Scholar
Lingxiao Li
Google Scholar ID: rxQDLWcAAAAJ
Netflix
Citations & Impact
Citations
747
H-index
10
i10-index
10
Publications
16
Co-authors
3
list available
Publications
Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
- Publications:
- - Correctness-Guaranteed Code Generation via Constrained Decoding
- - Go-with-the-Flow: Motion-Controllable Video Diffusion Models Using Real-Time Warped Noise
- - Infinite-Resolution Integral Noise Warping for Diffusion Models
- - Scalable Methodologies for Optimizing Over Probability Distributions (PhD thesis)
- - Debiased Distribution Compression
- - Self-Consistent Velocity Matching of Probability Flows
- - Sampling with Mollified Interaction Energy Descent
- - Learning Proximal Operators to Discover Multiple Optima
- - Wasserstein Iterative Networks for Barycenter Estimation
- - Interactive All-Hex Meshing via Cuboid Decomposition
- - Do Neural Optimal Transport Solvers Work? A Continuous Wasserstein-2 Benchmark
- - Large-Scale Wasserstein Gradient Flows
- - Continuous Wasserstein-2 Barycenter Estimation without Minimax Optimization
Research Experience
- Research Scientist at Netflix, working to push the boundaries of entertainment through AI innovation.
Education
- Ph.D. from MIT, advised by Justin Solomon; B.S. in Computer Science and Mathematics, and M.S. in Mathematics, both from Stanford University.
Background
- Research Interests: Pushing the boundaries of entertainment through AI innovation, particularly in video games. Believes that AI can empower player creativity, enabling entirely new forms of AI-assisted expression.
