Naoaki Okazaki

Stopping Computation for Converged Tokens in Masked Diffusion-LM Decoding

Rewriting Pre-Training Data Boosts LLM Performance in Math and Code

Autoregressive Direct Preference Optimization

Machine Text Detectors are Membership Inference Attacks

ExaGPT: Example-Based Machine-Generated Text Detection for Human Interpretability

Building Instruction-Tuning Datasets from Human-Written Instructions with Open-Weight Large Language Models

Vision Language Model Based Caption Evaluation Method Leveraging Visual Context Extraction