Wei Hu
98 papers · 2008–2026 · 17 venues · across top CS/AI venues
This profile combines several different researchers. Authors are keyed by name, and this name's papers fall into 22 separate collaboration groups - the largest holds only 27% of them. Pick the group below that matches the researcher you mean. How a shared name is split.
Achievements are not shown for a combined profile - each one describes a single researcher's record, which this is not.
Which Wei Hu?
14 groups of papers that share co-authors internally but none with each other - each most likely a different researcher. Pick one to see its papers.
with Yongyi Yang, Ekdeep Singh Lubana, Jacob Steinhardt
5 papers
· 2022–2025
· NeurIPS, ICML, ICLR
Hide ▲
Swing-by Dynamics in Concept Learning and Compositional Generalization
ICLR 2025
Abrupt Learning in Transformers: A Case Study on Matrix Completion
NeurIPS 2024
Are Neurons Actually Collapsed? On the Fine-Grained Structure in Neural Representations
ICML 2023
Going Beyond Linear Mode Connectivity: The Layerwise Linear Feature Connectivity
NeurIPS 2023
More Than a Toy: Random Matrix Models Predict How Real-World Neural Representations Generalize
ICML 2022
8 papers whose co-authors appear nowhere else under this name
Skill-Aware Data Selection and Fine-Tuning for Data-Efficient Reasoning Distillation
ACL 2026
DHGCN: Dynamic Hop Graph Convolution Network for Self-Supervised Point Cloud Learning
AAAI 2024
How Do Transformers Learn In-Context Beyond Simple Functions? A Case Study on Learning with Representations
ICLR 2024
Understanding Surprising Generalization Phenomena in Deep Learning
AAAI 2024
A Representation Learning Perspective on the Importance of Train-Validation Splitting in Meta-Learning
ICML 2021
Global-to-Local Neural Networks for Document-Level Relation Extraction
EMNLP 2020
Combinatorial Multi-Armed Bandit with General Reward Functions
NeurIPS 2016
Modeling Chinese Documents with Topical Word-Character Models
COLING 2008