Jea Kwon
4 papers · 2023–2026 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
🌍
Conference Polyglot
(2)
🌉
Interdisciplinary Bridge
🧭
Keyword Pioneer
🐝
Cross-Pollinator
(15)
Conferences
AAAI (1)
ACL (1)
ICLR (1)
NIPS (1)
Top co-authors
Keywords
transformer architecture
(1)
mutual information
(1)
training datum
(1)
parametric knowledge
(1)
knowledge utilization
(1)
moral uncertainty
(1)
memory consolidation
(1)
feed forward network
(1)
human-ai alignment
(1)
place cell
(1)
nmda receptor
(1)
hippocampal representation
(1)
binary entropy
(1)
in-context knowledge
(1)
intra-document repetition
(1)
Papers
Dropouts in Confidence: Moral Uncertainty in Human-LLM Alignment
AAAI 2026
How Training Data Shapes the Use of Parametric and In-Context Knowledge in Language Models
ACL 2026
Brain-inspired $L_p$-Convolution benefits large kernels and aligns better with visual cortex
ICLR 2025
Transformer as a hippocampal memory consolidation model based on NMDAR-inspired nonlinearity
NIPS 2023