Scholar
Lemeng Wu
Google Scholar ID: PCDSl2sAAAAJ
Computer Science Ph.D, UT Austin
Citations & Impact
Citations
1,434
H-index
17
i10-index
22
Publications
20
Co-authors
11
list available
Contact
Publications
Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
- Fast Point Cloud Generation with Straight Flows (CVPR 2023)
- FlowGrad: Controlling the Output of Generative ODEs with Gradients (CVPR 2023)
- PathFusion: Path-consistent Lidar-Camera Deep Feature Fusion (Arxiv Preprint)
- Learning Diffusion Bridges on Constrained Domains (ICLR 2023)
- Neural Volumetric Mesh Generator (NeurIPS 2022 Workshop on Score-Based Methods)
- Diffusion-based Molecule Generation with Informative Prior Bridges (NeurIPS 2022)
- First Hitting Diffusion Models (NeurIPS 2022)
- How to Fill the Optimum Set? Population Gradient Descent with Harmless Diversity (ICML 2022)
- Residual Mixture of Experts (Arxiv Preprint)
- Fusedream: Training-free text-to-image generation with improved clip+ gan space optimization (Arxiv Preprint)
- Centroid transformers: Learning to abstract with attention (Arxiv Preprint)
- Firefly Neural Architecture Descent: a General Approach for Growing Neural Networks (NeurIPS 2020)
- Greedy Optimization Provably Wins the Lottery: Logarithmic Number of Winning Tickets is Enough (NeurIPS 2020)
- Energy-Aware Neural Architecture Optimization with Fast Splitting Steepest Descent (NeurIPS 2019 Workshop)
- Splitting Steepest Descent for Progressive Training of Neural Networks (NeurIPS 2019 Spotlight)
- Path-Invariant Map Networks (CVPR 2019 Oral Presentation)
Education
- Ph.D. student in Computer Science at The University of Texas at Austin, advised by Professor Qiang Liu.
Background
- Research interests: building efficient models and developing generative models for vision and 3D tasks.
