Jeffrey Quesnelle

According to our database, Jeffrey Quesnelle authored at least 9 papers between 2017 and 2026.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of five.

2026

Long Context Pre-Training with Lighthouse Attention.

Bowen Peng, Subho Ghosh, Jeffrey Quesnelle

CoRR, May, 2026

Efficient Pre-Training with Token Superposition.

Bowen Peng, Théo Gigant, Jeffrey Quesnelle

CoRR, May, 2026

Decoupling the Benefits of Subword Tokenization for Language Model Training via Byte-level Simulation.

Théo Gigant, Bowen Peng, Jeffrey Quesnelle

CoRR, April, 2026

2025

CurvaDion: Curvature-Adaptive Distributed Orthonormalization.

Bhavesh Kumar, Roger Jin, Jeffrey Quesnelle

CoRR, December, 2025

Hermes 4 Technical Report.

Ryan Teknium, Roger Jin, Jai Suphavadeeprasit, Dakota Mahan, Jeffrey Quesnelle, Joe Li, Chen Guang, Shannon Sands, Karan Malhotra

CoRR, August, 2025

2024

DeMo: Decoupled Momentum Optimization.

Bowen Peng, Jeffrey Quesnelle, Diederik P. Kingma

CoRR, 2024

Hermes 3 Technical Report.

Ryan Teknium, Jeffrey Quesnelle, Chen Guang

CoRR, 2024

YaRN: Efficient Context Window Extension of Large Language Models.

Bowen Peng, Jeffrey Quesnelle, Honglu Fan, Enrico Shippole

Proceedings of the Twelfth International Conference on Learning Representations, 2024

2017

On the linkability of Zcash transactions.

Jeffrey Quesnelle

CoRR, 2017