Qinan Yu
6 papers · 2023–2025 · 5 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 ↓
🌍
Conference Polyglot · Silver
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(16)
🐣
Hot Topic Early Bird
❓
The Questioner
(2)
Venues
Top co-authors
Research topics
Keywords
circuit analysis
(2)
mechanistic interpretability
(2)
large language model
(2)
in-context learning
(1)
prompt engineering
(1)
instruction following
(1)
model behavior
(1)
language model
(1)
neural circuit
(1)
vision-language model
(1)
attention head
(1)
model scaling
(1)
human evaluation
(1)
permutation group
(1)
multilingual model
(1)
factual recall
(1)
human-ai comparison
(1)
zero-shot performance
(1)
neural network
(1)
prompt following
(1)
Papers
The Same but Different: Structural Similarities and Differences in Multilingual Language Modeling
ICLR 2025
Does CLIP Bind Concepts? Probing Compositionality in Large Image Models
EACL 2024
Grokking Group Multiplication with Cosets
ICML 2024
LLM Circuit Analyses Are Consistent Across Training and Scale
NeurIPS 2024
Are Language Models Worse than Humans at Following Prompts? It’s Complicated
EMNLP 2023
Characterizing Mechanisms for Factual Recall in Language Models
EMNLP 2023