Shangyu Wu
4 papers · 2024–2025 · 3 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
🗺️
Taxonomy Completionist
(10)
📈
Trend Setter
Top co-authors
Research topics
Keywords
model compression
(3)
post-training quantization
(1)
attention mechanism
(1)
natural language understanding
(1)
efficient inference
(1)
vector quantization
(1)
model inference
(1)
bilevel optimization
(1)
hidden state
(1)
feed-forward network
(1)
inference optimization
(1)
inference efficiency
(1)
weight quantization
(1)
kv cache
(1)
long context
(1)
knowledge-intensive task
(1)
bit-width allocation
(1)
small language model
(1)
retrieval-based augmentation
(1)
activation sparsification
(1)
Papers
A2ATS: Retrieval-Based KV Cache Reduction via Windowed Rotary Position Embedding and Query-Aware Vector Quantization
ACL 2025
MLWQ: Efficient Small Language Model Deployment via Multi-Level Weight Quantization
EMNLP 2025
CHESS: Optimizing LLM Inference via Channel-Wise Thresholding and Selective Sparsification
EMNLP 2024
ReFusion: Improving Natural Language Understanding with Computation-Efficient Retrieval Representation Fusion
ICLR 2024