[ICML 2025] Beyond Bradley-Terry Models: A General Preference Model for Language Model Alignment (https://arxiv.org/abs/2410.02197)
-
Updated
Sep 8, 2025 - Python
#
preference-optimization
Here are 25 public repositories matching this topic...
PipelineLLM 是一个系统性的大语言模型（LLM）后训练学习项目，涵盖从监督微调（SFT）到偏好优化（DPO）、强化学习（RLHF/PPO/GRPO）再到持续学习（Continual Learning)的完整技术栈。
reinforcement-learning lora fine-tuning post-training continual-learning sft rlhf llm-reasoning preference-optimization llm-infrastructure llm-processing
-
Updated
Jan 16, 2026 - Python
[TMLR] Triple Preference Optimization
-
Updated
Feb 19, 2025 - Python
Symmetrical Visual Contrastive Optimization: Aligning Vision-Language Models with Minimal Contrastive Images
-
Updated
Jun 4, 2025 - Python
A lightweight post-training framework for LLMs and VLMs. 51 algorithms, 38 verified models. Scales with DeepSpeed, vLLM, and Ray.
reinforcement-learning alignment post-training dpo deepspeed rlhf vllm llm-training preference-optimization grpo
-
Updated
May 6, 2026 - Python
[ACL 2025] Uncovering the Impact of Chain-of-Thought Reasoning for Direct Preference Optimization: Lessons from Text-to-SQL
-
Updated
Oct 9, 2025 - Python
Code for ICLR 2025 Paper: Synthio: Augmenting Small-Scale Audio Classification Datasets with Synthetic Data
audio audio-classification synthetic-data audio-generation large-language-models preference-optimization
-
Updated
Mar 31, 2025 - Python
[ICML 2025] TGDPO: Harnessing Token-Level Reward Guidance for Enhancing Direct Preference Optimization
alignment preference-learning large-language-models llm rlhf preference-alignment direct-preference-optimization preference-optimization
-
Updated
Jul 15, 2025 - Python
[TMLR] Dual Caption Preference Optimization
-
Updated
Feb 12, 2025 - Python
Pre-DPO: Improving Data Utilization in Direct Preference Optimization Using a Guiding Reference Model
-
Updated
Apr 23, 2025 - Python
🔬 Official implementation of ExPO-HM: Learning to Explain-then-Detect for Hateful Meme Detection (ICLR 2026). Novel multimodal RL approach for interpretable and explainable content moderation.
multimodal-learning explainable-ai content-moderation vision-language-models preference-optimization grpo iclr-2026 hateful-meme-detection multimodal-rl
-
Updated
Mar 1, 2026 - Python
Convex Optimization for Alignment and Preference Learning on a Single GPU
-
Updated
May 28, 2026 - Python
Open-source research engineering project for building the end-to-end post-training stack for reasoning language models, including SFT, preference learning, RLHF/RLVR, evaluation, inference-time scaling, and scalable systems for frontier-level reasoning.
open-source evaluation inference text-generation benchmarks post-training rlhf reward-modeling preference-optimization supervised-fine-tuning inference-time-scaling open-post-training-system
-
Updated
Jun 5, 2026 - Jupyter Notebook
🩺 Token-Level Flow-Guided Preference Optimization for Efficient Test-Time Alignment (AAAI 2026)
-
Updated
Jan 17, 2026 - Python
AIWG training-complete framework — corpus-to-dataset pipeline with SKILL.md agentic surface and optional Python runtime backend. Marketplace plugin for AIWG.
provenance synthetic-data training-data fine-tuning dpo model-cards decontamination dataset-curation sharegpt llm-training preference-optimization alpaca-format aiwg benchmark-contamination datasheets-for-datasets
-
Updated
Apr 16, 2026 - Python
Novel Preference Optimization Algorithms for state-of-the-art small LMs, enhancing performance in GenAI and NLP tasks
-
Updated
Jan 5, 2025 - Python
A weekly updated awesome list of RL, RLHF, DPO, GRPO, reward models, and preference optimization for image and video diffusion generation.
reinforcement-learning image-generation awesome-list video-generation diffusion-models rlhf preference-optimization grpo
-
Updated
May 19, 2026
Direct multi-agent policy optimization — unified DPO/KTO/ORPO/SimPO framework.
-
Updated
Apr 14, 2026 - Python
Curated list of papers, tools, datasets and resources for human-in-the-loop AI training — SFT, RLHF, preference optimization, red-teaming, evaluation.
awesome awesome-list model-evaluation human-in-the-loop red-teaming dpo ai-training llm rlhf preference-optimization
-
Updated
Apr 21, 2026
Preference optimization framework for text classification (DPO/ORPO/KTO), with SFT, encoder, and XGBoost baselines plus unified run pipeline and reproducible outputs.
nlp machine-learning text-classification xgboost lora peft dpo kto tranformers qlora llm-fine-tuning orpo preference-optimization
-
Updated
Apr 4, 2026 - Python
Improve this page
Add a description, image, and links to the preference-optimization topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the preference-optimization topic, visit your repo's landing page and select "manage topics."