ArXiv TLDR

Yaniv Romano

2 papers · Latest:

Robotics

Temporal Difference Calibration in Sequential Tasks: Application to Vision-Language-Action Models

This paper introduces Temporal Difference (TD) calibration for Vision-Language-Action models, improving uncertainty quantification in sequential robotic tasks.

2604.20472
Natural Language Processing

Accelerating Speculative Decoding with Block Diffusion Draft Trees

DDTree accelerates speculative decoding by constructing a draft tree from block diffusion models, improving acceptance length and efficiency.

2604.12989

📬 Weekly AI Paper Digest

Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.