Cengiz Pehlevan
~Cengiz_Pehlevan2
24
论文总数
12.0
年均投稿
平均评分
接收情况19/24
会议分布
ICLR
12
NeurIPS
6
ICML
5
COLM
1
发表论文 (24 篇)
202520 篇
4
Error Broadcast and Decorrelation as a Potential Artificial and Natural Learning Mechanism
ICLR 2025Rejected
4
Error Broadcast and Decorrelation as a Potential Artificial and Natural Learning Mechanism
NeurIPS 2025Spotlight
5
On the onset of memorization to generalization transition in diffusion models
ICLR 2025withdrawn
4
Deep Linear Network Training Dynamics from Random Initialization: Data, Width, Depth, and Hyperparameter Transfer
ICML 2025Poster
5
MLPs Learn In-Context on Regression and Classification Tasks
ICLR 2025Poster
4
A solvable model of learning generative diffusion: theory and insights
NeurIPS 2025Poster
4
An Analytical Theory of Spectral Bias in the Learning Dynamics of Diffusion Models
NeurIPS 2025Spotlight
3
A Brain-Inspired Regularizer for Adversarial Robustness
ICLR 2025Rejected
4
Adaptive kernel predictors from feature-learning infinite limits of neural networks
ICML 2025Poster
5
How Feature Learning Can Improve Neural Scaling Laws
ICLR 2025Spotlight
4
Do Mice Grok? Glimpses of Hidden Progress in Sensory Cortex
ICLR 2025Poster
4
Risk and cross validation in ridge regression with correlated samples
ICML 2025Poster
3
Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining
COLM 2025Poster
4
No Free Lunch from Random Feature Ensembles: Scaling Laws and Near-Optimality Conditions
ICML 2025Poster
3
A Model of Place Field Reorganization During Reward Maximization
ICML 2025Poster
5
No Free Lunch from Random Feature Ensembles
ICLR 2025Rejected
4
The Optimization Landscape of SGD Across the Feature Learning Strength
ICLR 2025Poster
4
A Model of Place Field Reorganization During Reward Maximization
ICLR 2025Rejected
4
Don't be lazy: CompleteP enables compute-efficient deep transformers
NeurIPS 2025Poster
4
Scaling Laws for Precision
ICLR 2025Oral
20244 篇
4
Infinite Limits of Multi-head Transformer Dynamics
NeurIPS 2024Poster
3
Partial observation can induce mechanistic mismatches in data-constrained models of neural dynamics
NeurIPS 2024Poster
4
Grokking as the transition from lazy to rich training dynamics
ICLR 2024Poster
4
Depthwise Hyperparameter Transfer in Residual Networks: Dynamics and Scaling Limit
ICLR 2024Poster