Cover Image

Drag-and-Drop LLMs: Zero-Shot Prompt-to-Weights

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liang, Zhiyuan, Tang, Dongwen, Zhou, Yuhao, Zhao, Xuanlei, Shi, Mingjia, Zhao, Wangbo, Li, Zekai, Wang, Peihao, Schürholt, Konstantin, Borth, Damian, Bronstein, Michael M., You, Yang, Wang, Zhangyang, Wang, Kai
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Recurrent Diffusion for Large-Scale Parameter Generation
by: Wang, Kai, et al.
Published: (2025)

The Impact of Model Zoo Size and Composition on Weight Space Learning
by: Falk, Damian, et al.
Published: (2025)

Towards Scalable and Versatile Weight Space Learning
by: Schürholt, Konstantin, et al.
Published: (2024)

REPA Works Until It Doesn't: Early-Stopped, Holistic Alignment Supercharges Diffusion Training
by: Wang, Ziqiao, et al.
Published: (2025)

Structure Is Not Enough: Leveraging Behavior for Neural Network Weight Reconstruction
by: Meynent, Léo, et al.
Published: (2025)

Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training
by: Shi, Mingjia, et al.
Published: (2024)

A Model Zoo of Vision Transformers
by: Falk, Damian, et al.
Published: (2025)

Learning Model Representations Using Publicly Available Model Hubs
by: Falk, Damian, et al.
Published: (2025)

Position: Weight Space Should Be a First-Class Generative AI Modality
by: Wang, Zhangyang, et al.
Published: (2026)

A Model Zoo on Phase Transitions in Neural Networks
by: Schürholt, Konstantin, et al.
Published: (2025)

Generalization Error Analysis for Sparse Mixture-of-Experts: A Preliminary Study
by: Zhao, Jinze, et al.
Published: (2024)

Hyper-Representations: Learning from Populations of Neural Networks
by: Schürholt, Konstantin
Published: (2024)

Dynamic Vision Mamba
by: Wu, Mengxuan, et al.
Published: (2025)

Why Neural Network Can Discover Symbolic Structures with Gradient-based Training: An Algebraic and Geometric Foundation for Neurosymbolic Reasoning
by: Wang, Peihao, et al.
Published: (2025)

Conditional LoRA Parameter Generation
by: Jin, Xiaolong, et al.
Published: (2024)

Real-Time Video Generation with Pyramid Attention Broadcast
by: Zhao, Xuanlei, et al.
Published: (2024)

Sample Weight Estimation Using Meta-Updates for Online Continual Learning
by: Hemati, Hamed, et al.
Published: (2024)

Lift3D: Zero-Shot Lifting of Any 2D Vision Model to 3D
by: T, Mukund Varma, et al.
Published: (2024)

Enhance-A-Video: Better Generated Video for Free
by: Luo, Yang, et al.
Published: (2025)

A Stitch in Time Saves Nine: Small VLM is a Precise Guidance for Accelerating Large VLMs
by: Zhao, Wangbo, et al.
Published: (2024)

Meta ControlNet: Enhancing Task Adaptation via Meta Learning
by: Yang, Junjie, et al.
Published: (2023)

LSTPrompt: Large Language Models as Zero-Shot Time Series Forecasters by Long-Short-Term Prompting
by: Liu, Haoxin, et al.
Published: (2024)

Know Your Attention Maps: Class-specific Token Masking for Weakly Supervised Semantic Segmentation
by: Hanna, Joelle, et al.
Published: (2025)

ResearchGPT: Benchmarking and Training LLMs for End-to-End Computer Science Research Workflows
by: Wang, Penghao, et al.
Published: (2025)

RAPID^3: Tri-Level Reinforced Acceleration Policies for Diffusion Transformer
by: Zhao, Wangbo, et al.
Published: (2025)

StarTrail: Concentric Ring Sequence Parallelism for Efficient Near-Infinite-Context Transformer Model Training
by: Liu, Ziming, et al.
Published: (2024)

StableDrag: Stable Dragging for Point-based Image Editing
by: Cui, Yutao, et al.
Published: (2024)

Boosting Quantitive and Spatial Awareness for Zero-Shot Object Counting
by: Zhang, Da, et al.
Published: (2026)

Self-Prompting Large Language Models for Zero-Shot Open-Domain QA
by: Li, Junlong, et al.
Published: (2022)

LoCoCo: Dropping In Convolutions for Long Context Compression
by: Cai, Ruisi, et al.
Published: (2024)

DragVideo: Interactive Drag-style Video Editing
by: Deng, Yufan, et al.
Published: (2023)

Magic Insert: Style-Aware Drag-and-Drop
by: Ruiz, Nataniel, et al.
Published: (2024)

Taxonomy-Guided Zero-Shot Recommendations with LLMs
by: Liang, Yueqing, et al.
Published: (2024)

Polynomial Width is Sufficient for Set Representation with High-dimensional Features
by: Wang, Peihao, et al.
Published: (2023)

Better Zero-Shot Reasoning with Role-Play Prompting
by: Kong, Aobo, et al.
Published: (2023)

Evolving, Not Training: Zero-Shot Reasoning Segmentation via Evolutionary Prompting
by: Ye, Kai, et al.
Published: (2025)

Privacy Preserving Diffusion Models for Mixed-Type Tabular Data Generation
by: Sattarov, Timur, et al.
Published: (2025)

FedTabDiff: Federated Learning of Diffusion Probabilistic Models for Synthetic Mixed-Type Tabular Data Generation
by: Sattarov, Timur, et al.
Published: (2024)

Federated Diffusion Modeling with Differential Privacy for Tabular Data Synthesis
by: Sattarov, Timur, et al.
Published: (2024)

MAPEX: Modality-Aware Pruning of Experts for Remote Sensing Foundation Models
by: Hanna, Joelle, et al.
Published: (2025)