Cover Image

Deterministic Continuous Replacement: Fast and Stable Module Replacement in Pretrained Transformers

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Bradbury, Rowan, Ashok, Aniket Srinivasan, Kasanagottu, Sai Ram, Jhingran, Gunmay, Meng, Shuai
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

Point-RTD: Replaced Token Denoising for Pretraining Transformer Models on Point Clouds
by: Stone, Gunner, et al.
Published: (2025)

Can Cross-Layer Transcoders Replace Vision Transformer Activations? An Interpretable Perspective on Vision
by: Chatzoudis, Gerasimos, et al.
Published: (2026)

PoM: A Linear-Time Replacement for Attention with the Polynomial Mixer
by: Picard, David, et al.
Published: (2026)

Replace in Translation: Boost Concept Alignment in Counterfactual Text-to-Image
by: Li, Sifan, et al.
Published: (2025)

An Inpainting-Infused Pipeline for Attire and Background Replacement
by: Perche-Mahlow, Felipe Rodrigues, et al.
Published: (2024)

Sparkle: Realizing Lively Instruction-Guided Video Background Replacement via Decoupled Guidance
by: Zeng, Ziyun, et al.
Published: (2026)

FAR: Function-preserving Attention Replacement for IMC-friendly Inference
by: Ren, Yuxin, et al.
Published: (2025)

Can Vision-Language Models Replace Human Annotators: A Case Study with CelebA Dataset
by: Lu, Haoming, et al.
Published: (2024)

FastTab: A Fast Table Recognizer with a Tiny Recursive Module and 1D Transformers
by: Hamdi, Laziz, et al.
Published: (2026)

RASA: Replace Anyone, Say Anything -- A Training-Free Framework for Audio-Driven and Universal Portrait Video Editing
by: Pan, Tianrui, et al.
Published: (2025)

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing
by: Kapse, Saarthak, et al.
Published: (2025)

Composite Classifier-Free Guidance for Multi-Modal Conditioning in Wind Dynamics Super-Resolution
by: Schnell, Jacob, et al.
Published: (2025)

AGIC: Attention-Guided Image Captioning to Improve Caption Relevance
by: Teja, L. D. M. S. Sai, et al.
Published: (2025)

ReplaceAnything3D:Text-Guided 3D Scene Editing with Compositional Neural Radiance Fields
by: Bartrum, Edward, et al.
Published: (2024)

Learning Transferable Features for Implicit Neural Representations
by: Vyas, Kushal, et al.
Published: (2024)

FactoFormer: Factorized Hyperspectral Transformers with Self-Supervised Pretraining
by: Mohamed, Shaheer, et al.
Published: (2023)

DifuzCam: Replacing Camera Lens with a Mask and a Diffusion Model
by: Yosef, Erez, et al.
Published: (2024)

Replace-then-Perturb: Targeted Adversarial Attacks With Visual Reasoning for Vision-Language Models
by: Jang, Jonggyu, et al.
Published: (2024)

Few-Shot Deployment of Pretrained MRI Transformers in Brain Imaging Tasks
by: Li, Mengyu, et al.
Published: (2025)

Fast OTSU Thresholding Using Bisection Method
by: Kodathala, Sai Varun
Published: (2025)

HQ-DiT: Efficient Diffusion Transformer with FP4 Hybrid Quantization
by: Liu, Wenxuan, et al.
Published: (2024)

FastTrackTr:Towards Fast Multi-Object Tracking with Transformers
by: Liao, Pan, et al.
Published: (2024)

MAP: Unleashing Hybrid Mamba-Transformer Vision Backbone's Potential with Masked Autoregressive Pretraining
by: Liu, Yunze, et al.
Published: (2024)

DDT: Decoupled Diffusion Transformer
by: Wang, Shuai, et al.
Published: (2025)

CornViT: A Multi-Stage Convolutional Vision Transformer Framework for Hierarchical Corn Kernel Analysis
by: Erukude, Sai Teja, et al.
Published: (2025)

Latent Modulated Function for Computational Optimal Continuous Image Representation
by: He, Zongyao, et al.
Published: (2024)

Back to the Barn with LLAMAs: Evolving Pretrained LLM Backbones in Finetuning Vision Language Models
by: Horawalavithana, Sameera, et al.
Published: (2026)

Attention Retention for Continual Learning with Vision Transformers
by: Lu, Yue, et al.
Published: (2026)

Patch Rebirth: Toward Fast and Transferable Model Inversion of Vision Transformers
by: Heo, Seongsoo, et al.
Published: (2025)

ANYPORTAL: Zero-Shot Consistent Video Background Replacement
by: Gao, Wenshuo, et al.
Published: (2025)

Vision-and-Language Navigation Generative Pretrained Transformer
by: Hanlin, Wen
Published: (2024)

Satellite to Street : Disaster Impact Estimator
by: Sai, Sreesritha, et al.
Published: (2025)

Efficient Zero-Shot AI-Generated Image Detection
by: Sonoda, Ryosuke, et al.
Published: (2026)

Channel Vision Transformers: An Image Is Worth 1 x 16 x 16 Words
by: Bao, Yujia, et al.
Published: (2023)

Time Series Representations for Classification Lie Hidden in Pretrained Vision Transformers
by: Roschmann, Simon, et al.
Published: (2025)

Mind's Eye: A Benchmark of Visual Abstraction, Transformation and Composition for Multimodal LLMs
by: Sinha, Rohit, et al.
Published: (2026)

AdaVid: Adaptive Video-Language Pretraining
by: Patel, Chaitanya, et al.
Published: (2025)

Separators in Enhancing Autoregressive Pretraining for Vision Mamba
by: Liu, Hanpeng, et al.
Published: (2026)

Spatial Transcriptomics as Images for Large-Scale Pretraining
by: Zhu, Yishun, et al.
Published: (2026)

Beyond Random Augmentations: Pretraining with Hard Views
by: Ferreira, Fabio, et al.
Published: (2023)