direct-preference-optimization

Pivotal Token Search

A Survey of Direct Preference Optimization (DPO)

PhyGDPO: Physics-Aware Groupwise Direct Preference Optimization for Physically Consistent Text-to-Video Generation (ECCV 2026)

Official Implementation (Pytorch) of the "VidChain: Chain-of-Tasks with Metric-based Direct Preference Optimization for Dense Video Captioning", AAAI 2025

[TPAMI 2026] A Comprehensive Survey of Direct Preference Optimization: Datasets, Theories, Variants, and Applications

[ICLR 2026] Official repository of "Uni-DPO: A Unified Paradigm for Dynamic Preference Optimization of LLMs".

[ICML 2025] TGDPO: Harnessing Token-Level Reward Guidance for Enhancing Direct Preference Optimization

Code for the paper "Polaris: Learning to Generate Table Descriptions from Retrieval Feedback"

End-to-end pipeline for video safety alignment: SFT + DPO on Qwen3-VL with structured outputs, benchmark design, and evaluation of over-refusal.

RankPO: Rank Preference Optimization

Notebooks to create an instruction following version of Microsoft's Phi 2 LLM with Supervised Fine Tuning and Direct Preference Optimization (DPO)

[ICML 2025 Workshop FM4BS] AnnoDPO: Protein Functional Annotation Learning with Direct Preference Optimization

DPO for Tool/Function Calling - Fine-tune LLMs to intelligently decide when to call external APIs vs generate text using Direct Preference Optimization. Achieve 94.1% schema accuracy on Llama-2-7B with LoRA.

The Rap Music Generator project is an innovative LLM-based tool designed to create rap lyrics. It offers multiple fine-tuning approaches to accommodate diverse rap generation techniques, providing users with a versatile platform for generating unique and stylistically varied content.

a small, research-focused Python library for post-training Large Language Models with autotuning

Backtranslation Augmented Direct Preference Optimization for Neural Machine Translation

End-to-end GPT training pipeline in PyTorch: pretraining, SFT and DPO.

Homework assignments for CMU 11-611 Natural Language Processing (Spring 2026) — covering language identification, n-gram LMs, text classification, machine translation evaluation, and DPO fine-tuning.

LLM을 위한 강화학습 종합 학습 가이드 - RL for LLMs Learning Site