty of reconstructed images. Diffusion models can express complex image priors, but recent approaches extending diffusion models to inverse problems do […]

Speaker: Dr. Kalyan Sunkavalli (Adobe) Title: 3D Graphics in the age of Generative AI Video: Click here to view Abstract:  2D generative models are now able to synthesize increasingly high-quality images and videos. This has interesting implications for 3D graphics tools that have been developed for essentially the same goal. In this talk, I will […]

Speaker: Dr. Rick Chang (Apple) Title:  "The pursuit of a good shape representation" Video: Click here to view Abstract:  How should we represent 3D shapes in modern learning systems? While representations like meshes, voxels, 3D Gaussians, density and distance fields excel in computer graphics and physics simulations, one would argue that for machine learning, a […]

Speaker: Dr. Elliot Wu Title: Recreating the Physical Natural World from Images Video: Click here to view Abstract:  Today, generative AI models excel at recreating the visual world through pixels, but often struggle with the comprehension of basic physical concepts such as 3D shape, motion, material, and lighting---key elements that connect computer vision to a […]