Sheng Lu
5 papers · 2023–2026 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
π Conference Polyglot (3) π Interdisciplinary Bridge π§ Keyword Pioneer πΊοΈ Taxonomy Completionist (15) π Cross-Pollinator (10)
π
Renaissance Researcher
(5)
β
The Questioner
(2)
Conferences
EMNLP (2)
AAAI (1)
ACL (1)
NAACL (1)
Top co-authors
Keywords
in-context learning
(3)
large language model
(2)
prompt engineering
(1)
topic modeling
(1)
linguistic knowledge
(1)
exemplar selection
(1)
edge computing
(1)
inference acceleration
(1)
prompt sensitivity
(1)
speculative decoding
(1)
model acceleration
(1)
greedy decoding
(1)
emergent abilities
(1)
aspect extraction
(1)
information measure
(1)
text clustering
(1)
model memory
(1)
ability evaluation
(1)
gradient-based saliency
(1)
emergent ability
(1)
Papers
DIAA: A Decoding-Efficient Inference Acceleration Approach for On-Device Large Language Models
AAAI 2026
Identifying Aspects in Peer Reviews
EMNLP 2025
Are Emergent Abilities in Large Language Models just In-Context Learning?
ACL 2024
How are Prompts Different in Terms of Sensitivity?
NAACL 2024
Measuring Pointwise π±-Usable Information In-Context-ly
EMNLP 2023