Bochen Lyu
5 papers · 2023–2025 · 4 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 ↓
π
Conference Polyglot Β· Bronze
π
Interdisciplinary Bridge Β· Bronze
πΊοΈ
Taxonomy Completionist
(12)
β
The Questioner
π
Renaissance Researcher
(5)
Venues
Top co-authors
Research topics
Keywords
implicit bia
(2)
transformer architecture
(1)
stochastic gradient descent
(1)
in-context learning
(1)
causal structure learning
(1)
dynamic causal modeling
(1)
sparse regression
(1)
gradient flow
(1)
momentum method
(1)
linear neural network
(1)
ordinary differential equation
(1)
diagonal linear network
(1)
riccati equation
(1)
large language model
(1)
neural scaling law
(1)
conceptual abstraction
(1)
structure-mapping theory
(1)
analogy annotation
(1)
story-level analogies
(1)
time series analysis
(1)
Papers
A Solvable Attention for Neural Scaling Laws
ICLR 2025
Can Language Models Serve as Analogy Annotators?
ACL 2025
DyCAST: Learning Dynamic Causal Structure from Time Series
ICLR 2025
Effects of Momentum in Implicit Bias of Gradient Flow for Diagonal Linear Networks
AAAI 2025
Implicit Bias of (Stochastic) Gradient Descent for Rank-1 Linear Neural Network
NeurIPS 2023