ResearchAlpha Leak

Conferences Topics Top Authors Rankings Browse All

Home/Authors/Michael Ryoo

Michael Ryoo

Topic trends: 32,543 papers · similarity ≥ 0.4 · year ≥ 2024 · Data sourced from Semantic Scholar

34,598 papers | Abstracts: 31,650 (91.5%) | Citations: 34,598 (100.0%) | arXiv: 26,074 (75.4%)

Built: Feb 15, 2026, 3:13 AM AMS

10

papers

328

total citations

papers (10)

Learning to Localize Objects Improves Spatial Reasoning in Visual-LLMs

Go-with-the-Flow: Motion-Controllable Video Diffusion Models Using Real-Time Warped Noise

Adaptive Caching for Faster Video Generation with Diffusion Transformers

AViD Dataset: Anonymized Videos from Diverse Countries

NEURIPS 2020arXiv

VicTR: Video-conditioned Text Representations for Activity Recognition

Does Self-supervised Learning Really Improve Reinforcement Learning from Pixels?

NEURIPS 2022arXiv

Mirasol3B: A Multimodal Autoregressive Model for Time-Aligned and Contextual Modalities

Learning Viewpoint-Agnostic Visual Representations by Recovering Tokens in 3D Space

NEURIPS 2022arXiv

TokenLearner: Adaptive Space-Time Tokenization for Videos

MAGICK: A Large-scale Captioned Dataset from Matting Generated Images using Chroma Keying