Verbalized Sampling, a training-free prompting strategy to mitigate mode collapse in LLMs by requesting responses with probabilities. Achieves 2-3x diversity improvement while maintaining quality. Model-agnostic framework with CLI/API for creative writing, synthetic data generation, and dialogue simulation.

A Python library for dynamic classifier and ensemble selection

MSGAN: Mode Seeking Generative Adversarial Networks for Diverse Image Synthesis (CVPR2019)

[ICCV-2023] Official code for work "HumanMAC: Masked Motion Completion for Human Motion Prediction".

Code base for the precision, recall, density, and coverage metrics for generative models. ICML 2020.

[ECCV 2020] Official PyTorch Implementation of "DLow: Diversifying Latent Flows for Diverse Human Motion Prediction". ECCV 2020.

ECCV2018

NAACL 2019: Submodular optimization-based diverse paraphrasing and its effectiveness in data augmentation

The official implementation of "DGCN: Diversified Recommendation with Graph Convolutional Networks" (WWW '21)

👩‍💻 Repository with Awesome PyLadies' content

Code for Paper (Preserving Diversity in Supervised Fine-tuning of Large Language Models)

[NeurIPS 2024] Train LLMs with diverse system messages reflecting individualized preferences to generalize to unseen system messages

Code from the paper "Effective Diversity in Population Based Reinforcement Learning", presented as a spotlight at NeurIPS 2020. This is the Evolution Strategies implementation, but of course the method can be used for gradient based RL algorithms (e.g. TD3).

A pytorch implementation for the MMI-anti model

creating hybrid-gene phylogenetic trees for diversity analyses

MAP-Elites Hyper-Heuristic based algorithm for generating schedules for the Resource Constrained Project Scheduling Problem

SIREN: A Simulation Framework for Understanding the Effects of Recommender Systems in Online News Environments

Jointly Measuring Diversity and Quality in Text Generation Models

[CVPR 2022] "The Principle of Diversity: Training Stronger Vision Transformers Calls for Reducing All Levels of Redundancy" by Tianlong Chen, Zhenyu Zhang, Yu Cheng, Ahmed Awadallah, Zhangyang Wang

Code for Blog Post: Can Better Cold-Start Strategies Improve RL Training for LLMs?