Lemeng Wu
21 papers · 2019–2026 · 8 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+11 more ↓ Show less ↑
π Interdisciplinary Bridge π Academic Marathon (6) π Conference Polyglot (7) π Renaissance Researcher (6) πΊοΈ Taxonomy Completionist (36)
πΊοΈ
Taxonomy Completionist
(36)
π§
Keyword Pioneer
π£
Hot Topic Early Bird
π
Keyword Champion
π
Grand Slam
π§¬
Topic Evolution
π€
Dynamic Duo
(13)
ποΈ
Keyword Collector
(86)
β
The Questioner
β‘
Prolific Year
(5)
π
Century Club
(20)
Conferences
NIPS (7)
CVPR (6)
ICLR (2)
ICML (2)
AAAI (1)
ACL (1)
ICCV (1)
NAACL (1)
Top co-authors
Keywords
model compression
(6)
diffusion model
(5)
generative model
(3)
ordinary differential equation
(2)
point cloud generation
(2)
vision transformer
(2)
segment anything model
(2)
knowledge distillation
(2)
neural network
(2)
stochastic gradient descent
(1)
ensemble learning
(1)
probabilistic modeling
(1)
video segmentation
(1)
catastrophic forgetting
(1)
lottery ticket hypothesis
(1)
network architecture
(1)
neural architecture search
(1)
continual learning
(1)
scene reconstruction
(1)
graph generation
(1)
Papers
MobileLLM-Flash: Latency-Guided On-Device LLM Design for Industry Scale Deployment
ACL 2026
LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding
ICML 2025
Longhorn: State Space Models are Amortized Online Learners
ICLR 2025
Efficient Track Anything
ICCV 2025
EdgeTAM: On-Device Track Anything Model
CVPR 2025
Steepest Descent Density Control for Compact 3D Gaussian Splatting
CVPR 2025
Communication Efficient Distributed Training with Distributed Lion
NIPS 2024
LanguageFlow: Advancing Diffusion Language Generation with Probabilistic Flows
NAACL 2024
EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything
CVPR 2024
PrivCirNet: Efficient Private Inference via Block Circulant Transformation
NIPS 2024
Layer Compression of Deep Networks with Straight Flows
AAAI 2024
FlowGrad: Controlling the Output of Generative ODEs With Gradients
CVPR 2023
Fast Point Cloud Generation With Straight Flows
CVPR 2023
Learning Diffusion Bridges on Constrained Domains
ICLR 2023
How to Fill the Optimum Set? Population Gradient Descent with Harmless Diversity
ICML 2022
Diffusion-based Molecule Generation with Informative Prior Bridges
NIPS 2022
First Hitting Diffusion Models for Generating Manifold, Graph and Categorical Data
NIPS 2022
Greedy Optimization Provably Wins the Lottery: Logarithmic Number of Winning Tickets is Enough
NIPS 2020
Firefly Neural Architecture Descent: a General Approach for Growing Neural Networks
NIPS 2020
Path-Invariant Map Networks
CVPR 2019
Splitting Steepest Descent for Growing Neural Architectures
NIPS 2019