Ligeng Zhu
16 papers · 2018–2026 · 6 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+8 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (25) π Academic Marathon Β· Sprint π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Bronze π£ Hot Topic Early Bird
π§
Keyword Pioneer
π₯
Mega-Team Β· Squad
π€
Dynamic Duo
(15)
β‘
Prolific Year Β· Productive
π₯
Unstoppable Β· Bronze
π
Century Club Β· Bronze
π
Conference Pioneer
ποΈ
Keyword Collector
(59)
Top co-authors
Research topics
Artificial Intelligence
(11)
Deep Learning
(10)
Core AI
(10)
Machine Learning
(9)
Application Areas
(7)
Architectures
(6)
Optimization & Theory Β· Machine Learning
(5)
Computer Vision
(3)
Models
(3)
Optimization & Theory Β· Deep Learning
(3)
Techniques
(3)
Generation
(2)
Learning Paradigms
(2)
Learning Types
(2)
Natural Language Processing
(1)
Keywords
model compression
(5)
efficient computing
(3)
visual language model
(3)
transfer learning
(2)
neural architecture search
(2)
memory efficiency
(2)
hardware-aware design
(2)
image generation
(2)
autoregressive generation
(1)
parameter efficient
(1)
transformer architecture
(1)
distributed training
(1)
data privacy
(1)
diffusion model
(1)
computational cost
(1)
efficient inference
(1)
vision-language model
(1)
foundation model
(1)
convolutional neural network
(1)
video understanding
(1)
Papers
Grounded 3D-Aware Spatial Vision-Language Modeling
CVPR 2026
COAT: Compressing Optimizer states and Activations for Memory-Efficient FP8 Training
ICLR 2025
LongVILA: Scaling Long-Context Visual Language Models for Long Videos
ICLR 2025
NVILA: Efficient Frontier Visual Language Models
CVPR 2025
SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer
ICML 2025
SANA: Efficient High-Resolution Text-to-Image Synthesis with Linear Diffusion Transformers
ICLR 2025
SparseLoRA: Accelerating LLM Fine-Tuning with Contextual Sparsity
ICML 2025
VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation
ICLR 2025
On-Device Training Under 256KB Memory
NeurIPS 2022
Delayed Gradient Averaging: Tolerate the Communication Latency for Federated Learning
NeurIPS 2021
DataMix: Efficient Privacy-Preserving Edge-Cloud Inference
ECCV 2020
HAT: Hardware-Aware Transformers for Efficient Natural Language Processing
ACL 2020
TinyTL: Reduce Memory, Not Parameters for Efficient On-Device Learning
NeurIPS 2020
Deep Leakage from Gradients
NeurIPS 2019
ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware
ICLR 2019
Sparsely Aggregated Convolutional Networks
ECCV 2018