Shengyu Liu
6 papers · 2024–2026 · 4 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
π
Conference Polyglot Β· Bronze
π
Interdisciplinary Bridge Β· Silver
πΊοΈ
Taxonomy Completionist
(16)
π
Renaissance Researcher
(5)
Top co-authors
Research topics
Machine Learning
(5)
Optimization & Theory
(4)
Deep Learning
(3)
Natural Language Processing
(3)
Application Areas
(3)
Artificial Intelligence
(2)
Core AI
(2)
Resources & Methods
(2)
Computer Science
(1)
Computer Vision
(1)
Reinforcement Learning
(1)
Architectures
(1)
Domain-Specific
(1)
Learning Types
(1)
Methods
(1)
Keywords
large language model
(2)
model compression
(1)
transfer learning
(1)
attention mechanism
(1)
named entity recognition
(1)
autoregressive generation
(1)
graph representation
(1)
neural network optimization
(1)
model parallelism
(1)
reinforcement learning from human feedback
(1)
training optimization
(1)
dynamic programming
(1)
model pruning
(1)
kernel optimization
(1)
throughput optimization
(1)
layer-adaptive pruning
(1)
pre-trained language model
(1)
training throughput
(1)
gpu resource allocation
(1)
structured pruning
(1)
Papers
FastServe: Iteration-Level Preemptive Scheduling for Large Language Model Inference
NSDI 2026
GAP: a Global Adaptive Pruning Method for Large Language Models
EMNLP 2025
Mirage: A Multi-Level Superoptimizer for Tensor Programs
OSDI 2025
Multi-Domain Ancient Chinese Named Entity Recognition Based on Attention-Enhanced Pre-trained Language Model
NAACL 2025
Optimizing RLHF Training for Large Language Models with Stage Fusion
NSDI 2025
DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving
OSDI 2024