Jiaoda Li
7 papers · 2021–2026 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+5 more ↓ Show less ↑
π£ Hot Topic Early Bird π Interdisciplinary Bridge π§ Keyword Pioneer π Conference Polyglot (3) π Cross-Pollinator (12)
π
Renaissance Researcher
(6)
πΊοΈ
Taxonomy Completionist
(23)
π₯
Unstoppable
(5)
π
Trend Setter
β
The Questioner
Conferences
ACL (3)
EMNLP (2)
NAACL (2)
Top co-authors
Keywords
transformer expressivity
(2)
language model
(2)
linear temporal logic
(2)
attention mechanism
(1)
in-context learning
(1)
neural machine translation
(1)
language modeling
(1)
model analysis
(1)
task generalization
(1)
formal methods
(1)
linguistic knowledge
(1)
visual context
(1)
model interpretability
(1)
mechanistic interpretability
(1)
attention head
(1)
formal language
(1)
dataset bia
(1)
pre-trained language model
(1)
dataset evaluation
(1)
pretrained language model
(1)
Papers
Characterizing the Expressivity of Local Attention in Transformers
ACL 2026
Unique Hard Attention: A Tale of Two Sides
ACL 2025
A Transformer with Stack Attention
NAACL 2024
What Do Language Models Learn in Context? The Structured Task Hypothesis.
ACL 2024
Towards a Mechanistic Interpretation of Multi-Step Reasoning Capabilities of Language Models
EMNLP 2023
Probing via Prompting
NAACL 2022
Vision Matters When It Should: Sanity Checking Multimodal Machine Translation Models
EMNLP 2021