Clement Neo
7 papers · 2024–2026 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
π Interdisciplinary Bridge π§ Keyword Pioneer π Conference Polyglot (3) π Cross-Pollinator (6) πΊοΈ Taxonomy Completionist (11)
π
Trend Setter
Conferences
EMNLP (3)
ICLR (2)
ACL (1)
NIPS (1)
Top co-authors
Keywords
neural network interpretability
(2)
large language model
(2)
mechanistic interpretability
(2)
sparse autoencoder
(2)
vision-language model
(1)
jailbreak attack
(1)
activation probe
(1)
learned feedback pattern
(1)
alignment verification
(1)
hidden state analysis
(1)
refusal behavior
(1)
multi-layer perceptron
(1)
neural interpretability
(1)
causal mediation
(1)
text-to-sql generation
(1)
activation patching
(1)
probing classifier
(1)
feature intervention
(1)
neural network
(1)
activation analysis
(1)
Papers
Spectra: A Mechanistic Interpretability Library for Vision-Language Models
ACL 2026
TinySQL: A Progressive Text-to-SQL Dataset for Mechanistic Interpretability Research
EMNLP 2025
Understanding Refusal in Language Models with Sparse Autoencoders
EMNLP 2025
Turning Up the Heat: Min-p Sampling for Creative and Coherent LLM Outputs
ICLR 2025
Towards Interpreting Visual Information Processing in Vision-Language Models
ICLR 2025
Interpreting Learned Feedback Patterns in Large Language Models
NIPS 2024
Interpreting Context Look-ups in Transformers: Investigating Attention-MLP Interactions
EMNLP 2024