10 papers
SimWAM: A Simple World Action Model for End-to-End Autonomous Driving
Zongchuang Zhao, Xin Zhou, Tianyang Xu +6
In autonomous driving, World-Action Models (WAMs) have improved end-to-end planning by transferring video dynamics priors to action prediction, but many still couple planning with…
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…
Advancing Narrative Long Video Generation via Training-Free Identity-Aware Memory
Jinzhuo Liu, Jiangning Zhang, Wencan Jiang +5
Autoregressive video generation has improved rapidly in visual fidelity and interactivity, but it still suffers from long-term inconsistency and memory degradation. Most existing s…
Generative 3D Gaussians with Learned Density Control
Runjie Yan, Yan-Pei Cao, Peng Wang +2
We present Density-Sampled Gaussians (DeG), a novel 3D representation designed to bridge the gap between adaptive rendering primitives and scalable generative modeling. Unlike exis…
When Numbers Speak: Aligning Textual Numerals and Visual Instances in Text-to-Video Diffusion Models
Zhengyang Sun, Yu Chen, Xin Zhou +4
Text-to-video diffusion models have enabled open-ended video synthesis, but often struggle with generating the correct number of objects specified in a prompt. We introduce NUMINA…
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…
Generation Models Know Space: Unleashing Implicit 3D Priors for Scene Understanding
Xianjin Wu, Dingkang Liang, Tianrui Feng +5
While Multimodal Large Language Models demonstrate impressive semantic capabilities, they often suffer from spatial blindness, struggling with fine-grained geometric reasoning and…
FVAR: Visual Autoregressive Modeling via Next Focus Prediction
Xiaofan Li, Chenming Wu, Yanpeng Sun +6
Visual autoregressive models achieve remarkable generation quality through next-scale predictions across multi-scale token pyramids. However, the conventional method uses uniform s…
Video4Edit: Viewing Image Editing as a Degenerate Temporal Process
Xiaofan Li, Yanpeng Sun, Chenming Wu +5
We observe that recent advances in multimodal foundation models have propelled instruction-driven image generation and editing into a genuinely cross-modal, cooperative regime. Nev…
DriVerse: Navigation World Model for Driving Simulation via Multimodal Trajectory Prompting and Motion Alignment
Xiaofan Li, Chenming Wu, Zhao Yang +5
This paper presents DriVerse, a generative model for simulating navigation-driven driving scenes from a single image and a future trajectory. Previous autonomous driving world mode…