Runjin Chen
7 papers · 2019–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
π§ Keyword Pioneer π Conference Polyglot (4) π Academic Marathon (6) π Cross-Pollinator (10) π Interdisciplinary Bridge
πΊοΈ
Taxonomy Completionist
(10)
π£
Hot Topic Early Bird
Conferences
ICML (4)
ICCV (1)
NAACL (1)
NIPS (1)
Top co-authors
Keywords
natural language processing
(1)
information bottleneck
(1)
knowledge extraction
(1)
attention mechanism
(1)
knowledge transfer
(1)
knowledge distillation
(1)
explainable ai
(1)
model behavior
(1)
model safety
(1)
neural network interpretability
(1)
model analysis
(1)
feature attribution
(1)
additive model
(1)
convolutional neural network
(1)
positional encoding
(1)
alignment evaluation
(1)
long context
(1)
context fusion
(1)
large language model alignment
(1)
explainable model
(1)
Papers
Extracting and Understanding the Superficial Knowledge in Alignment
NAACL 2025
Learning Along the Arrow of Time: Hyperbolic Geometry for Backward-Compatible Representation Learning
ICML 2025
From Low Rank Gradient Subspace Stabilization to Low-Rank Weights: Observations, Theories, and Applications
ICML 2025
LLaGA: Large Language and Graph Assistant
ICML 2024
Found in the Middle: How Language Models Use Long Contexts Better via Plug-and-Play Positional Encoding
NIPS 2024
Towards a Deep and Unified Understanding of Deep Neural Models in NLP
ICML 2019
Explaining Neural Networks Semantically and Quantitatively
ICCV 2019