Cover Image

Improving the Physics of Video Generation with VJEPA-2 Reward Signal

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yuan, Jianhao, Zhang, Xiaofeng, Friedrich, Felix, Beltran-Velez, Nicolas, Hall, Melissa, Askari-Hemmat, Reyhane, Han, Xiaochuang, Ballas, Nicolas, Drozdzal, Michal, Romero-Soriano, Adriana
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Graphics
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Inference-time Physics Alignment of Video Generative Models with Latent World Models
by: Yuan, Jianhao, et al.
Published: (2026)

Improving Geo-diversity of Generated Images with Contextualized Vendi Score Guidance
by: Hemmat, Reyhane Askari, et al.
Published: (2024)

Increasing the Utility of Synthetic Images through Chamfer Guidance
by: Dall'Asen, Nicola, et al.
Published: (2025)

Feedback-guided Data Synthesis for Imbalanced Classification
by: Hemmat, Reyhane Askari, et al.
Published: (2023)

Multi-Modal Language Models as Text-to-Image Model Evaluators
by: Chen, Jiahui, et al.
Published: (2025)

Improving the Scaling Laws of Synthetic Data with Deliberate Practice
by: Askari-Hemmat, Reyhane, et al.
Published: (2025)

On Improved Conditioning Mechanisms and Pre-training Strategies for Diffusion Models
by: Ifriqi, Tariq Berrada, et al.
Published: (2024)

Multimodal RewardBench 2: Evaluating Omni Reward Models for Interleaved Text and Image
by: Hu, Yushi, et al.
Published: (2025)

DIG In: Evaluating Disparities in Image Generations with Indicators for Geographic Diversity
by: Hall, Melissa, et al.
Published: (2023)

Unified Text-Image Generation with Weakness-Targeted Post-Training
by: Chen, Jiahui, et al.
Published: (2026)

Why Less is More (Sometimes): A Theory of Data Curation
by: Dohmatob, Elvis, et al.
Published: (2025)

Harness Local Rewards for Global Benefits: Effective Text-to-Video Generation Alignment with Patch-level Reward Models
by: Wang, Shuting, et al.
Published: (2025)

Non-Euclidean Sliced Optimal Transport Sampling
by: Genest, Baptiste, et al.
Published: (2024)

Implementing a Machine Learning Deformer for CG Crowds: Our Journey
by: Arcelin, Bastien, et al.
Published: (2024)

NePHIM: A Neural Physics-Based Head-Hand Interaction Model
by: Wagner, Nicolas, et al.
Published: (2024)

The Intricate Dance of Prompt Complexity, Quality, Diversity, and Consistency in T2I Models
by: Xiaofeng, Zhang, et al.
Published: (2025)

Dr.Jit: A Just-In-Time Compiler for Differentiable Rendering
by: Jakob, Wenzel, et al.
Published: (2022)

Audio2Rig: Artist-oriented deep learning tool for facial animation
by: Arcelin, Bastien, et al.
Published: (2024)

Learning Human-like Locomotion Based on Biological Actuation and Rewards
by: Kim, Minkwan, et al.
Published: (2024)

Deformation Recovery: Localized Learning for Detail-Preserving Deformations
by: Sundararaman, Ramana, et al.
Published: (2024)

CAD-Coder: Text-to-CAD Generation with Chain-of-Thought and Geometric Reward
by: Guan, Yandong, et al.
Published: (2025)

Shap-MeD
by: Laverde, Nicolás, et al.
Published: (2025)

PosterReward: Unlocking Accurate Evaluation for High-Quality Graphic Design Generation
by: Lai, Jianyu, et al.
Published: (2026)

R3-RECON: Radiance-Field-Free Active Reconstruction via Renderability
by: Jin, Xiaofeng, et al.
Published: (2026)

Automatic Inbetweening for Stroke‐Based Painterly Animation
by: Nicolas Barroso, et al.
Published: (2024)

Non‐Euclidean Sliced Optimal Transport Sampling
by: Baptiste Genest, et al.
Published: (2024)

VideoFrom3D: 3D Scene Video Generation via Complementary Image and Video Diffusion Models
by: Kim, Geonung, et al.
Published: (2025)

TransVDM: Motion-Constrained Video Diffusion Model for Transparent Video Synthesis
by: Li, Menghao, et al.
Published: (2025)

Nearest Neighbor Classification for Classical Image Upsampling
by: Matthews, Evan, et al.
Published: (2024)

SURF: Signature-Retained Fast Video Generation
by: Ding, Kaixin, et al.
Published: (2025)

FreqPrior: Improving Video Diffusion Models with Frequency Filtering Gaussian Noise
by: Yuan, Yunlong, et al.
Published: (2025)

Holographic Parallax Improves 3D Perceptual Realism
by: Kim, Dongyeon, et al.
Published: (2024)

T2Bs: Text-to-Character Blendshapes via Video Generation
by: Luo, Jiahao, et al.
Published: (2025)

Artist‐Inator: Text‐based, Gloss‐aware Non‐photorealistic Stylization
by: J. Daniel Subias, et al.
Published: (2025)

Data Visualization for Improving Financial Literacy: A Systematic Review
by: Du, Meng, et al.
Published: (2025)

AnimaMimic: Imitating 3D Animation from Video Priors
by: Xie, Tianyi, et al.
Published: (2025)

HIL: Hybrid Imitation Learning of Diverse Parkour Skills from Videos
by: Wang, Jiashun, et al.
Published: (2025)

Topology-Aware Optimization of Gaussian Primitives for Human-Centric Volumetric Videos
by: Jiang, Yuheng, et al.
Published: (2025)

Improving Sparse IMU-based Motion Capture with Motion Label Smoothing
by: Meng, Zhaorui, et al.
Published: (2025)

Visualization of Escher‐like Kaleidoscopic Spherical Patterns of Regular Polyhedron Symmetry
by: Krzysztof Gdawiec, et al.
Published: (2024)