auxiliary-losses

Tag

Cards List
#auxiliary-losses

Task-Level Natural Language Priors as Learning Signals for Low-Resource LLM Training

arXiv cs.AI · 2026-09-03 Cached

The paper proposes Prior-Guided Tuning (PGT) and Contrastive Prior Steering (CPS) to use natural language priors as auxiliary learning signals, improving low-resource LLM training performance on tasks like AmbiMath, Jigsaw, and MNLI/HANS.

0 favorites 0 likes
#auxiliary-losses

Cosine Misleads: Auxiliary Losses Reshape Vision Language Models, Not Their Latents

Hugging Face Daily Papers · 2026-06-04 Cached

The paper challenges the assumption that cosine alignment between supervised latents and visual targets improves accuracy in vision-language models, finding a strong negative correlation. It introduces PRISM diagnostics revealing that answers are decoded downstream from latents, not within them, and that the auxiliary loss reshapes the language model via shared parameters.

0 favorites 0 likes
← Back to home

Submit Feedback