Picture for Ellie Pavlick

Ellie Pavlick

Shammie

How Do Vision-Language Models Process Conflicting Information Across Modalities?

Add code
Jul 02, 2025
Viaarxiv icon

Transferring Features Across Language Models With Model Stitching

Add code
Jun 07, 2025
Viaarxiv icon

Paths Not Taken: Understanding and Mending the Multilingual Factual Recall Pipeline

Add code
May 28, 2025
Viaarxiv icon

Born a Transformer -- Always a Transformer?

Add code
May 27, 2025
Viaarxiv icon

EHOP: A Dataset of Everyday NP-Hard Optimization Problems

Add code
Feb 19, 2025
Viaarxiv icon

Does Training on Synthetic Data Make Models Less Robust?

Add code
Feb 11, 2025
Viaarxiv icon

$100K or 100 Days: Trade-offs when Pre-Training with Academic Resources

Add code
Oct 30, 2024
Viaarxiv icon

Are LLMs Models of Distributional Semantics? A Case Study on Quantifiers

Add code
Oct 17, 2024
Figure 1 for Are LLMs Models of Distributional Semantics? A Case Study on Quantifiers
Figure 2 for Are LLMs Models of Distributional Semantics? A Case Study on Quantifiers
Figure 3 for Are LLMs Models of Distributional Semantics? A Case Study on Quantifiers
Figure 4 for Are LLMs Models of Distributional Semantics? A Case Study on Quantifiers
Viaarxiv icon

The Same But Different: Structural Similarities and Differences in Multilingual Language Modeling

Add code
Oct 11, 2024
Viaarxiv icon

Beyond the Doors of Perception: Vision Transformers Represent Relations Between Objects

Add code
Jun 22, 2024
Figure 1 for Beyond the Doors of Perception: Vision Transformers Represent Relations Between Objects
Figure 2 for Beyond the Doors of Perception: Vision Transformers Represent Relations Between Objects
Figure 3 for Beyond the Doors of Perception: Vision Transformers Represent Relations Between Objects
Figure 4 for Beyond the Doors of Perception: Vision Transformers Represent Relations Between Objects
Viaarxiv icon