Cover Image

Beyond Pixels: Introducing Geometric-Semantic World Priors for Video-based Embodied Models via Spatio-temporal Alignment

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Tang, Jinzhou, zhang, Jusheng, Liu, Sidi, Xiu, Waikit, Lv, Qinhan, Li, Xiying
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

LASAR: Towards Spatio-temporal Reasoning with Latent Cognitive Map
by: Tang, Jinzhou, et al.
Published: (2026)

HiVA: Self-organized Hierarchical Variable Agent via Goal-driven Semantic-Topological Evolution
by: Tang, Jinzhou, et al.
Published: (2025)

Contrastive Learning-Driven Traffic Sign Perception: Multi-Modal Fusion of Text and Vision
by: Lu, Qiang, et al.
Published: (2025)

Traffic-MLLM: Curiosity-Regularized Supervised Learning for Traffic Scenario Case-Based Reasoning
by: Xiu, Waikit, et al.
Published: (2025)

From Motion to Behavior: Hierarchical Modeling of Humanoid Generative Behavior Control
by: Zhang, Jusheng, et al.
Published: (2025)

DepthSSC: Monocular 3D Semantic Scene Completion via Depth-Spatial Alignment and Voxel Adaptation
by: Yao, Jiawei, et al.
Published: (2023)

ResAgent: Entropy-based Prior Point Discovery and Visual Reasoning for Referring Expression Segmentation
by: Wang, Yihao, et al.
Published: (2026)

Beyond Pixels: Leveraging the Language of Soccer to Improve Spatio-Temporal Action Detection in Broadcast Videos
by: Ochin, Jeremie, et al.
Published: (2025)

Task-Adapter++: Task-specific Adaptation with Order-aware Alignment for Few-shot Action Recognition
by: Cao, Congqi, et al.
Published: (2025)

HybridToken-VLM: Hybrid Token Compression for Vision-Language Models
by: Zhang, Jusheng, et al.
Published: (2025)

Multimodal Spatio-temporal Graph Learning for Alignment-free RGBT Video Object Detection
by: Wang, Qishun, et al.
Published: (2025)

PastNet: Introducing Physical Inductive Biases for Spatio-temporal Video Prediction
by: Wu, Hao, et al.
Published: (2023)

GeoVideo: Introducing Geometric Regularization into Video Generation Model
by: Bai, Yunpeng, et al.
Published: (2025)

MoWM: Mixture-of-World-Models for Embodied Planning via Latent-to-Pixel Feature Modulation
by: Yu, Yangcheng, et al.
Published: (2025)

Video-Language Alignment via Spatio-Temporal Graph Transformer
by: Zhang, Shi-Xue, et al.
Published: (2024)

KVPO: ODE-Native GRPO for Autoregressive Video Alignment via KV Semantic Exploration
by: Zhang, Ruicheng, et al.
Published: (2026)

Beyond Pixel Simulation: Pathology Image Generation via Diagnostic Semantic Tokens and Prototype Control
by: Han, Minghao, et al.
Published: (2025)

SGR-OCC: Evolving Monocular Priors for Embodied 3D Occupancy Prediction via Soft-Gating Lifting and Semantic-Adaptive Geometric Refinement
by: Guo, Yiran, et al.
Published: (2026)

CoAgent: Collaborative Planning and Consistency Agent for Coherent Video Generation
by: Zeng, Qinglin, et al.
Published: (2025)

Fast Omni-Directional Image Super-Resolution: Adapting the Implicit Image Function with Pixel and Semantic-Wise Spherical Geometric Priors
by: Shen, Xuelin, et al.
Published: (2025)

MM-CoT:A Benchmark for Probing Visual Chain-of-Thought Reasoning in Multimodal Models
by: Zhang, Jusheng, et al.
Published: (2025)

SNOW: Spatio-Temporal Scene Understanding with World Knowledge for Open-World Embodied Reasoning
by: Sohn, Tin Stribor, et al.
Published: (2025)

SeeClear: Semantic Distillation Enhances Pixel Condensation for Video Super-Resolution
by: Tang, Qi, et al.
Published: (2024)

Stable Single-Pixel Contrastive Learning for Semantic and Geometric Tasks
by: Pogorelyuk, Leonid, et al.
Published: (2025)

Mitigating Prior Shape Bias in Point Clouds via Differentiable Center Learning
by: Li, Zhe, et al.
Published: (2024)

Beyond Semantic Features: Pixel-level Mapping for Generalized AI-Generated Image Detection
by: Zhou, Chenming, et al.
Published: (2025)

Semantic Lens: Instance-Centric Semantic Alignment for Video Super-Resolution
by: Tang, Qi, et al.
Published: (2023)

Top-Down Semantic Refinement for Image Captioning
by: Zhang, Jusheng, et al.
Published: (2025)

Wanderland: Geometrically Grounded Simulation for Open-World Embodied AI
by: Liu, Xinhao, et al.
Published: (2025)

SPARS3R: Semantic Prior Alignment and Regularization for Sparse 3D Reconstruction
by: Tang, Yutao, et al.
Published: (2024)

STAF: 3D Human Mesh Recovery from Video with Spatio-Temporal Alignment Fusion
by: Yao, Wei, et al.
Published: (2024)

Blur-aware Spatio-temporal Sparse Transformer for Video Deblurring
by: Zhang, Huicong, et al.
Published: (2024)

STDiff: Spatio-temporal Diffusion for Continuous Stochastic Video Prediction
by: Ye, Xi, et al.
Published: (2023)

DreamSAC: Learning Hamiltonian World Models via Symmetry Exploration
by: Tang, Jinzhou, et al.
Published: (2026)

DVFace: Spatio-Temporal Dual-Prior Diffusion for Video Face Restoration
by: Chen, Zheng, et al.
Published: (2026)

Representations Before Pixels: Semantics-Guided Hierarchical Video Prediction
by: Karypidis, Efstathios, et al.
Published: (2026)

Compression Beyond Pixels: Semantic Compression with Multimodal Foundation Models
by: Shen, Ruiqi, et al.
Published: (2025)

Beyond Pixels: Semantic-aware Typographic Attack for Geo-Privacy Protection
by: Zhu, Jiayi, et al.
Published: (2025)

Rethinking Video Generation Model for the Embodied World
by: Deng, Yufan, et al.
Published: (2026)

Unleashing Semantic and Geometric Priors for 3D Scene Completion
by: Chen, Shiyuan, et al.
Published: (2025)