ArXiv TLDR

Yuan Zhang

3 papers · Latest:

Artificial Intelligence

First-Order Efficiency for Probabilistic Value Estimation via A Statistical Viewpoint

This paper introduces EASE, an estimator for probabilistic values that minimizes first-order MSE by optimizing sampling and surrogate functions.

2605.02827
Robotics

Unified 4D World Action Modeling from Video Priors with Asynchronous Denoising

X-WAM is a unified 4D world model that combines real-time robotic action with high-fidelity 4D synthesis using video priors and asynchronous denoising.

2604.26694
Natural Language Processing

General365: Benchmarking General Reasoning in Large Language Models Across Diverse and Challenging Tasks

General365 is a new benchmark assessing LLMs' general reasoning, revealing their domain-dependent abilities and significant room for improvement beyond specialized tasks.

2604.11778

📬 Weekly AI Paper Digest

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