Cover Image

Theoretical Guarantees for High Order Trajectory Refinement in Generative Flows

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Gong, Chengyue, Li, Xiaoyu, Liang, Yingyu, Long, Jiangxuan, Shi, Zhenmei, Song, Zhao, Tian, Yu
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

High-Order Matching for One-Step Shortcut Diffusion Models
by: Chen, Bo, et al.
Published: (2025)

HOFAR: High-Order Augmentation of Flow Autoregressive Transformers
by: Liang, Yingyu, et al.
Published: (2025)

On Computational Limits of FlowAR Models: Expressivity and Efficiency
by: Cao, Yang, et al.
Published: (2025)

RichSpace: Enriching Text-to-Video Prompt Space via Text Embedding Interpolation
by: Cao, Yuefan, et al.
Published: (2025)

Unraveling the Smoothness Properties of Diffusion Models: A Gaussian Mixture Perspective
by: Liang, Yingyu, et al.
Published: (2024)

Universal Approximation of Visual Autoregressive Transformers
by: Chen, Yifang, et al.
Published: (2025)

Visual Autoregressive Transformers Must Use $Ω(n^2 d)$ Memory
by: Cao, Yang, et al.
Published: (2025)

Text-to-Image Diffusion Models Cannot Count, and Prompt Refinement Cannot Help
by: Guo, Xuyang, et al.
Published: (2025)

On Computational Limits and Provably Efficient Criteria of Visual Autoregressive Models: A Fine-Grained Complexity Analysis
by: Ke, Yekun, et al.
Published: (2025)

Force Matching with Relativistic Constraints: A Physics-Inspired Approach to Stable and Efficient Generative Modeling
by: Cao, Yang, et al.
Published: (2025)

Can You Count to Nine? A Human Evaluation Benchmark for Counting Limits in Modern Text-to-Video Models
by: Guo, Xuyang, et al.
Published: (2025)

Beyond Linear Approximations: A Novel Pruning Approach for Attention Matrix
by: Liang, Yingyu, et al.
Published: (2024)

Circuit Complexity Bounds for RoPE-based Transformer Architecture
by: Chen, Bo, et al.
Published: (2024)

Your Vision-Language Model Can't Even Count to 20: Exposing the Failures of VLMs in Compositional Counting
by: Guo, Xuyang, et al.
Published: (2025)

Towards High-Order Mean Flow Generative Models: Feasibility, Expressivity, and Provably Efficient Criteria
by: Cao, Yang, et al.
Published: (2025)

Unsupervised Object Detection with Theoretical Guarantees
by: Longa, Marian, et al.
Published: (2024)

T2VTextBench: A Human Evaluation Benchmark for Textual Control in Video Generation Models
by: Guo, Xuyang, et al.
Published: (2025)

T2VPhysBench: A First-Principles Benchmark for Physical Consistency in Text-to-Video Generation
by: Guo, Xuyang, et al.
Published: (2025)

T2VWorldBench: A Benchmark for Evaluating World Knowledge in Text-to-Video Generation
by: Chen, Yubin, et al.
Published: (2025)

FlowTurbo: Towards Real-time Flow-Based Image Generation with Velocity Refiner
by: Zhao, Wenliang, et al.
Published: (2024)

DiReCT: Disentangled Regularization of Contrastive Trajectories for Physics-Refined Video Generation
by: Meyarian, Abolfazl, et al.
Published: (2026)

JanusFlow: Harmonizing Autoregression and Rectified Flow for Unified Multimodal Understanding and Generation
by: Ma, Yiyang, et al.
Published: (2024)

Generative Modelling with High-Order Langevin Dynamics
by: Shi, Ziqiang, et al.
Published: (2024)

Learning Generalized and Flexible Trajectory Models from Omni-Semantic Supervision
by: Zhu, Yuanshao, et al.
Published: (2025)

LoCoT2V-Bench: Benchmarking Long-Form and Complex Text-to-Video Generation
by: Zheng, Xiangqing, et al.
Published: (2025)

Theoretical Constraints on the Expressive Power of $\mathsf{RoPE}$-based Tensor Attention Transformers
by: Li, Xiaoyu, et al.
Published: (2024)

Locality-aware Parallel Decoding for Efficient Autoregressive Image Generation
by: Zhang, Zhuoyang, et al.
Published: (2025)

Context-Aware Weakly Supervised Image Manipulation Localization with SAM Refinement
by: Wang, Xinghao, et al.
Published: (2025)

RefineNet: Enhancing Text-to-Image Conversion with High-Resolution and Detail Accuracy through Hierarchical Transformers and Progressive Refinement
by: Shi, Fan
Published: (2023)

Letting Trajectories Spread: Quality-Preserving Control for Diverse Flow Matching
by: Wu, Jingxuan, et al.
Published: (2025)

Seeking Consistent Flat Minima for Better Domain Generalization via Refining Loss Landscapes
by: Li, Aodi, et al.
Published: (2024)

InfBaGel: Human-Object-Scene Interaction Generation with Dynamic Perception and Iterative Refinement
by: Zou, Yude, et al.
Published: (2026)

Theoretical Foundation of Flow-Based Time Series Generation: Provable Approximation, Generalization, and Efficiency
by: Long, Jiangxuan, et al.
Published: (2025)

Seeing Right but Saying Wrong: Inter- and Intra-Layer Refinement in MLLMs without Training
by: Song, Shezheng, et al.
Published: (2026)

Is A Picture Worth A Thousand Words? Delving Into Spatial Reasoning for Vision Language Models
by: Wang, Jiayu, et al.
Published: (2024)

Training-Free Refinement of Flow Matching with Divergence-based Sampling
by: Cha, Yeonwoo, et al.
Published: (2026)

MirrorDiffusion: Stabilizing Diffusion Process in Zero-shot Image Translation by Prompts Redescription and Beyond
by: Lin, Yupei, et al.
Published: (2024)

MagicMan: Generative Novel View Synthesis of Humans with 3D-Aware Diffusion and Iterative Refinement
by: He, Xu, et al.
Published: (2024)

Trajectory Consistency for One-Step Generation on Euler Mean Flows
by: Li, Zhiqi, et al.
Published: (2026)

ArcFlow: Unleashing 2-Step Text-to-Image Generation via High-Precision Non-Linear Flow Distillation
by: Yang, Zihan, et al.
Published: (2026)