Ellie Pavlick
~Ellie_Pavlick1
14
论文总数
7.0
年均投稿
平均评分
接收情况9/14
会议分布
ICLR
8
NeurIPS
4
COLM
2
发表论文 (14 篇)
20256 篇
4
Transferring Linear Features Across Language Models With Model Stitching
NeurIPS 2025Spotlight
4
Dual Process Learning: Controlling Use of In-Context vs. In-Weights Strategies with Weight Forgetting
ICLR 2025Poster
5
The Same but Different: Structural Similarities and Differences in Multilingual Language Modeling
ICLR 2025Poster
3
Transformer Mechanisms Mimic Frontostriatal Gating Operations When Trained on Human Working Memory Tasks
ICLR 2025Rejected
4
Born a Transformer -- Always a Transformer? On the Effect of Pretraining on Architectural Abilities
NeurIPS 2025Poster
4
$100K or 100 Days: Trade-offs when Pre-Training with Academic Resources
COLM 2025Poster
20248 篇
5
Uncovering Causal Variables in Transformers Using Circuit Probing
ICLR 2024withdrawn
4
Circuit Component Reuse Across Tasks in Transformer Language Models
ICLR 2024Spotlight
4
A Mechanism for Solving Relational Tasks in Transformer Language Models
ICLR 2024withdrawn
3
Instilling Inductive Biases with Subnetworks
ICLR 2024Rejected
3
Uncovering Intermediate Variables in Transformers using Circuit Probing
COLM 2024Poster
5
Talking Heads: Understanding Inter-Layer Communication in Transformer Language Models
NeurIPS 2024Poster
4
Beyond the Doors of Perception: Vision Transformers Represent Relations Between Objects
NeurIPS 2024Poster
4
Deep Neural Networks Can Learn Generalizable Same-Different Visual Relations
ICLR 2024Rejected