Changye Li
9 papers · 2022–2026 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (34) π Cross-Pollinator (9) π Renaissance Researcher (7) π Interdisciplinary Bridge π§ Keyword Pioneer
π
Conference Polyglot
(4)
β‘
Prolific Year
(6)
β
The Questioner
Conferences
ACL (5)
NAACL (2)
AAAI (1)
ICML (1)
Top co-authors
Keywords
language model
(3)
alzheimer disease
(2)
transfer learning
(1)
text classification
(1)
model robustness
(1)
attention mechanism
(1)
speech analysis
(1)
language model alignment
(1)
phonetic analysis
(1)
message passing
(1)
data compression
(1)
schizophrenia detection
(1)
cognitive modeling
(1)
autoregressive model
(1)
multi-agent reinforcement learning
(1)
medical diagnosis
(1)
cognitive assessment
(1)
linguistic feature
(1)
neural language 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
Language Models Resist Alignment: Evidence From Data Compression
ACL 2025
Bigger But Not Better: Small Neural Language Models Outperform LLMs in Detection of Thought Disorder
NAACL 2025
βIs There Anything Else?β: Examining Administrator Influence on Linguistic Features from the Cookie Theft Picture Description Cognitive Test
NAACL 2025
Mitigating Confounding in Speech-Based Dementia Detection through Weight Masking
ACL 2025
Towards Efficient Collaboration via Graph Modeling in Reinforcement Learning
AAAI 2025
SAE-V: Interpreting Multimodal Models for Enhanced Alignment
ICML 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