AI.info

Daisuke Oba

Explore Daisuke Oba on AI.info.

• 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