Yeonju Ro
6 papers · 2022–2025 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
π Interdisciplinary Bridge π§ Keyword Pioneer π Conference Polyglot (5) π Cross-Pollinator (4) π Renaissance Researcher (5)
πΊοΈ
Taxonomy Completionist
(14)
π£
Hot Topic Early Bird
Conferences
ICML (2)
CVPR (1)
EMNLP (1)
NIPS (1)
NSDI (1)
Top co-authors
Keywords
model compression
(3)
neural network compression
(1)
autoregressive decoding
(1)
data augmentation
(1)
ensemble training
(1)
early exit
(1)
reconstruction error
(1)
distributed training
(1)
mixture of expert
(1)
inference optimization
(1)
layer skipping
(1)
weight quantization
(1)
inference acceleration
(1)
expert routing
(1)
post-training quantization
(1)
request scheduling
(1)
tail latency
(1)
datacenter networking
(1)
load balancing
(1)
neural network quantization
(1)
Papers
On-the-Fly Adaptive Distillation of Transformer to Dual-State Linear Attention for Long-Context LLM Serving
ICML 2025
$\textit{Read-ME}$: Refactorizing LLMs as Router-Decoupled Mixture of Experts with System Co-Design
NIPS 2024
FFN-SkipLLM: A Hidden Gem for Autoregressive Decoding with Adaptive Feed Forward Skipping
EMNLP 2024
Lowering the Pre-training Tax for Gradient-based Subset Training: A Lightweight Distributed Pre-Training Toolkit
ICML 2023
RingLeader: Efficiently Offloading Intra-Server Orchestration to NICs
NSDI 2023
Mr.BiQ: Post-Training Non-Uniform Quantization Based on Minimizing the Reconstruction Error
CVPR 2022