Published Mar 18, 2024
Video as a Universal Interface for AI Reasoning with Sherry Yang - 676
Sherry Yang from Google DeepMind delves into the transformative potential of video as a universal interface for AI reasoning, exploring how it can simulate real-world tasks, enhance decision-making, and serve as a unified data format akin to language models. The discussion highlights the challenges, advancements, and future innovations in video-based AI, offering new perspectives on AI-driven simulations and problem-solving.

Topics covered
Popular Clips
Episode Highlights
Related Episodes


AI Agents for Data Analysis with Shreya Shankar - 703
Answers 383 questions

Gen AI at the Edge: Qualcomm AI Research at CVPR 2024 with Fatih Porikli - 688
Answers 383 questions

Visual Generative AI Ecosystem Challenges with Richard Zhang - 656
Answers 383 questions

Generating SQL [Database Queries] from Natural Language with Yanshuai Cao - #519
Answers 383 questions

Unifying Vision and Language Models with Mohit Bansal - 636
Answers 383 questions

What’s Next in LLM Reasoning? with Roland Memisevic - 646
Answers 383 questions

Social Commonsense Reasoning with Yejin Choi - 518
Answers 383 questions

Learning Visiolinguistic Representations with ViLBERT w/ Stefan Lee - #358
Answers 383 questions

Genie: Generative Interactive Environments with Ashley Edwards - 696
Answers 383 questions

AI Agents and Data Integration with GPT and LLaMa with Jerry Liu - 628
Answers 383 questions

Symbolic and Subsymbolic Natural Language Processing with Jonathan Mugan - #49
Answers 383 questions

Simulation and Synthetic Data for Computer Vision with Batu Arisoy - TWiML Talk #281
Answers 383 questions

Automated Reasoning to Prevent LLM Hallucination with Byron Cook - 712
Answers 383 questions

Spatiotemporal Data Analysis with Rose Yu - #508
Answers 383 questions














