↓Skip to main content

🏢 KAIST AI

Preference Alignment with Flow Matching
·2735 words·13 mins· loading · loading
AI Generated Machine Learning Reinforcement Learning 🏢 KAIST AI
Preference Flow Matching (PFM) streamlines preference integration into pre-trained models using flow matching, overcoming fine-tuning limitations and enabling robust alignment with human preferences.
Aligning to Thousands of Preferences via System Message Generalization
·3279 words·16 mins· loading · loading
Natural Language Processing Large Language Models 🏢 KAIST AI
JANUS, a 7B LLM, achieves high alignment to thousands of user preferences by generalizing from diverse system messages, outperforming existing LLMs on various benchmarks.
Accelerating Blockwise Parallel Language Models with Draft Refinement
·2883 words·14 mins· loading · loading
Natural Language Processing Large Language Models 🏢 KAIST AI
Boost LLM inference speed by 3x! This paper refines blockwise parallel decoding (BPD) by cleverly refining draft predictions, resulting in faster text generation for large language models.