Jian Guo

LazyTrain boosts training efficiency by 1.24× and enables larger batch sizes, revolutionizing resource allocation for large language models on limited hardware.

LAGO Policy achieves smooth, collision-free manipulation by seamlessly integrating trajectory optimization with advanced diffusion techniques, setting a new standard for real-world robotic execution.

Bayesian-Agent transforms how LLM agents evolve skills, achieving up to 100% success on complex benchmarks through a novel posterior-guided optimization approach.

Current image quality metrics struggle to articulate *why* one high-quality image is better than another, but this challenge shows MLLMs are closing the gap by providing expert-level explanations.

Uncover the hidden dynamics of your RL agent with a new visualization framework that reveals how TD errors sculpt the optimization landscape and drive policy updates.

Visualizing the loss landscape of off-policy RL critics reveals distinct geometric patterns linked to convergence and divergence, offering a new diagnostic tool for understanding optimization dynamics.

Visualizing the critic's loss landscape reveals distinct characteristics linked to stable vs. unstable learning in online RL, offering a new window into algorithm dynamics.

Achieve state-of-the-art dynamic graph anomaly detection with limited labels by learning a robust decision boundary around normal data, outperforming methods that overfit to scarce anomalies.