Search papers, labs, and topics across Lattice.
PhD student at Virginia Tech
2
4
5
5
Unlock hidden potential: you can boost a model's reasoning skills by linearly transferring capabilities learned by *other* models, even across different sizes, without any training.
Forget retraining from scratch: port fine-tuning updates between LLM versions and get up to 47% performance boost on tasks like instruction following, even surpassing fully fine-tuned models.
