Carole-Jean Wu
7 papers · 2022–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+4 more ↓ Show less ↑
π£ Hot Topic Early Bird π§ Keyword Pioneer π Conference Polyglot (4) πΊοΈ Taxonomy Completionist (30) π Interdisciplinary Bridge
π
Cross-Pollinator
(11)
π
Renaissance Researcher
(6)
π₯
Mega-Team
(47)
π
Trend Setter
Conferences
NIPS (4)
ACL (1)
EMNLP (1)
ICML (1)
Top co-authors
Keywords
large language model
(2)
inference optimization
(2)
model compression
(2)
efficient inference
(2)
machine translation
(1)
model evaluation
(1)
benchmark suite
(1)
knowledge distillation
(1)
empirical study
(1)
early exit
(1)
machine learning
(1)
synthetic datum
(1)
scaling law
(1)
mixture of expert
(1)
throughput optimization
(1)
model collapse
(1)
data quality
(1)
recommendation system
(1)
language modeling
(1)
collaborative filtering
(1)
Papers
Demystifying Synthetic Data in LLM Pre-training: A Systematic Study of Scaling Laws, Benefits, and Pitfalls
EMNLP 2025
Croissant: A Metadata Format for ML-Ready Datasets
NIPS 2024
Toward Efficient Inference for Mixture of Experts
NIPS 2024
LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding
ACL 2024
CHAI: Clustered Head Attention for Efficient LLM Inference
ICML 2024
DataPerf: Benchmarks for Data-Centric AI Development
NIPS 2023
Infinite Recommendation Networks: A Data-Centric Approach
NIPS 2022