Cover Image

Can Test-Time Scaling Improve World Foundation Model?

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Cong, Wenyan, Zhu, Hanqing, Wang, Peihao, Liu, Bangya, Xu, Dejia, Wang, Kevin, Pan, David Z., Wang, Yan, Fan, Zhiwen, Wang, Zhangyang
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS
by: Fan, Zhiwen, et al.
Published: (2023)

VideoLifter: Lifting Videos to 3D with Fast Hierarchical Stereo Alignment
by: Cong, Wenyan, et al.
Published: (2025)

Why Neural Network Can Discover Symbolic Structures with Gradient-based Training: An Algebraic and Geometric Foundation for Neurosymbolic Reasoning
by: Wang, Peihao, et al.
Published: (2025)

SteinDreamer: Variance Reduction for Text-to-3D Score Distillation via Stein Identity
by: Wang, Peihao, et al.
Published: (2023)

Lift3D: Zero-Shot Lifting of Any 2D Vision Model to 3D
by: T, Mukund Varma, et al.
Published: (2024)

E3D-Bench: A Benchmark for End-to-End 3D Geometric Foundation Models
by: Cong, Wenyan, et al.
Published: (2025)

Taming Mode Collapse in Score Distillation for Text-to-3D Generation
by: Wang, Peihao, et al.
Published: (2023)

FSGS: Real-Time Few-shot View Synthesis using Gaussian Splatting
by: Zhu, Zehao, et al.
Published: (2023)

Large Spatial Model: End-to-end Unposed Images to Semantic 3D
by: Fan, Zhiwen, et al.
Published: (2024)

Oscillation Inversion: Understand the structure of Large Flow Model through the Lens of Inversion Method
by: Zheng, Yan, et al.
Published: (2024)

Martian World Model: Controllable Video Synthesis with Physically Accurate 3D Reconstructions
by: Li, Longfei, et al.
Published: (2025)

InstantSplat: Sparse-view Gaussian Splatting in Seconds
by: Fan, Zhiwen, et al.
Published: (2024)

4DGen: Grounded 4D Content Generation with Spatial-temporal Consistency
by: Yin, Yuyang, et al.
Published: (2023)

Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fields
by: Zhou, Shijie, et al.
Published: (2023)

INR-Arch: A Dataflow Architecture and Compiler for Arbitrary-Order Gradient Computations in Implicit Neural Representation Processing
by: Abi-Karam, Stefan, et al.
Published: (2023)

DreamScene360: Unconstrained Text-to-3D Scene Generation with Panoramic Gaussian Splatting
by: Zhou, Shijie, et al.
Published: (2024)

4K4DGen: Panoramic 4D Generation at 4K Resolution
by: Li, Renjie, et al.
Published: (2024)

LLMGeo: Benchmarking Large Language Models on Image Geolocation In-the-wild
by: Wang, Zhiqiang, et al.
Published: (2024)

Feature4X: Bridging Any Monocular Video to 4D Agentic AI with Versatile Gaussian Feature Fields
by: Zhou, Shijie, et al.
Published: (2025)

Meta ControlNet: Enhancing Task Adaptation via Meta Learning
by: Yang, Junjie, et al.
Published: (2023)

SpatialStack: Layered Geometry-Language Fusion for 3D VLM Spatial Reasoning
by: Zhang, Jian, et al.
Published: (2026)

Steepest Descent Density Control for Compact 3D Gaussian Splatting
by: Wang, Peihao, et al.
Published: (2025)

FlexGS: Train Once, Deploy Everywhere with Many-in-One Flexible 3D Gaussian Splatting
by: Liu, Hengyu, et al.
Published: (2025)

AGG: Amortized Generative 3D Gaussians for Single Image to 3D
by: Xu, Dejia, et al.
Published: (2024)

CamCo: Camera-Controllable 3D-Consistent Image-to-Video Generation
by: Xu, Dejia, et al.
Published: (2024)

$\nabla$-Reasoner: LLM Reasoning via Test-Time Gradient Descent in Latent Space
by: Wang, Peihao, et al.
Published: (2026)

Learning Actionable Manipulation Recovery via Counterfactual Failure Synthesis
by: Li, Dayou, et al.
Published: (2026)

Position: Weight Space Should Be a First-Class Generative AI Modality
by: Wang, Zhangyang, et al.
Published: (2026)

VASE: Object-Centric Appearance and Shape Manipulation of Real Videos
by: Peruzzo, Elia, et al.
Published: (2024)

Egocentric World Model for Photorealistic Hand-Object Interaction Synthesis
by: Li, Dayou, et al.
Published: (2026)

When Do Graph Foundation Models Transfer? A Data-Centric Theory
by: Zhu, Jiajun, et al.
Published: (2026)

Comp4D: LLM-Guided Compositional 4D Scene Generation
by: Xu, Dejia, et al.
Published: (2024)

Cavia: Camera-controllable Multi-view Video Diffusion with View-Integrated Attention
by: Xu, Dejia, et al.
Published: (2024)

Generalization Error Analysis for Sparse Mixture-of-Experts: A Preliminary Study
by: Zhao, Jinze, et al.
Published: (2024)

Diffusion4D: Fast Spatial-temporal Consistent 4D Generation via Video Diffusion Models
by: Liang, Hanwen, et al.
Published: (2024)

Expressive Gaussian Human Avatars from Monocular RGB Video
by: Hu, Hezhen, et al.
Published: (2024)

SwinGS: Sliding Window Gaussian Splatting for Volumetric Video Streaming with Arbitrary Length
by: Liu, Bangya, et al.
Published: (2024)

APOLLO: SGD-like Memory, AdamW-level Performance
by: Zhu, Hanqing, et al.
Published: (2024)

Learning Traffic Crashes as Language: Datasets, Benchmarks, and What-if Causal Analyses
by: Fan, Zhiwen, et al.
Published: (2024)

CIPHER: Culvert Inspection through Pairwise Frame Selection and High-Efficiency Reconstruction
by: Lee, Seoyoung, et al.
Published: (2026)