Fixed 16-bit binary token codes can replace trainable input embeddings in 32-layer decoder-only models while maintaining comparable held-out perplexity on 17B tokens.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
POVID generates AI-created preference data to fine-tune vision-language models with DPO, reducing hallucinations and improving benchmark scores.
citing papers explorer
-
Language Models Without a Trainable Input Embedding Table: Learning from Fixed Minimal Binary Token Codes
Fixed 16-bit binary token codes can replace trainable input embeddings in 32-layer decoder-only models while maintaining comparable held-out perplexity on 17B tokens.
-
Aligning Modalities in Vision Large Language Models via Preference Fine-tuning
POVID generates AI-created preference data to fine-tune vision-language models with DPO, reducing hallucinations and improving benchmark scores.