Picture for Felix Hill

Felix Hill

Strategy Coopetition Explains the Emergence and Transience of In-Context Learning

Add code
Mar 07, 2025
Viaarxiv icon

Why transformers are obviously good models of language

Add code
Aug 07, 2024
Viaarxiv icon

What needs to go right for an induction head? A mechanistic study of in-context learning circuits and their formation

Add code
Apr 10, 2024
Figure 1 for What needs to go right for an induction head? A mechanistic study of in-context learning circuits and their formation
Figure 2 for What needs to go right for an induction head? A mechanistic study of in-context learning circuits and their formation
Figure 3 for What needs to go right for an induction head? A mechanistic study of in-context learning circuits and their formation
Figure 4 for What needs to go right for an induction head? A mechanistic study of in-context learning circuits and their formation
Viaarxiv icon

SODA: Bottleneck Diffusion Models for Representation Learning

Add code
Nov 29, 2023
Viaarxiv icon

The Transient Nature of Emergent In-Context Learning in Transformers

Add code
Nov 15, 2023
Figure 1 for The Transient Nature of Emergent In-Context Learning in Transformers
Figure 2 for The Transient Nature of Emergent In-Context Learning in Transformers
Figure 3 for The Transient Nature of Emergent In-Context Learning in Transformers
Figure 4 for The Transient Nature of Emergent In-Context Learning in Transformers
Viaarxiv icon

Vision-Language Models as Success Detectors

Add code
Mar 13, 2023
Viaarxiv icon

The Edge of Orthogonality: A Simple View of What Makes BYOL Tick

Add code
Feb 09, 2023
Viaarxiv icon

Collaborating with language models for embodied reasoning

Add code
Feb 01, 2023
Viaarxiv icon

SemPPL: Predicting pseudo-labels for better contrastive representations

Add code
Jan 12, 2023
Viaarxiv icon

Transformers generalize differently from information stored in context vs in weights

Add code
Oct 11, 2022
Figure 1 for Transformers generalize differently from information stored in context vs in weights
Figure 2 for Transformers generalize differently from information stored in context vs in weights
Figure 3 for Transformers generalize differently from information stored in context vs in weights
Figure 4 for Transformers generalize differently from information stored in context vs in weights
Viaarxiv icon