Cover Image

Alchemist: Unlocking Efficiency in Text-to-Image Model Training via Meta-Gradient Data Selection

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ding, Kaixin, Zhou, Yang, Chen, Xi, Yang, Miao, Ou, Jiarong, Chen, Rui, Tao, Xin, Zhao, Hengshuang
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

Alchemist: Turning Public Text-to-Image Data into Generative Gold
by: Startsev, Valerii, et al.
Published: (2025)

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

AlphaGRPO: Unlocking Self-Reflective Multimodal Generation in UMMs via Decompositional Verifiable Reward
by: Huang, Runhui, et al.
Published: (2026)

PhysMaster: Mastering Physical Representation for Video Generation via Reinforcement Learning
by: Ji, Sihui, et al.
Published: (2025)

FocalClick-XL: Towards Unified and High-quality Interactive Segmentation
by: Chen, Xi, et al.
Published: (2025)

BadVideo: Stealthy Backdoor Attack against Text-to-Video Generation
by: Wang, Ruotong, et al.
Published: (2025)

MemFlow: Flowing Adaptive Memory for Consistent and Efficient Long Video Narratives
by: Ji, Sihui, et al.
Published: (2025)

An Alchemist in Chains
by: Stjernfelt, Frederik
Published: (2024)

Easier Painting Than Thinking: Can Text-to-Image Models Set the Stage, but Not Direct the Play?
by: Li, Ouxiang, et al.
Published: (2025)

Unleashing the Power of Emojis in Texts via Self-supervised Graph Pre-Training
by: Zhang, Zhou, et al.
Published: (2024)

The Occult: Diabolica to Alchemists
by: Delaney, Oliver J.
Published: (1971)

From Noisy Traces to Stable Gradients: Bias-Variance Optimized Preference Optimization for Aligning Large Reasoning Models
by: Zhu, Mingkang, et al.
Published: (2025)

Lens: Rethinking Training Efficiency for Foundational Text-to-Image Models
by: Chen, Dong, et al.
Published: (2026)

Influential Language Data Selection via Gradient Trajectory Pursuit
by: Deng, Zhiwei, et al.
Published: (2024)

DreamMask: Boosting Open-vocabulary Panoptic Segmentation with Synthetic Data
by: Tu, Yuanpeng, et al.
Published: (2025)

Wall Street's New Alchemist

Less is Enough: Training-Free Video Diffusion Acceleration via Runtime-Adaptive Caching
by: Zhou, Xin, et al.
Published: (2025)

DiffCamera: Arbitrary Refocusing on Images
by: Wang, Yiyang, et al.
Published: (2025)

AlchemistCoder: Harmonizing and Eliciting Code Capability by Hindsight Tuning on Multi-source Data
by: Song, Zifan, et al.
Published: (2024)

A Lightweight Clustering Framework for Unsupervised Semantic Segmentation
by: Cheung, Yau Shing Jonathan, et al.
Published: (2023)

AnyDoor: Zero-shot Object-level Image Customization
by: Chen, Xi, et al.
Published: (2023)

FashionComposer: Compositional Fashion Image Generation
by: Ji, Sihui, et al.
Published: (2024)

Text2Earth: Unlocking Text-driven Remote Sensing Image Generation with a Global-Scale Dataset and a Foundation Model
by: Liu, Chenyang, et al.
Published: (2025)

Imbalance in Balance: Online Concept Balancing in Generation Models
by: Shi, Yukai, et al.
Published: (2025)

Seg-VAR: Image Segmentation with Visual Autoregressive Modeling
by: Zheng, Rongkun, et al.
Published: (2025)

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning
by: Chen, Xinrui, et al.
Published: (2026)

FASTER: Rethinking Real-Time Flow VLAs
by: Lu, Yuxiang, et al.
Published: (2026)

Unlocking the Hidden Treasures: Enhancing Recommendations with Unlabeled Data
by: Zhao, Yuhan, et al.
Published: (2024)

UniMatch V2: Pushing the Limit of Semi-Supervised Semantic Segmentation
by: Yang, Lihe, et al.
Published: (2024)

Improving Memory Efficiency for Training KANs via Meta Learning
by: Zhao, Zhangchi, et al.
Published: (2025)

DPC: Training-Free Text-to-SQL Candidate Selection via Dual-Paradigm Consistency
by: Li, Boyan, et al.
Published: (2026)

TMT-VIS: Taxonomy-aware Multi-dataset Joint Training for Video Instance Segmentation
by: Zheng, Rongkun, et al.
Published: (2023)

Can Modifying Data Address Graph Domain Adaptation?
by: Huang, Renhong, et al.
Published: (2024)

Modular Customization of Diffusion Models via Blockwise-Parameterized Low-Rank Adaptation
by: Zhu, Mingkang, et al.
Published: (2025)

BOOD: Boundary-based Out-Of-Distribution Data Generation
by: Liao, Qilin, et al.
Published: (2025)

On the Difficulty of Learning a Meta-network for Training Data Selection
by: Du, Zilin, et al.
Published: (2026)

Zero-shot Image Editing with Reference Imitation
by: Chen, Xi, et al.
Published: (2024)

Node Flexibility Unlocks Structural Adaptability and Guest Versatility of Anionocages
by: Yu Tao, et al.
Published: (2025)

Node Flexibility Unlocks Structural Adaptability and Guest Versatility of Anionocages
by: Yu Tao, et al.
Published: (2025)

Towards Better Text-to-Image Generation Alignment via Attention Modulation
by: Wu, Yihang, et al.
Published: (2024)