PaperHub

Andrew Gordon Wilson

~Andrew_Gordon_Wilson1

26
论文总数
13.0
年均投稿
5.9
平均评分
接收情况14/26
会议分布
ICLR
16
NeurIPS
6
ICML
4

发表论文 (26 篇)

202516

6.5
4

Improving Discrete Diffusion with Schedule-Conditioning

ICLR 2025Rejected
5.5
4

Training Flexible Models of Genetic Variant Effects from Functional Annotations using Accelerated Linear Algebra

ICML 2025Poster
5.8
3

Why Masking Diffusion Works: Condition on the Jump Schedule for Improved Discrete Diffusion

NeurIPS 2025Poster
8.3
4

Scaling Collapse Reveals Universal Dynamics in Compute-Optimally Trained Neural Networks

ICML 2025Oral
7.3
4

Small Batch Size Training for Language Models: When Vanilla SGD Works, and Why Gradient Accumulation is Wasteful

NeurIPS 2025Poster
3.5
4

LLMs Boost the Performance of Decision Trees on Tabular Data across Sample Sizes

ICLR 2025Rejected
4.4
5

Molecular Active Learning: How can LLMs Help?

ICLR 2025withdrawn
7.1
5

How to Scale Second-Order Optimization

NeurIPS 2025Poster
6.6
4

Customizing the Inductive Biases of Softmax Attention using Structured Matrices

ICML 2025Poster
4.8
5

Just How Flexible are Neural Networks in Practice?

ICLR 2025Rejected
5.3
3

The Promises and Pitfalls of Language Models for Structured Numerical Data

ICLR 2025Rejected
5.5
4

Enhancing Foundation Models for Time Series Forecasting via Wavelet-based Tokenization

ICLR 2025Rejected
4.8
4

Pathologies of Out-of-Distribution Detection

ICLR 2025Rejected
6.0
5

Compute-Optimal LLMs Provably Generalize Better with Scale

ICLR 2025Poster
6.1
4

Enhancing Foundation Models for Time Series Forecasting via Wavelet-based Tokenization

ICML 2025Poster
7.3
4

Bayesian Optimization of Antibodies Informed by a Generative Model of Evolving Sequences

ICLR 2025Spotlight

202410