Junyi Wei
5 papers · 2022–2024 · 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
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(17)
👑
Triple Crown
❓
The Questioner
Venues
Top co-authors
Research topics
Deep Learning
(4)
Machine Learning
(4)
Core Methods
(4)
Artificial Intelligence
(3)
Architectures
(3)
Core AI · Artificial Intelligence
(2)
Optimization & Theory
(2)
Computer Vision
(1)
Core AI · Computer Vision
(1)
Learning Paradigms
(1)
Learning Types · Machine Learning
(1)
Learning Types · Deep Learning
(1)
Models
(1)
Techniques
(1)
Keywords
transfer learning
(2)
learning theory
(2)
neural network
(2)
foundation model
(2)
feature learning
(1)
few-shot learning
(1)
image retrieval
(1)
in-context learning
(1)
information retrieval
(1)
multimodal learning
(1)
transformer
(1)
gradient descent
(1)
closed-form solution
(1)
vision-language model
(1)
embedding alignment
(1)
interleaved embedding
(1)
hidden feature
(1)
multi-task fine-tuning
(1)
task selection
(1)
noise sensitivity
(1)
Papers
Interfacing Foundation Models' Embeddings
NeurIPS 2024
Towards Few-Shot Adaptation of Foundation Models via Multitask Finetuning
ICLR 2024
Why Larger Language Models Do In-context Learning Differently?
ICML 2024
Provable Guarantees for Neural Networks via Gradient Feature Learning
NeurIPS 2023
A Theoretical Analysis on Feature Learning in Neural Networks: Emergence from Inputs and Advantage over Fixed Features
ICLR 2022