Shih-Yang Liu
6 papers · 2022–2025 · 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 ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(17)
🐣
Hot Topic Early Bird
Top co-authors
Research topics
Deep Learning
(6)
Machine Learning
(6)
Artificial Intelligence
(5)
Application Areas
(5)
Core AI · Artificial Intelligence
(5)
Architectures
(4)
Optimization & Theory · Deep Learning
(3)
Optimization & Theory · Machine Learning
(2)
Computer Vision
(1)
Data Science & Analytics
(1)
Core AI · Computer Vision
(1)
Core Methods
(1)
Learning Types
(1)
Methods
(1)
Keywords
weight quantization
(2)
large language model
(2)
post-training quantization
(1)
vision transformer
(1)
attention mechanism
(1)
deep learning
(1)
efficient computing
(1)
meta tokens
(1)
time series forecasting
(1)
matrix prediction
(1)
state space model
(1)
parameter-efficient fine-tuning
(1)
low-rank adaptation
(1)
low-bit quantization
(1)
weight decomposition
(1)
weight activation quantization
(1)
quantization-aware training
(1)
fine tuning
(1)
activation outlier
(1)
financial forecasting
(1)
Papers
Hymba: A Hybrid-head Architecture for Small Language Models
ICLR 2025
DoRA: Weight-Decomposed Low-Rank Adaptation
ICML 2024
RoLoRA: Fine-tuning Rotated Outlier-free LLMs for Effective Weight-Activation Quantization
EMNLP 2024
LLM-FP4: 4-Bit Floating-Point Quantized Transformers
EMNLP 2023
Oscillation-free Quantization for Low-bit Vision Transformers
ICML 2023
Forecasting Asset Dependencies to Reduce Portfolio Risk
AAAI 2022