activity
20242026
collaborators

8 papers

cs.CV2026

EgoDyn-Bench: Evaluating Ego-Motion Understanding in Vision-Centric Foundation Models for Autonomous Driving

Finn Rasmus Schäfer, Yuan Gao, Dingrui Wang +5

While Vision-Language Models (VLMs) have advanced high-level reasoning in autonomous driving, their ability to ground this reasoning in the underlying physics of ego-motion remains…

cs.CV2026

WorldCache: Accelerating World Models for Free via Heterogeneous Token Caching

Weilun Feng, Guoxin Fan, Haotong Qin +10

Diffusion-based world models have shown strong potential for unified world simulation, but the iterative denoising remains too costly for interactive use and long-horizon rollouts.…

cs.CV2026

Target-Bench: Can Video World Models Achieve Mapless Path Planning with Semantic Targets?

Dingrui Wang, Zhihao Liang, Hongyuan Ye +13

While recent video world models can generate highly realistic videos, their ability to perform semantic reasoning and planning remains unclear and unquantified. We introduce Target…

cs.AI2026

DUPLEX: Agentic Dual-System Planning via LLM-Driven Information Extraction

Keru Hua, Ding Wang, Yaoying Gu +1

While Large Language Models (LLMs) provide semantic flexibility for robotic task planning, their susceptibility to hallucination and logical inconsistency limits their reliability…

cs.RO2026

Foundation Models in Autonomous Driving: A Survey on Scenario Generation and Scenario Analysis

Yuan Gao, Mattia Piccinini, Yuchen Zhang +12

For autonomous vehicles, safe navigation in complex environments depends on handling a broad range of diverse and rare driving scenarios. Simulation- and scenario-based testing hav…

cs.AI2025

Enhancing Physical Consistency in Lightweight World Models

Dingrui Wang, Zhexiao Sun, Zhouheng Li +8

A major challenge in deploying world models is the trade-off between size and performance. Large world models can capture rich physical dynamics but require massive computing resou…