Christopher M. Lott

Papers on Lattice

Total citations

Topics

h-index

Publication activitypapers/week, last 8 weeks

Research focus

Inference & Quantization (1)Natural Language Processing (1)Training Efficiency & Optimization (1)

Frequent co-authors

Raghavv Goel (1)Mukul Gagrani (1)Mingu Lee (1)Chris Lott (1)

Papers (1)

Mar 18, 2026

Raghavv Goel +42w ago

Efficient Training-Free Multi-Token Prediction via Embedding-Space Probing

LLMs can predict multiple tokens in parallel without any training, simply by cleverly probing their embedding space with dynamically generated mask tokens.

Raghavv Goel, Mukul Gagrani, Mingu Lee +2

Inference & Quantization Natural Language Processing Training Efficiency & Optimization

Search

Christopher M. Lott

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (1)