Xin Zhou
5 papers · Latest:
HERMES++: Toward a Unified Driving World Model for 3D Scene Understanding and Generation
HERMES++ unifies 3D scene understanding and future geometry prediction in a driving world model, outperforming specialist methods.
Inter-Stance: A Dyadic Multimodal Corpus for Conversational Stance Analysis
Inter-Stance introduces a 20TB multimodal dyadic corpus for conversational stance analysis, enabling novel modeling of interpersonal behavior.
Quantum limits on squeezing
This paper derives quantum limits on steady-state squeezing in bosonic networks, showing new bounds for dissipative and parametrically driven systems.
OVPD: A Virtual-Physical Fusion Testing Dataset of OnSite Auton-omous Driving Challenge
OVPD is a new virtual-physical fusion dataset for autonomous driving, offering high-fidelity, replayable, and diagnosable testing data.
When Numbers Speak: Aligning Textual Numerals and Visual Instances in Text-to-Video Diffusion Models
NUMINA improves numerical alignment in text-to-video diffusion models by guiding regeneration, boosting counting accuracy and CLIP alignment.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.