2 papers
cs.CV2026
Comparative study of adapting pre-trained models for driving behavior video captioning
Sayak Mallick, Philipp Geiger, Augustin Kelava
This report examines and compares some of the many fine tuning and prompting methods existing, applying them within the domain of autonomous driving. The idea is to compare these m…
cs.LG2025
LLMs on the Line: Data Determines Loss-to-Loss Scaling Laws
Prasanna Mayilvahanan, Thaddäus Wiedemer, Sayak Mallick +2
Scaling laws guide the development of large language models (LLMs) by offering estimates for the optimal balance of model size, tokens, and compute. More recently, loss-to-loss sca…