[ICLR 2025] IterComp: Iterative Composition-Aware Feedback Learning from Model Gallery for Text-to-Image Generation
-
Updated
Feb 19, 2025 - Python
#
reward-modeling
Here are 28 public repositories matching this topic...
Datasets collection and preprocessings framework for NLP extreme multitask learning
nlp benchmark text-classification glue scaling natural-language-inference crossfit multi-task-learning meta-learning bigbench discriminative huggingface dataset-collection instruction-tuning preprocessings multi-task-learning-scaling extreme-multi-task-learning extreme-mtl curated-datasets reward-modeling
-
Updated
Jul 9, 2025 - Python
[CVPR 2026] Official Code for "ARM-Thinker: Reinforcing Multimodal Generative Reward Models with Agentic Tool Use and Visual Reasoning"
-
Updated
Feb 13, 2026 - Python
official implementation of ICLR'2025 paper: Rethinking Bradley-Terry Models in Preference-based Reward Modeling: Foundations, Theory, and Alternatives
reward inverse-reinforcement-learning large-language-models rlhf reward-models largelanguagemodels reward-modeling llm-aligment llmalignment
-
Updated
Apr 2, 2025 - Python
A comrephensive collection of learning from rewards in the post-training and test-time scaling of LLMs, with a focus on both reward models and learning strategies across training, inference, and post-inference stages.
reinforcement-learning post-training self-correction reward-learning large-language-models llm llms reward-models reward-model reward-modeling guided-decoding test-time-scaling
-
Updated
Jun 13, 2025
This training offers an intensive exploration into the frontier of reinforcement learning techniques with large language models (LLMs). We will explore advanced topics such as Reinforcement Learning with Human Feedback (RLHF), Reinforcement Learning from AI Feedback (RLAIF), Reasoning LLMs, and demonstrate practical applications such as fine-tuning
-
Updated
Mar 9, 2026 - Jupyter Notebook
[CVPR 2025] Science-T2I: Addressing Scientific Illusions in Image Synthesis
-
Updated
Mar 31, 2026 - Python
An easy python package to run quick basic QA evaluations. This package includes standardized QA evaluation metrics and semantic evaluation metrics: Black-box and Open-Source large language model prompting and evaluation, exact match, F1 Score, PEDANT semantic match, transformer match. Our package also supports prompting OPENAI and Anthropic API.
qa-automation-test rl-training llm exact-matching llm-evaluation llm-evaluation-toolkit llm-evaluation-framework reward-modeling
-
Updated
Jul 18, 2025 - Python
Official Repo for Paper: "Reward Auditor: Inference on Reward Modeling Suitability in Real-World Perturbed Scenarios"
-
Updated
Jan 24, 2026 - Python
Learning to route instances for Human vs AI Feedback (ACL Main '25)
-
Updated
Jul 23, 2025 - Python
Revealing and unlocking the context boundary of reward models
-
Updated
Jan 11, 2026 - Python
[ACL2024 Findings]DMoERM: Recipes of Mixture-of-Experts for Effective Reward Modeling
-
Updated
Jun 6, 2024 - Python
ToolRM: Towards Agentic Tool-Use Reward Modeling
-
Updated
Jan 14, 2026 - Python
Code for SFT and RL
-
Updated
Jun 22, 2025 - Python
Implementation for our COLM paper "Off-Policy Corrected Reward Modeling for RLHF"
-
Updated
Jul 23, 2025 - Python
The code used in the paper "DogeRM: Equipping Reward Models with Domain Knowledge through Model Merging"
-
Updated
Oct 8, 2024 - Python
Source code of our paper "Transferring Textual Preferences to Vision-Language Understanding through Model Merging", ACL 2025
-
Updated
Apr 25, 2025 - Python
A novel Group Relative Reward Model (GRRM) framework enhances machine translation quality and reasoning capabilities by improving intra-group ranking through comparative analysis rather than isolated metric evaluation.
reinforcement-learning deep-learning machine-translation large-language-models llm-reasoning reward-modeling grpo
-
Updated
Mar 27, 2026 - Python
Building an LLM with RLHF involves fine-tuning using human-labeled preferences. Based on Learning to Summarize from Human Feedback, it uses supervised learning, reward modeling, and PPO to improve response quality and alignment.
transformer reinforcement-learning-algorithms fine-tuning ppo-agent policy-optimization-algorithms supervised-finetuning flan-t5 reward-modeling
-
Updated
Mar 24, 2025 - Jupyter Notebook
RewardAnything: Generalizable Principle-Following Reward Models
-
Updated
Jul 15, 2025 - HTML
Improve this page
Add a description, image, and links to the reward-modeling topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the reward-modeling topic, visit your repo's landing page and select "manage topics."