Ligeng Zhu
15 papers · 2018–2025 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+9 more ↓ Show less ↑
π Renaissance Researcher (5) π Interdisciplinary Bridge π Academic Marathon (7) π Conference Polyglot (6) πΊοΈ Taxonomy Completionist (17)
π
Academic Marathon
(7)
πΊοΈ
Taxonomy Completionist
(17)
π
Cross-Pollinator
(15)
π₯
Mega-Team
(25)
π€
Dynamic Duo
(14)
π₯
Unstoppable
(5)
π
Century Club
(15)
π
Conference Pioneer
β‘
Prolific Year
(7)
Conferences
ICLR (5)
NIPS (4)
ECCV (2)
ICML (2)
ACL (1)
CVPR (1)
Top co-authors
Research topics
Keywords
efficient computing
(3)
model compression
(3)
transfer learning
(2)
privacy attack
(1)
neural architecture search
(1)
efficient inference
(1)
parameter efficient
(1)
distributed training
(1)
data privacy
(1)
memory efficiency
(1)
on-device training
(1)
quantization-aware training
(1)
on-device learning
(1)
local computation
(1)
token compression
(1)
visual language model
(1)
hardware optimization
(1)
feature adaptation
(1)
spatial resolution
(1)
gradient leakage
(1)
Papers
COAT: Compressing Optimizer states and Activations for Memory-Efficient FP8 Training
ICLR 2025
VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation
ICLR 2025
LongVILA: Scaling Long-Context Visual Language Models for Long Videos
ICLR 2025
SparseLoRA: Accelerating LLM Fine-Tuning with Contextual Sparsity
ICML 2025
SANA: Efficient High-Resolution Text-to-Image Synthesis with Linear Diffusion Transformers
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
On-Device Training Under 256KB Memory
NIPS 2022
Delayed Gradient Averaging: Tolerate the Communication Latency for Federated Learning
NIPS 2021
DataMix: Efficient Privacy-Preserving Edge-Cloud Inference
ECCV 2020
TinyTL: Reduce Memory, Not Parameters for Efficient On-Device Learning
NIPS 2020
HAT: Hardware-Aware Transformers for Efficient Natural Language Processing
ACL 2020
ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware
ICLR 2019
Deep Leakage from Gradients
NIPS 2019
Sparsely Aggregated Convolutional Networks
ECCV 2018