works on

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

collaborators

6 papers

cs.LG2026

Beyond Myopic World Models: Long-Horizon End-to-End Training for Direct Future Prediction

Xinyi Li, Zaishuo Xia, Chenjie Hao +1

World models are expected to support imagination over extended temporal horizons, yet most are still trained through local few-step prediction objectives and deployed by recursivel…

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.CV2026

MotionPyramid: Hierarchical Motion Representation and Residual Interfaces

Gao Zhu, Zaishuo Xia, Yubei Chen

We ask whether the representational hierarchy seen in perception, from local primitives such as edges to higher level structures such as parts and objects, can be established for m…

cs.LG2026

Cloning Deterministic Worlds: The Critical Role of Latent Geometry in Long-Horizon World Models

Zaishuo Xia, Yukuan Lu, Xinyi Li +2

A world model is an internal model that simulates how the world evolves. Given past observations and actions, it predicts the future physical state of both the embodied agent and i…

cs.CL2026

How Do Large Language Models Learn Concepts During Continual Pre-Training?

Barry Menglong Yao, Sha Li, Yunzhi Yao +4

Human beings primarily understand the world through concepts (e.g., dog), abstract mental representations that structure perception, reasoning, and learning. However, how large lan…

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…