Image de couverture de livre

Task Matrices: Linear Maps for Cross-Model Finetuning Transfer

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Brien, Darrin O', Gajulapalli, Dhikshith, Xia, Eric
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Computation and Language Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

ETHER: Efficient Finetuning of Large-Scale Models with Hyperplane Reflections
par: Bini, Massimo, et autres
Publié: (2024)

Vision-Language Models Create Cross-Modal Task Representations
par: Luo, Grace, et autres
Publié: (2024)

Orthogonal Finetuning Made Scalable
par: Qiu, Zeju, et autres
Publié: (2025)

Exposing and Addressing Cross-Task Inconsistency in Unified Vision-Language Models
par: Maharana, Adyasha, et autres
Publié: (2023)

Linear Alignment of Vision-language Models for Image Captioning
par: Paischer, Fabian, et autres
Publié: (2023)

Parameter-Efficient Orthogonal Finetuning via Butterfly Factorization
par: Liu, Weiyang, et autres
Publié: (2023)

CROME: Cross-Modal Adapters for Efficient Multimodal LLM
par: Ebrahimi, Sayna, et autres
Publié: (2024)

BYOM: Building Your Own Multi-Task Model For Free
par: Jiang, Weisen, et autres
Publié: (2023)

Multi-Task Model Merging via Adaptive Weight Disentanglement
par: Xiong, Feng, et autres
Publié: (2024)

MoLEx: Mixture of Layer Experts for Finetuning with Sparse Upcycling
par: Teo, Rachel S. Y., et autres
Publié: (2025)

RadZero: Similarity-Based Cross-Attention for Explainable Vision-Language Alignment in Chest X-ray with Zero-Shot Multi-Task Capability
par: Park, Jonggwon, et autres
Publié: (2025)

Localize-and-Stitch: Efficient Model Merging via Sparse Task Arithmetic
par: He, Yifei, et autres
Publié: (2024)

VLSM-Adapter: Finetuning Vision-Language Segmentation Efficiently with Lightweight Blocks
par: Dhakal, Manish, et autres
Publié: (2024)

LLM-CXR: Instruction-Finetuned LLM for CXR Image Understanding and Generation
par: Lee, Suhyeon, et autres
Publié: (2023)

MoTe: Learning Motion-Text Diffusion Model for Multiple Generation Tasks
par: Wu, Yiming, et autres
Publié: (2024)

X-VILA: Cross-Modality Alignment for Large Language Model
par: Ye, Hanrong, et autres
Publié: (2024)

How LoRA Remembers? A Parametric Memory Law for LLM Finetuning
par: Xu, Ziwen, et autres
Publié: (2026)

Efficient Stitchable Task Adaptation
par: He, Haoyu, et autres
Publié: (2023)

How Vision-Language Tasks Benefit from Large Pre-trained Models: A Survey
par: Qi, Yayun, et autres
Publié: (2024)

Mind the Gap Between Prototypes and Images in Cross-domain Finetuning
par: Tian, Hongduan, et autres
Publié: (2024)

Revisiting Mixout: An Overlooked Path to Robust Finetuning
par: Aminbeidokhti, Masih, et autres
Publié: (2025)

Connect, Collapse, Corrupt: Learning Cross-Modal Tasks with Uni-Modal Data
par: Zhang, Yuhui, et autres
Publié: (2024)

Transformer-VQ: Linear-Time Transformers via Vector Quantization
par: Lingle, Lucas D.
Publié: (2023)

Transferability-Guided Cross-Domain Cross-Task Transfer Learning
par: Tan, Yang, et autres
Publié: (2022)

Neural Style Transfer for Synthesising a Dataset of Ancient Egyptian Hieroglyphs
par: Creed, Lewis Matheson
Publié: (2025)

MM-GEN: Enhancing Task Performance Through Targeted Multimodal Data Curation
par: Joshi, Siddharth, et autres
Publié: (2025)

Task-Specific Directions: Definition, Exploration, and Utilization in Parameter Efficient Fine-Tuning
par: Si, Chongjie, et autres
Publié: (2024)

Language-Pretraining-Induced Bias: A Strong Foundation for General Vision Tasks
par: Luo, Yaxin, et autres
Publié: (2026)

Monkey Jump : MoE-Style PEFT for Efficient Multi-Task Learning
par: Prottasha, Nusrat Jahan, et autres
Publié: (2026)

VisualWebArena: Evaluating Multimodal Agents on Realistic Visual Web Tasks
par: Koh, Jing Yu, et autres
Publié: (2024)

GenSim: Generating Robotic Simulation Tasks via Large Language Models
par: Wang, Lirui, et autres
Publié: (2023)

MapIQ: Evaluating Multimodal Large Language Models for Map Question Answering
par: Srivastava, Varun, et autres
Publié: (2025)

VLM Judges Can Rank but Cannot Score: Task-Dependent Uncertainty in Multimodal Evaluation
par: Kumar, Divake, et autres
Publié: (2026)

Crossing Language Borders: A Pipeline for Indonesian Manhwa Translation
par: Narasimhan, Nithyasri, et autres
Publié: (2025)

Cross-modal Causal Relation Alignment for Video Question Grounding
par: Chen, Weixing, et autres
Publié: (2025)

Text-to-Image Cross-Modal Generation: A Systematic Review
par: Żelaszczyk, Maciej, et autres
Publié: (2024)

Understanding Space Is Rocket Science -- Only Top Reasoning Models Can Solve Spatial Understanding Tasks
par: Hoehing, Nils, et autres
Publié: (2025)

The Double Dilemma in Multi-Task Radiology Report Generation: A Gradient Dynamics Analysis and Solution
par: Zhang, Erjian, et autres
Publié: (2026)

MMed-RAG: Versatile Multimodal RAG System for Medical Vision Language Models
par: Xia, Peng, et autres
Publié: (2024)

Person-Centric Annotations of LAION-400M: Auditing Bias and Its Transfer to Models
par: Girrbach, Leander, et autres
Publié: (2025)