Awesome Multimodal
📄
Papers
🧭
Topics
🔥
Trending
🗺️
Map
🏆
Leaderboards
🎓
Learn
🤖
Ask AI
⋯
More
👥
Authors
📚
Reading Packs
📊
Datasets
🛠️
Tools
📰
News
📝
Blogs
✉️
Newsletter
🎯
Research Radar
🔖
Saved
+ Add Paper
☾
☀
← authors
·
overview
Loading author…
🤖
Ask AI
Pavel Tokmakov — most-cited papers & profile · Multimodal
← authors
·
overview
Pavel Tokmakov
9
papers ·
2
citations ·
15
h-index
Toyota Research Institute
Google Scholar ↗
Semantic Scholar ↗
OpenAlex ↗
Most-cited papers
Towards Segmenting Anything That Moves
2019 · 2 citations
RoboDream: Compositional World Models for Scalable Robot Data Synthesis
2026
Walk through Paintings: Egocentric World Models from Internet Priors
2026
AnchorDream: Repurposing Video Diffusion for Embodiment-Aware Robot Data Synthesis
2025
Video Generators are Robot Policies
2025
Learning to Segment Moving Objects
2017
Dreamitate: Real-World Visuomotor Policy Learning via Video Generation
2024
ReferEverything: Towards Segmenting Everything We Can Speak of in Videos
2024
Topics
Manipulation
Control
Segmentation
Video Understanding
Sim-to-Real
Human-Robot Interaction
Tracking
Navigation
Humanoid
Perception