Zichang Liu
7 papers · 2021–2023 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
π Cross-Pollinator (15) π Conference Polyglot (4) π Renaissance Researcher (6) π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (17)
π§
Keyword Pioneer
π£
Hot Topic Early Bird
π
Triple Crown
Conferences
NIPS (3)
ICLR (2)
CVPR (1)
ICML (1)
Top co-authors
Keywords
inference efficiency
(2)
large language model
(2)
inference optimization
(2)
catastrophic forgetting
(1)
vision transformer
(1)
robotic manipulation
(1)
object detection
(1)
attention mechanism
(1)
in-context learning
(1)
point cloud
(1)
incremental learning
(1)
sparse approximation
(1)
robot grasping
(1)
memory efficiency
(1)
data heterogeneity
(1)
memory optimization
(1)
attention head
(1)
client selection
(1)
kv cache compression
(1)
contextual sparsity
(1)
Papers
Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Time
ICML 2023
Learning Multimodal Data Augmentation in Feature Space
ICLR 2023
Scissorhands: Exploiting the Persistence of Importance Hypothesis for LLM KV Cache Compression at Test Time
NIPS 2023
One-Pass Distribution Sketch for Measuring Data Heterogeneity in Federated Learning
NIPS 2023
SAR-Net: Shape Alignment and Recovery Network for Category-Level 6D Object Pose and Size Estimation
CVPR 2022
Retaining Knowledge for Learning with Dynamic Definition
NIPS 2022
MONGOOSE: A Learnable LSH Framework for Efficient Neural Network Training
ICLR 2021