AI.info

Naoaki Okazaki

Explore Naoaki Okazaki on AI.info.

• Autoregressive Direct Preference Optimization
• Aligning Tree-Search Policies with Fixed Token Budgets in Test-Time Scaling of LLMs
• From Correspondence to Actions: Human-Like Multi-Image Spatial Reasoning in Multi-modal Large Language Models
• Stopping Computation for Converged Tokens in Masked Diffusion-LM Decoding
• From Interpretability to Performance: Optimizing Retrieval Heads for Long-Context Language Models
• QuantumBench: A Benchmark for Quantum Problem Solving