Cover Image

Task Alignment: A simple and effective proxy for model merging in computer vision

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	de Jorge, Pau, de Souza, César Roberto, Michele, Björn, Sarıyıldız, Mert Bülent, Weinzaepfel, Philippe, Perronnin, Florent, Larlus, Diane, Kalantidis, Yannis
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

UNIC: Universal Classification Models via Multi-teacher Distillation
by: Sariyildiz, Mert Bulent, et al.
Published: (2024)

DUNE: Distilling a Universal Encoder from Heterogeneous 2D and 3D Teachers
by: Sariyildiz, Mert Bulent, et al.
Published: (2025)

Weatherproofing Retrieval for Localization with Generative AI and Geometric Consistency
by: Kalantidis, Yannis, et al.
Published: (2024)

Kinaema: a recurrent sequence model for memory and pose in motion
by: Sariyildiz, Mert Bulent, et al.
Published: (2025)

What could go wrong? Discovering and describing failure modes in computer vision
by: Csurka, Gabriela, et al.
Published: (2024)

Label Propagation for Zero-shot Classification with Vision-Language Models
by: Stojnić, Vladan, et al.
Published: (2024)

On Good Practices for Task-Specific Distillation of Large Pretrained Visual Models
by: Marrie, Juliette, et al.
Published: (2024)

Innominate Artery Cannulation for Proximal Aortic Surgery
by: Bülent Mert
Published: (2023)

LPOSS: Label Propagation Over Patches and Pixels for Open-vocabulary Semantic Segmentation
by: Stojnić, Vladan, et al.
Published: (2025)

ELViS: Efficient Visual Similarity from Local Descriptors that Generalizes Across Domains
by: Suma, Pavel, et al.
Published: (2026)

PANDAS: Prototype-based Novel Class Discovery and Detection
by: Hayes, Tyler L., et al.
Published: (2024)

Layered Motion Fusion: Lifting Motion Segmentation to 3D in Egocentric Videos
by: Tschernezki, Vadim, et al.
Published: (2025)

AMC26: High-performance DOb for robust position control
by: Sariyildiz, Emre
Published: (2026)

AMC'24 "Analysis and Synthesis of the Disturbance Observer-based Robust Force Control Systems in State Space"
by: Emre, Sariyildiz
Published: (2024)

AMC26: VSSEA robust position control
by: Sariyildiz, Emre
Published: (2026)

IEEEICM25: "Stability of Digital Robust Motion Control Systems with Disturbance Observer"
by: Sariyildiz, Emre
Published: (2025)

IEEEICM25: "A High-Performance Disturbance Observer"
by: Sariyildiz, Emre
Published: (2025)

IEEE_TIE25: Analysis and Synthesis of DOb-based Robust Motion Controllers
by: Sariyildiz, Emre
Published: (2025)

AMC'24 "A Novel Stiffness Modulation Mechanism for Energy Efficient Variable Stiffness Actuators"
by: Emre, Sariyildiz
Published: (2024)

What does really matter in image goal navigation?
by: Monaci, Gianluca, et al.
Published: (2025)

LUDVIG: Learning-Free Uplifting of 2D Visual Features to Gaussian Splatting Scenes
by: Marrie, Juliette, et al.
Published: (2024)

Geo4D: Leveraging Video Generators for Geometric 4D Scene Reconstruction
by: Jiang, Zeren, et al.
Published: (2025)

Mesh4D: 4D Mesh Reconstruction and Tracking from Monocular Video
by: Jiang, Zeren, et al.
Published: (2026)

Win-Win: Training High-Resolution Vision Transformers from Two Windows
by: Leroy, Vincent, et al.
Published: (2023)

A simple geometric proof for the characterisation of e-merging functions
by: Clerico, Eugenio
Published: (2025)

Factors Affecting the Impact of LBBBP on Ventricular Electrical Activation
by: Erdi Babayigit, et al.
Published: (2025)

PoseFix: Correcting 3D Human Poses with Natural Language
by: Delmas, Ginger, et al.
Published: (2023)

PoseEmbroider: Towards a 3D, Visual, Semantic-aware Human Pose Representation
by: Delmas, Ginger, et al.
Published: (2024)

Algorithmic randomness and the weak merging of computable probability measures
by: Huttegger, Simon M., et al.
Published: (2025)

Multi-vision-based Picking Point Localisation of Target Fruit for Harvesting Robots
by: Beldek, C., et al.
Published: (2025)

On merge-models
by: Buffière, Hector, et al.
Published: (2026)

Pow3R: Empowering Unconstrained 3D Reconstruction with Camera and Scene Priors
by: Jang, Wonbong, et al.
Published: (2025)

Forecasting the population properties of merging black holes
by: De Renzis, Viola, et al.
Published: (2024)

HOSt3R: Keypoint-free Hand-Object 3D Reconstruction from RGB images
by: Swamy, Anilkumar, et al.
Published: (2025)

PoseScript: Linking 3D Human Poses and Natural Language
by: Delmas, Ginger, et al.
Published: (2022)

Carbonate dissolution proxies of ODP Site 154-927
by: Frenz, Michael, et al.
Published: (2006)

Carbonate dissolution proxies of ODP Hole 154-929A
by: Frenz, Michael, et al.
Published: (2006)

MASt3R-SfM: a Fully-Integrated Solution for Unconstrained Structure-from-Motion
by: Duisterhof, Bardienus, et al.
Published: (2024)

HAMSt3R: Human-Aware Multi-view Stereo 3D Reconstruction
by: Rojas, Sara, et al.
Published: (2025)

EPIC Fields: Marrying 3D Geometry and Video Understanding
by: Tschernezki, Vadim, et al.
Published: (2023)