Yingyan (Celine) Lin
8 papers · 2023–2024 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+4 more ↓ Show less ↑
π£ Hot Topic Early Bird π Interdisciplinary Bridge π§ Keyword Pioneer π Conference Polyglot (3) π Cross-Pollinator (10)
π
Renaissance Researcher
(6)
πΊοΈ
Taxonomy Completionist
(28)
β‘
Prolific Year
(5)
π
Trend Setter
Conferences
NIPS (4)
CVPR (3)
ECCV (1)
Top co-authors
Keywords
model compression
(2)
efficient inference
(2)
large language model
(2)
vision transformer
(2)
novel view synthesis
(2)
knowledge distillation
(1)
foundation model
(1)
ensemble learning
(1)
neural rendering
(1)
virtual reality
(1)
few-shot learning
(1)
parameter-efficient fine-tuning
(1)
low-rank adaptation
(1)
3d gaussian splatting
(1)
neural architecture search
(1)
real-time rendering
(1)
neural radiance field
(1)
parameter-efficient tuning
(1)
data augmentation
(1)
feature learning
(1)
Papers
3D Gaussian Rendering Can Be Sparser: Efficient Rendering via Learned Fragment Pruning
NIPS 2024
ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization
NIPS 2024
AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment
NIPS 2024
Rad-NeRF: Ray-decoupled Training of Neural Radiance Field
NIPS 2024
Omni-Recon: Harnessing Image-based Rendering for General-Purpose Neural Radiance Fields
ECCV 2024
Auto-CARD: Efficient and Robust Codec Avatar Driving for Real-Time Mobile Telepresence
CVPR 2023
Hint-Aug: Drawing Hints From Foundation Vision Transformers Towards Boosted Few-Shot Parameter-Efficient Tuning
CVPR 2023
Castling-ViT: Compressing Self-Attention via Switching Towards Linear-Angular Attention at Vision Transformer Inference
CVPR 2023