RewardBench: the first evaluation tool for reward models.
-
Updated
Sep 30, 2026 - Python
#
preference-learning
Here are 99 public repositories matching this topic...
Free and open source code of the https://tournesol.app platform. Meet the community on Discord https://discord.gg/WvcSG55Bf3
python youtube django reactjs django-rest-framework dataset recommendation-engine preference-learning social-choice ai-ethics bradley-terry-model golden-ratio-optimization preference-aggregation
-
Updated
Oct 2, 2026 - Python
Pairwise LLM judges (A/B/tie): budget-aware multi-turn packing, position-bias correction, pseudo-label distillation. Generalized from the 4th-place (gold) solution to Kaggle LMSYS Chatbot Arena.
nlp kaggle-competition lora preference-learning kaggle-solution gold-medal llm rlhf reward-model llm-as-judge chatbot-arena
-
Updated
Jul 24, 2026 - Python
The MAGICAL benchmark suite for robust imitation learning (NeurIPS 2020)
-
Updated
Dec 5, 2023 - Python
Self-evolving agentic reward framework for image-editing evaluation — 47.4% on EditReward-Bench from only 100 preference demos, no reward-model training. arXiv 2605.08703.
benchmark evaluation image-editing gemini vlm ai-agents preference-learning rlhf reward-model agentic llm-evaluation qwen-vl reward-modeling self-evolving llm-judge
-
Updated
Aug 25, 2026 - Python
Policy-driven preference data for content moderation, with source-linked evidence, resumable runs, budget controls and TRL/ShareGPT exports.
python data-validation multi-agent dataset-generation synthetic-data preference-learning content-moderation dpo llm rlhf
-
Updated
Sep 30, 2026 - Python
This repository contains the source code for our paper: "NaviSTAR: Socially Aware Robot Navigation with Hybrid Spatio-Temporal Graph Transformer and Preference Learning". For more details, please refer to our project website at https://sites.google.com/view/san-navistar.
machine-learning reinforcement-learning transformer preference-learning robot-navigation socially-aware-navigation
-
Updated
Mar 8, 2025 - Python
Python-based GUI to collect Feedback of Chemist in Molecules
machine-learning drug-discovery human-in-the-loop preference-learning de-novo-drug-design generative-ai
-
Updated
Oct 15, 2024 - Python
Accelerate LLM preference tuning via prefix sharing with a single line of code
-
Updated
Jul 4, 2025 - Python
Official implementation of Bootstrapping Language Models via DPO Implicit Rewards
-
Updated
Apr 15, 2025 - Python
Code for the paper "Aligning LLM Agents by Learning Latent Preference from User Edits".
transformers alignment user-feedback edits interpretability preference-learning gpt4 llm llms human-feedback
-
Updated
Nov 23, 2024 - Python
Policy Learning from Large Vision-Language Model Feedback Without Reward Modeling (IROS 2025)
-
Updated
Dec 26, 2025 - Python
Official code for ICML 2024 paper, "RIME: Robust Preference-based Reinforcement Learning with Noisy Preferences" (ICML 2024 Spotlight)
reinforcement-learning deep-learning robotics artificial-intelligence manipulation locomotion preference-learning reinforcement-learning-from-human-feedback
-
Updated
Oct 15, 2024 - Python
[ICLR 2026] MergeMix: A Unified Augmentation Paradigm for Visual and Multi-Modal Understanding
image-classification data-augmentation preference-learning mixup multimodal ranking-loss mmcv llava token-merging token-compression iclr2026
-
Updated
Feb 27, 2026 - Python
PyTorch implementations for Offline Preference-Based RL (PbRL) algorithms
-
Updated
Mar 24, 2025 - Python
[ICLR 2025 Spotlight] Weak-to-strong preference optimization: stealing reward from weak aligned model
-
Updated
Feb 24, 2025 - Python
Data and models for the paper "Configurable Safety Tuning of Language Models with Synthetic Preference Data"
-
Updated
Jul 27, 2024 - Python
Official PyTorch implementation of "LPOI: Listwise Preference Optimization for Vision Language Models" (ACL 2025 Main)
-
Updated
Jun 19, 2026 - Python
Official implementation of "Learning User Preferences for Image Generation Models"
-
Updated
Aug 16, 2025 - Python
Code for "Monocular Depth Estimation via Listwise Ranking using the Plackett-Luce Model" as published at CVPR 2021.
machine-learning deep-learning learning-to-rank cvpr weakly-supervised-learning preference-learning monocular-depth monocular-depth-estimation plackett-luce cvpr2021 relative-depth
-
Updated
Feb 3, 2024 - Python
Add this topic to your repo
To associate your repository with the preference-learning topic, visit your repo's landing page and select "manage topics."