Daniel Soudry
~Daniel_Soudry1
17
论文总数
8.5
年均投稿
平均评分
接收情况14/17
会议分布
NeurIPS
10
ICLR
6
ICML
1
发表论文 (17 篇)
202511 篇
4
Alias-Free ViT: Fractional Shift Invariance via Linear Attention
NeurIPS 2025Poster
4
De-biasing Diffusion: Data-Free FP8 Quantization of Text-to-Image Models with Billions of Parameters
ICLR 2025Rejected
4
Foldable SuperNets: Scalable Merging of Transformers with Different Initializations and Tasks
ICLR 2025Rejected
4
FP4 All the Way: Fully Quantized Training of Large Language Models
NeurIPS 2025Spotlight
4
Scaling FP8 training to trillion-token LLMs
ICLR 2025Spotlight
4
Optimal Rates in Continual Linear Regression via Increasing Regularization
NeurIPS 2025Poster
4
Tensor-Parallelism with Partially Synchronized Activations
NeurIPS 2025Poster
4
Temperature is All You Need for Generalization in Langevin Dynamics and other Markov Processes
NeurIPS 2025Spotlight
4
Are Greedy Task Orderings Better Than Random in Continual Linear Regression?
NeurIPS 2025Poster
4
When Diffusion Models Memorize: Inductive Biases in Probability Flow of Minimum-Norm Shallow Neural Nets
ICML 2025Poster
4
The Inductive Bias of Minimum-Norm Shallow Diffusion Models That Perfectly Fit the Data
ICLR 2025Rejected
20246 篇
3
Exponential Quantum Communication Advantage in Distributed Inference and Learning
NeurIPS 2024Poster
4
The Implicit Bias of Gradient Descent on Separable Multiclass Data
NeurIPS 2024Poster
4
Towards Cheaper Inference in Deep Networks with Lower Bit-Width Accumulators
ICLR 2024Poster
6
The Joint Effect of Task Similarity and Overparameterization on Catastrophic Forgetting — An Analytical Model
ICLR 2024Poster
4
Stable Minima Cannot Overfit in Univariate ReLU Networks: Generalization by Large Step Sizes
NeurIPS 2024Spotlight
4
Provable Tempered Overfitting of Minimal Nets and Typical Nets
NeurIPS 2024Poster