Changye Li
9 papers · 2022–2026 · 4 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 ↓+2 more ↓ Show less ↑
🌉 Interdisciplinary Bridge · Silver 🗺️ Taxonomy Completionist (37) 🌍 Conference Polyglot · Bronze 🗃️ Keyword Collector (57) 🌈 Renaissance Researcher (5)
❓
The Questioner
⚡
Prolific Year · Productive
Top co-authors
Research topics
Artificial Intelligence
(6)
Core AI
(6)
Deep Learning
(5)
Healthcare & Medicine
(5)
Machine Learning
(5)
Clinical
(5)
Natural Language Processing
(4)
Learning Types · Machine Learning
(3)
Learning Types · Deep Learning
(3)
Optimization & Theory
(3)
Application Areas
(2)
Applications
(2)
Architectures
(2)
Core Methods
(2)
Models
(2)
Keywords
language model
(3)
alzheimer disease
(2)
transfer learning
(1)
text classification
(1)
model robustness
(1)
interpretability
(1)
language model alignment
(1)
autoregressive model
(1)
speech analysis
(1)
phonetic analysis
(1)
message passing
(1)
data compression
(1)
schizophrenia detection
(1)
attention mechanism
(1)
cognitive modeling
(1)
multi-agent reinforcement learning
(1)
sparse autoencoder
(1)
medical diagnosis
(1)
multimodal model
(1)
transformer architecture
(1)
Papers
"Newspaper Eat" Means "Not Tasty": A Taxonomy and Benchmark for Coded Language in Real-World Chinese Online Reviews
ACL 2026
Bigger But Not Better: Small Neural Language Models Outperform LLMs in Detection of Thought Disorder
NAACL 2025
“Is There Anything Else?”: Examining Administrator Influence on Linguistic Features from the Cookie Theft Picture Description Cognitive Test
NAACL 2025
Language Models Resist Alignment: Evidence From Data Compression
ACL 2025
Mitigating Confounding in Speech-Based Dementia Detection through Weight Masking
ACL 2025
SAE-V: Interpreting Multimodal Models for Enhanced Alignment
ICML 2025
Towards Efficient Collaboration via Graph Modeling in Reinforcement Learning
AAAI 2025
Too Big to Fail: Larger Language Models are Disproportionately Resilient to Induction of Dementia-Related Linguistic Anomalies
ACL 2024
GPT-D: Inducing Dementia-related Linguistic Anomalies by Deliberate Degradation of Artificial Neural Language Models
ACL 2022