Alvin Cheung
15 papers · 2016–2024 · 7 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+8 more ↓ Show less ↑
π Academic Marathon (8) π§ Keyword Pioneer π Interdisciplinary Bridge π Conference Polyglot (7) π Cross-Pollinator (12)
π
Cross-Pollinator
(12)
π
Renaissance Researcher
(6)
πΊοΈ
Taxonomy Completionist
(29)
π§¬
Topic Evolution
π
Century Club
(15)
π
Trend Setter
β‘
Prolific Year
(6)
ποΈ
Keyword Collector
(51)
Conferences
ACL (4)
ICML (4)
EMNLP (2)
IJCNLP (2)
IJCAI (1)
NAACL (1)
NIPS (1)
Top co-authors
Keywords
code generation
(5)
program synthesis
(5)
semantic parsing
(3)
code transpilation
(2)
hierarchical decoder
(2)
syntax tree
(2)
code idiom
(2)
source code
(1)
zero-shot generalization
(1)
sql generation
(1)
training dynamics
(1)
memory optimization
(1)
sequence model
(1)
model scaling
(1)
functional equivalence
(1)
bleu score
(1)
verified lifting
(1)
sequence-to-sequence learning
(1)
user feedback
(1)
layer freezing
(1)
Papers
Verified Code Transpilation with LLMs
NIPS 2024
AST-T5: Structure-Aware Pretraining for Code Generation and Understanding
ICML 2024
Evaluation of LLMs on Syntax-Aware Code Fill-in-the-Middle Tasks
ICML 2024
Online Speculative Decoding
ICML 2024
ADELT: Transpilation between Deep Learning Frameworks
IJCAI 2024
SlimFit: Memory-Efficient Fine-Tuning of Transformer-based Models Using Training Dynamics
NAACL 2024
Model-Generated Pretraining Signals Improves Zero-Shot Generalization of Text-to-Text Transformers
ACL 2023
GACT: Activation Compressed Training for Generic Network Architectures
ICML 2022
PlotCoder: Hierarchical Decoding for Synthesizing Visualization Code in Programmatic Context
ACL 2021
PlotCoder: Hierarchical Decoding for Synthesizing Visualization Code in Programmatic Context
IJCNLP 2021
Learning Programmatic Idioms for Scalable Semantic Parsing
IJCNLP 2019
Learning Programmatic Idioms for Scalable Semantic Parsing
EMNLP 2019
Mapping Language to Code in Programmatic Context
EMNLP 2018
Learning a Neural Semantic Parser from User Feedback
ACL 2017
Summarizing Source Code using a Neural Attention Model
ACL 2016