Oscar Li
5 papers · 2019–2024 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+4 more ↓ Show less ↑
π Conference Polyglot (3) π Academic Marathon (5) π Renaissance Researcher (6) π Interdisciplinary Bridge π Cross-Pollinator (15)
πΊοΈ
Taxonomy Completionist
(14)
π§
Keyword Pioneer
π£
Hot Topic Early Bird
π
Trend Setter
Conferences
NIPS (3)
EMNLP (1)
ICLR (1)
Top co-authors
Keywords
image classification
(1)
benchmark evaluation
(1)
few-shot learning
(1)
prototype learning
(1)
weakly supervised learning
(1)
neural network interpretability
(1)
gradient estimation
(1)
online optimization
(1)
variance reduction
(1)
distribution shift
(1)
task distribution
(1)
out-of-distribution evaluation
(1)
few-shot classification
(1)
deep network
(1)
prototypical part
(1)
evolution strategy
(1)
evolution strategies
(1)
interpretable deep learning
(1)
neural network
(1)
in-distribution evaluation
(1)
Papers
GRASS: Compute Efficient Low-Memory LLM Training with Structured Sparse Gradients
EMNLP 2024
Variance-Reduced Gradient Estimation via Noise-Reuse in Online Evolution Strategies
NIPS 2023
Label Leakage and Protection in Two-party Split Learning
ICLR 2022
Two Sides of Meta-Learning Evaluation: In vs. Out of Distribution
NIPS 2021
This Looks Like That: Deep Learning for Interpretable Image Recognition
NIPS 2019