✨Terminal Velocity Matching

📝 Summary:
Terminal Velocity Matching TVM generalizes flow matching for high-fidelity generative modeling. It achieves state-of-the-art ImageNet performance with minimal steps, e.g., 1.99 FID in 4 NFEs, through improved diffusion transition modeling and adapted transformers.

🔹 Publication Date: Published on Nov 24

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.19797
• PDF: https://arxiv.org/pdf/2511.19797

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#GenerativeAI #FlowMatching #DeepLearning #ComputerVision #DiffusionModels

✨DiG-Flow: Discrepancy-Guided Flow Matching for Robust VLA Models

📝 Summary:
DiG-Flow enhances VLA model robustness by using geometric regularization to align observation and action embeddings. It measures embedding discrepancy, applies residual updates, and consistently boosts performance on complex tasks and with limited data.

🔹 Publication Date: Published on Dec 1

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2512.01715
• PDF: https://arxiv.org/pdf/2512.01715
• Project Page: https://beingbeyond.github.io/DiG-Flow/
• Github: https://beingbeyond.github.io/DiG-Flow

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#VLAModels #RobustAI #FlowMatching #MachineLearning #DeepLearning

✨Stable Velocity: A Variance Perspective on Flow Matching

📝 Summary:
Stable Velocity tackles high-variance training in flow matching by identifying low-variance regimes. It introduces StableVM and VA-REPA for more efficient training, and StableVS for over 2x faster sampling. This improves both training and inference without compromising quality.

🔹 Publication Date: Published on Feb 5

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.05435
• PDF: https://arxiv.org/pdf/2602.05435
• Project Page: https://linydthu.github.io/StableVelocity/
• Github: https://github.com/linYDTHU/StableVelocity

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#FlowMatching #GenerativeAI #MachineLearning #DeepLearning #VarianceReduction

✨Best of Both Worlds: Multimodal Reasoning and Generation via Unified Discrete Flow Matching

📝 Summary:
UniDFlow is a unified discrete flow-matching framework for multimodal understanding, generation, and editing. It decouples understanding and generation via low-rank adapters and improves tasks with reference-based alignment without retraining. This achieves SOTA performance and strong zero-shot g...

🔹 Publication Date: Published on Feb 12

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.12221
• PDF: https://arxiv.org/pdf/2602.12221
• Project Page: https://plan-lab.github.io/unidflow

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#MultimodalAI #GenerativeAI #FlowMatching #MachineLearning #DeepLearning

✨Unified Number-Free Text-to-Motion Generation Via Flow Matching

📝 Summary:
Existing text-to-motion models struggle with variable agents, leading to inefficiency and errors. This paper proposes Unified Motion Flow UMF, a two-stage approach prior and reaction that uses P-Flow and S-Flow in a unified latent space. UMF effectively generates multi-person motion from text, mi...

🔹 Publication Date: Published on Mar 27

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.27040
• PDF: https://arxiv.org/pdf/2603.27040
• Project Page: https://githubhgh.github.io/umf/
• Github: https://github.com/Githubhgh/UMF_CVPR

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#TextToMotion #FlowMatching #GenerativeAI #MotionSynthesis #DeepLearning

✨WorldFlow3D: Flowing Through 3D Distributions for Unbounded World Generation

📝 Summary:
WorldFlow3D generates unbounded 3D worlds by modeling 3D data distributions as a flow matching problem. This latent-free approach achieves rapid convergence and high-quality generation with controllable geometric and texture properties. It outperforms existing methods on both real and synthetic s...

🔹 Publication Date: Published on Mar 31

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.29089
• PDF: https://arxiv.org/pdf/2603.29089
• Project Page: https://princeton-computational-imaging.github.io/WorldFlow3D/

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#3DGeneration #GenerativeAI #FlowMatching #ComputerGraphics #AIResearch