Dake Bu
4 papers · 2024–2025 · 2 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
🗺️
Taxonomy Completionist
(12)
Venues
Top co-authors
Research topics
Deep Learning
(3)
Machine Learning
(3)
Architectures
(3)
Optimization & Theory · Machine Learning
(3)
Artificial Intelligence
(2)
Core AI
(2)
Reinforcement Learning
(1)
Learning Types · Machine Learning
(1)
Learning Types · Deep Learning
(1)
Methods
(1)
Models
(1)
Optimization & Theory · Deep Learning
(1)
Keywords
in-context learning
(2)
transformer architecture
(1)
feature learning
(1)
sparse coding
(1)
attention mechanism
(1)
semantic representation
(1)
neural network optimization
(1)
gradient descent
(1)
label complexity
(1)
regret bound
(1)
multi-objective reinforcement learning
(1)
cross-entropy loss
(1)
exponential convergence
(1)
multi-concept semantics
(1)
vector arithmetic
(1)
large language model
(1)
transformer model
(1)
lexicographic reward
(1)
episode length
(1)
misspecified setting
(1)
Papers
Multi-objective Linear Reinforcement Learning with Lexicographic Rewards
ICML 2025
Provable In-Context Vector Arithmetic via Retrieving Task Concepts
ICML 2025
Provably Neural Active Learning Succeeds via Prioritizing Perplexing Samples
ICML 2024
Provably Transformers Harness Multi-Concept Word Semantics for Efficient In-Context Learning
NeurIPS 2024