works on

From the 1 of 6 linked papers with an AI index.

collaborators

6 papers

cs.AI2026

Concept-Guided Spatial Regularization for World Models in Atari Pong

Yukuan Lu, Zaishuo Xia, Weyl Lu +1

The paper evaluates several visual world‑model agents on Atari Pong, identifies systematic rollout failures, and introduces Concept‑Guided Spatial Regularization (CGSReg) to improv…

cs.AI2026

When Models Know When They Do Not Know: Calibration, Cascading, and Cleaning

Chenjie Hao, Weyl Lu, Yuko Ishiwaka +3

When a model knows when it does not know, many possibilities emerge. The first question is how to enable a model to recognize that it does not know. A promising approach is to use…

cs.LG2026

Deep Networks Favor Simple Data

Weyl Lu, Chenjie Hao, Yubei Chen

Estimated density is often interpreted as indicating how typical a sample is under a model. Yet deep models trained on one dataset can assign higher density to simpler out-of-distr…

cs.LG2025

SmallWorlds: Assessing Dynamics Understanding of World Models in Isolated Environments

Xinyi Li, Zaishuo Xia, Weyl Lu +2

Current world models lack a unified and controlled setting for systematic evaluation, making it difficult to assess whether they truly capture the underlying rules that govern envi…

cs.LG2025

Neural Motion Simulator: Pushing the Limit of World Models in Reinforcement Learning

Chenjie Hao, Weyl Lu, Yifan Xu +1

An embodied system must not only model the patterns of the external world but also understand its own motion dynamics. A motion dynamic model is essential for efficient skill acqui…

cs.LG2025

RA-PbRL: Provably Efficient Risk-Aware Preference-Based Reinforcement Learning

Yujie Zhao, Jose Efraim Aguilar Escamill, Weyl Lu +1

Reinforcement Learning from Human Feedback (RLHF) has recently surged in popularity, particularly for aligning large language models and other AI systems with human intentions. At…