ResearchAlpha Leak

Conferences Topics Top Authors Rankings Browse All

Home/Authors/Lemeng Wu

Lemeng Wu

Topic trends: 31,945 papers · similarity ≥ 0.4 · year ≥ 2024 · Data sourced from Semantic Scholar

34,180 papers | Abstracts: 30,895 (90.4%) | Citations: 34,180 (100.0%) | arXiv: 25,727 (75.3%)

Built: Feb 6, 2026, 1:36 PM AMS

12

papers

291

total citations

papers (12)

EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything

Longhorn: State Space Models are Amortized Online Learners

Efficient Track Anything

EdgeTAM: On-Device Track Anything Model

Steepest Descent Density Control for Compact 3D Gaussian Splatting

Layer Compression of Deep Networks with Straight Flows

Fast Point Cloud Generation With Straight Flows

FlowGrad: Controlling the Output of Generative ODEs With Gradients

Greedy Optimization Provably Wins the Lottery: Logarithmic Number of Winning Tickets is Enough

NeurIPS 2020arXiv

Firefly Neural Architecture Descent: a General Approach for Growing Neural Networks

NeurIPS 2020arXiv

First Hitting Diffusion Models for Generating Manifold, Graph and Categorical Data

NeurIPS 2022arXiv

Diffusion-based Molecule Generation with Informative Prior Bridges

NeurIPS 2022arXiv