Kayvon Fatahalian

Stanford University — United States

Computer Science · Physical Sciences

30h-index4.8kcitations108works3.42yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Computer Graphics and Visualization Techniques(33), 3D Shape Modeling and Analysis(17), Parallel Computing and Optimization Techniques(16), Video Analysis and Summarization(14), Advanced Vision and Imaging(13)

Publications108 total

In-Context Distillation with Self-Consistency Cascades: A Simple, Training-Free Way to Reduce LLM Agent Costs
arXiv (Cornell University)·2025Open Access
Learning to Ball: Composing Policies for Long-Horizon Basketball Moves
ACM Transactions on Graphics·2025Open Access
Axes-and-Tags: LLM-Driven Design Galleries for Generative Content
2025
Generating Detailed Character Motion from Blocking Poses
arXiv (Cornell University)·2025Open Access
Self-Generated In-Context Examples Improve LLM Agents for Sequential Decision-Making Tasks
arXiv (Cornell University)·2025Open Access
Generative Motion Infilling from Imprecisely Timed Keyframes
Computer Graphics Forum·2025· 2 citedOpen Access
Cube: A Roblox View of 3D Intelligence
arXiv (Cornell University)·2025· 1 citedOpen Access
Generative Motion Infilling From Imprecisely Timed Keyframes
arXiv (Cornell University)·2025Open Access
High-Throughput Batch Rendering for Embodied AI
2024Open Access
AI Metropolis: Scaling Large Language Model-based Multi-Agent Simulation with Out-of-order Execution
arXiv (Cornell University)·2024Open Access
Block and Detail: Scaffolding Sketch-to-Image Generation
2024· 12 cited
Automated Rewards via LLM-Generated Progress Functions
arXiv (Cornell University)·2024Open Access
Learning to Move Like Professional Counter‐Strike Players
Computer Graphics Forum·2024· 5 cited
Learning to Move Like Professional Counter-Strike Players
arXiv (Cornell University)·2024Open Access
Iterative Motion Editing with Natural Language
2024· 15 cited
Learning Subject-Aware Cropping by Outpainting Professional Photos
Proceedings of the AAAI Conference on Artificial Intelligence·2024· 6 citedOpen Access
Block and Detail: Scaffolding Sketch-to-Image Generation
arXiv (Cornell University)·2024Open Access
Collage Diffusion
2024· 20 cited
Learning Subject-Aware Cropping by Outpainting Professional Photos
arXiv (Cornell University)·2023· 1 citedOpen Access
Iterative Motion Editing with Natural Language
arXiv (Cornell University)·2023Open Access
page 1 of 6Next →

Frequent Co-authors

Pat Hanrahan(17), Mike Houston(11), Yong He(6), Tim Foley(5), Daniel Reiter Horn(5), Jeremy Sugerman(5), William R. Mark(5), Kurt Akeley(5), Haotian Zhang(5), Maneesh Agrawala(5), Ian Buck(4), Timothy J. Knight(4), Manman Ren(4), Solomon Boulos(4), James Won‐Ki Hong(4), Matthew Fisher(4), Daniel Y. Fu(4), Mattan Erez(3), Michaël Gharbi(3), William J. Dally(3)