Siyu Lou
4 papers · 2023–2026 · 3 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 · Bronze
Top co-authors
Research topics
Keywords
explainable ai
(2)
deep neural network
(2)
feature attribution
(1)
efficient computing
(1)
model explanation
(1)
bayesian neural network
(1)
sparse attention
(1)
shapley value
(1)
long-context inference
(1)
interaction primitive
(1)
concept encoding
(1)
adversarial vulnerability
(1)
complex concept
(1)
harsanyi interaction
(1)
generalization power
(1)
variational inference
(1)
symbolic extraction
(1)
game theory
(1)
Papers
RRAtention: Dynamic Block Sparse Attention via Per-Head Round-Robin Shifts for Long-Context Inference
ACL 2026
Defining and extracting generalizable interaction primitives from DNNs
ICLR 2024
Bayesian Neural Networks Avoid Encoding Complex and Perturbation-Sensitive Concepts
ICML 2023
HarsanyiNet: Computing Accurate Shapley Values in a Single Forward Propagation
ICML 2023