Cover Image

Beyond the Golden Data: Resolving the Motion-Vision Quality Dilemma via Timestep Selective Training

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Luo, Xiangyang, Li, Qingyu, Li, Yuming, Huang, Guanbo, Zhu, Yongjie, Qin, Wenyu, Wang, Meng, Wan, Pengfei, Huang, Shao-Lun
Format:	Preprint
Published:	2026
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

FilmWeaver: Weaving Consistent Multi-Shot Videos with Cache-Guided Autoregressive Diffusion
by: Luo, Xiangyang, et al.
Published: (2025)

Analytic Score Optimization for Multi Dimension Video Quality Assessment
by: Lin, Boda, et al.
Published: (2026)

AEGPO: Adaptive Entropy-Guided Policy Optimization for Diffusion Models
by: Li, Yuming, et al.
Published: (2026)

KPM-Bench: A Kinematic Parsing Motion Benchmark for Fine-grained Motion-centric Video Understanding
by: Lin, Boda, et al.
Published: (2026)

ReflexFlow: Rethinking Learning Objective for Exposure Bias Alleviation in Flow Matching
by: Huang, Guanbo, et al.
Published: (2025)

Embed-RL: Reinforcement Learning for Reasoning-Driven Multimodal Embeddings
by: Jiang, Haonan, et al.
Published: (2026)

Omni-o3: Deep Nested Omnimodal Deduction for Deliberative Audio-Visual Reasoning
by: Zhang, Zhicheng, et al.
Published: (2026)

VidEmo: Affective-Tree Reasoning for Emotion-Centric Video Foundation Models
by: Zhang, Zhicheng, et al.
Published: (2025)

CanonSwap: High-Fidelity and Consistent Video Face Swapping via Canonical Space Modulation
by: Luo, Xiangyang, et al.
Published: (2025)

Unified Optimization of Source Weights and Transfer Quantities in Multi-Source Transfer Learning: An Asymptotic Framework
by: Zhang, Qingyue, et al.
Published: (2026)

LIVE: Leveraging Image Manipulation Priors for Instruction-based Video Editing
by: Wang, Weicheng, et al.
Published: (2026)

Characterizing Motion Encoding in Video Diffusion Timesteps
by: Baherwani, Vatsal, et al.
Published: (2025)

HG-PIPE: Vision Transformer Acceleration with Hybrid-Grained Pipeline
by: Guo, Qingyu, et al.
Published: (2024)

LoRA-DA: Data-Aware Initialization for Low-Rank Adaptation via Asymptotic Analysis
by: Zhang, Qingyue, et al.
Published: (2025)

Native Visual Understanding: Resolving Resolution Dilemmas in Vision-Language Models
by: Niu, Junbo, et al.
Published: (2025)

SPF-Portrait: Towards Pure Text-to-Portrait Customization with Semantic Pollution-Free Fine-Tuning
by: Xian, Xiaole, et al.
Published: (2025)

HumanAesExpert: Advancing a Multi-Modality Foundation Model for Human Image Aesthetic Assessment
by: Liao, Zhichao, et al.
Published: (2025)

A High-Dimensional Statistical Method for Optimizing Transfer Quantities in Multi-Source Transfer Learning
by: Zhang, Qingyue, et al.
Published: (2025)

GRACE ‐ MORE : A Motion‐Resolved Golden‐Angle Radial CEST MRI Technique for Free‐Breathing Abdominal Imaging
by: Yitian Fan, et al.
Published: (2026)

Source-Free Domain Adaptation Guided by Vision and Vision-Language Pre-Training
by: Zhang, Wenyu, et al.
Published: (2024)

LanTu: Dynamics-Enhanced Deep Learning for Eddy-Resolving Ocean Forecasting
by: Zheng, Qingyu, et al.
Published: (2025)

Not All Timesteps Matter Equally: Selective Alignment Knowledge Distillation for Spiking Neural Networks
by: Sun, Kai, et al.
Published: (2026)

Image-Free Timestep Distillation via Continuous-Time Consistency with Trajectory-Sampled Pairs
by: Tang, Bao, et al.
Published: (2025)

Intermediate Outputs Are More Sensitive Than You Think
by: Huang, Tao, et al.
Published: (2024)

Strategic Change in Resolving the Efficiency‐Equity Dilemma: A Novel Approach to Portfolio Selection
by: Rania A. Azmi, et al.
Published: (2024)

Transferability Estimation for Semantic Segmentation Task
by: Tan, Yang, et al.
Published: (2021)

Practical Transferability Estimation for Image Classification Tasks
by: Tan, Yang, et al.
Published: (2021)

TMPQ-DM: Joint Timestep Reduction and Quantization Precision Selection for Efficient Diffusion Models
by: Sun, Haojun, et al.
Published: (2024)

Target-Driven Distillation: Consistency Distillation with Target Timestep Selection and Decoupled Guidance
by: Wang, Cunzheng, et al.
Published: (2024)

Improving Viewpoint-Independent Object-Centric Representations through Active Viewpoint Selection
by: Huang, Yinxuan, et al.
Published: (2024)

S-GRPO: Unified Post-Training for Large Vision-Language Models
by: Yan, Yuming, et al.
Published: (2026)

Multi‐modal mass spectrometry imaging of a single tissue section
by: Lingpeng Zhan, et al.
Published: (2024)

Entanglement is protected by acceleration-induced transparency in thermal field
by: Pan, Yongjie, et al.
Published: (2025)

Resolving the Acquisitions Dilemma: Into the Electronic Information Environment.
by: Smith, Eldred
Published: (1991)

ART for Diffusion Sampling: A Reinforcement Learning Approach to Timestep Schedule
by: Huang, Yilie, et al.
Published: (2026)

Leveraging High‐Dimensional Mapping for Effective JPEG Steganalysis
by: Meng Xu, et al.
Published: (2025)

Incentivizing High-Quality Human Annotations with Golden Questions
by: Liu, Shang, et al.
Published: (2025)

The Emergence of Cooperation in the well-mixed Prisoner's Dilemma: Memory Couples Individual and Group Strategies
by: Di, Changyan, et al.
Published: (2024)

MODA: MOdular Duplex Attention for Multimodal Perception, Cognition, and Emotion Understanding
by: Zhang, Zhicheng, et al.
Published: (2025)

TCAQ-DM: Timestep-Channel Adaptive Quantization for Diffusion Models
by: Huang, Haocheng, et al.
Published: (2024)