activity
20232026
most citedParameter-Efficient Fine-Tuning in Spectral Domain for Point Cloud Learning

2 citations · 8 across the 19 of their papers we have counts for

collaborators
Showing cs.CVShow all

20 papers · 1 filter

cs.CV2026

Qwen-Drive-1.0: An Initial Step towards a Vision-Language Foundation Model for Autonomous Driving

Xin Zhou, Zongchuang Zhao, Zhibo Yang +13

We present Qwen-Drive-1.0, an initial step towards a vision-language foundation model for autonomous driving. Qwen-Drive-1.0 retains the architecture of the pretrained vision-langu…

cs.CV2026

SimWAM: A Simple World Action Model for End-to-End Autonomous Driving

Zongchuang Zhao, Xin Zhou, Tianyang Xu +6

World-Action Models (WAMs) improve end-to-end autonomous driving by transferring video dynamics priors to action prediction, but existing methods incur costly test-time future imag…

cs.CV2026

ROAD: Reciprocal-Objective Alignment of Discriminative Semantics for 3D Shape Generation

Xiao Luo, Mingyang Du, Xin Zhou +5

High-fidelity 3D generation predominantly relies on scaling model capacity and data, which incurs prohibitive computational costs. This paradigm typically requires learning geometr…

cs.CV2026

HERMES++: Toward a Unified Driving World Model for 3D Scene Understanding and Generation

Xin Zhou, Dingkang Liang, Xiwu Chen +4

Driving world models serve as a pivotal technology for autonomous driving by simulating environmental dynamics. However, existing approaches predominantly focus on future scene gen…

cs.CV2026

Out of Sight but Not Out of Mind: Hybrid Memory for Dynamic Video World Models

Kaijin Chen, Dingkang Liang, Xin Zhou +4

Video world models have shown immense potential in simulating the physical world, yet existing memory mechanisms primarily treat environments as static canvases. When dynamic subje…

cs.CV2025

More Than Generation: Unifying Generation and Depth Estimation via Text-to-Image Diffusion Models

Hongkai Lin, Dingkang Liang, Mingyang Du +2

Generative depth estimation methods leverage the rich visual priors stored in pre-trained text-to-image diffusion models, demonstrating astonishing zero-shot capability. However, p…