Guangxuan Xiao
8 papers · 2023–2025 · 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
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(12)
🐣
Hot Topic Early Bird
👑
Triple Crown
Venues
Top co-authors
Research topics
Keywords
large language model
(4)
attention mechanism
(3)
model compression
(3)
weight quantization
(2)
kv cache
(2)
inference acceleration
(2)
inference efficiency
(2)
streaming inference
(1)
parameter-efficient fine-tuning
(1)
attention head
(1)
multi-tenant serving
(1)
knowledge compression
(1)
inference latency
(1)
weight activation quantization
(1)
self attention
(1)
retrieval head
(1)
attention sink
(1)
context memory
(1)
block-sparse attention
(1)
activation quantization
(1)
Papers
DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads
ICLR 2025
Retrieval Head Mechanistically Explains Long-Context Factuality
ICLR 2025
XAttention: Block Sparse Attention with Antidiagonal Scoring
ICML 2025
BitDelta: Your Fine-Tune May Only Be Worth One Bit
NeurIPS 2024
Efficient Streaming Language Models with Attention Sinks
ICLR 2024
InfLLM: Training-Free Long-Context Extrapolation for LLMs with an Efficient Context Memory
NeurIPS 2024
QUEST: Query-Aware Sparsity for Efficient Long-Context LLM Inference
ICML 2024
SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models
ICML 2023