Cover Image

Continual Learning in Vision-Language Models via Aligned Model Merging

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Sokar, Ghada, Dziugaite, Gintare Karolina, Arnab, Anurag, Iscen, Ahmet, Castro, Pablo Samuel, Schmid, Cordelia
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Retrieval-Enhanced Contrastive Vision-Text Models
by: Iscen, Ahmet, et al.
Published: (2023)

Web-Scale Visual Entity Recognition: An LLM-Driven Data Approach
by: Caron, Mathilde, et al.
Published: (2024)

A Generative Approach for Wikipedia-Scale Visual Entity Recognition
by: Caron, Mathilde, et al.
Published: (2024)

OVFact: Measuring and Improving Open-Vocabulary Factuality for Long Caption Models
by: Wysoczańska, Monika, et al.
Published: (2025)

Memory-Modular Classification: Learning to Generalize with Memory Replacement
by: Kang, Dahyun, et al.
Published: (2025)

Dense Video Object Captioning from Disjoint Supervision
by: Zhou, Xingyi, et al.
Published: (2023)

VOLD: Reasoning Transfer from LLMs to Vision-Language Models via On-Policy Distillation
by: Bousselham, Walid, et al.
Published: (2025)

Identifying Spurious Biases Early in Training through the Lens of Simplicity Bias
by: Yang, Yu, et al.
Published: (2023)

CAViAR: Critic-Augmented Video Agentic Reasoning
by: Menon, Sachit, et al.
Published: (2025)

Time-, Memory- and Parameter-Efficient Visual Adaptation
by: Mercea, Otniel-Bogdan, et al.
Published: (2024)

PointACT: Vision-Language-Action Models with Multi-Scale Point-Action Interaction
by: Chen, Shizhe, et al.
Published: (2026)

What Are You Doing? A Closer Look at Controllable Human Video Generation
by: Bugliarello, Emanuele, et al.
Published: (2025)

Towards Generalizable Vision-Language Robotic Manipulation: A Benchmark and LLM-guided 3D Policy
by: Garcia, Ricardo, et al.
Published: (2024)

Learning Correlation Structures for Vision Transformers
by: Kim, Manjin, et al.
Published: (2024)

Audiovisual Masked Autoencoders
by: Georgescu, Mariana-Iuliana, et al.
Published: (2022)

Scaling Cross-Environment Failure Reasoning Data for Vision-Language Robotic Manipulation
by: Pacaud, Paul, et al.
Published: (2025)

VoCap: Video Object Captioning and Segmentation from Any Prompt
by: Uijlings, Jasper, et al.
Published: (2025)

Streaming Dense Video Captioning
by: Zhou, Xingyi, et al.
Published: (2024)

Learning text-to-video retrieval from image captioning
by: Ventura, Lucas, et al.
Published: (2024)

Gondola: Grounded Vision Language Planning for Generalizable Robotic Manipulation
by: Chen, Shizhe, et al.
Published: (2025)

MergeSlide: Continual Model Merging and Task-to-Class Prompt-Aligned Inference for Lifelong Learning on Whole Slide Images
by: Bui, Doanh C., et al.
Published: (2025)

BrickNet: Graph-Backed Generative Brick Assembly
by: Kulits, Peter, et al.
Published: (2026)

From Dormant to Deleted: Tamper-Resistant Unlearning Through Weight-Space Regularization
by: Siddiqui, Shoaib Ahmed, et al.
Published: (2025)

SceneCraft: An LLM Agent for Synthesizing 3D Scene as Blender Code
by: Hu, Ziniu, et al.
Published: (2024)

Convolutional Prompting meets Language Models for Continual Learning
by: Roy, Anurag, et al.
Published: (2024)

Grounded Video Caption Generation
by: Kazakos, Evangelos, et al.
Published: (2024)

ComposeAnything: Composite Object Priors for Text-to-Image Generation
by: Khan, Zeeshan, et al.
Published: (2025)

Large-scale Pre-training for Grounded Video Caption Generation
by: Kazakos, Evangelos, et al.
Published: (2025)

Temporal Chain of Thought: Long-Video Understanding by Thinking in Frames
by: Arnab, Anurag, et al.
Published: (2025)

AMES: Asymmetric and Memory-Efficient Similarity Estimation for Instance-level Retrieval
by: Suma, Pavel, et al.
Published: (2024)

ViViDex: Learning Vision-based Dexterous Manipulation from Human Videos
by: Chen, Zerui, et al.
Published: (2024)

Interpretable Zero-Shot Learning with Locally-Aligned Vision-Language Model
by: Chen, Shiming, et al.
Published: (2025)

MINERVA: Evaluating Complex Video Reasoning
by: Nagrani, Arsha, et al.
Published: (2025)

Dense Optical Tracking: Connecting the Dots
by: Moing, Guillaume Le, et al.
Published: (2023)

Enhanced Continual Learning of Vision-Language Models with Model Fusion
by: Gao, Haoyuan, et al.
Published: (2025)

Enhancing Continual Learning of Vision-Language Models via Dynamic Prefix Weighting
by: Jang, Hyeonseo, et al.
Published: (2026)

Boosting Continual Learning of Vision-Language Models via Mixture-of-Experts Adapters
by: Yu, Jiazuo, et al.
Published: (2024)

Towards Efficient Vision State Space Models via Token Merging
by: Park, Jinyoung, et al.
Published: (2025)

SUGAR: Pre-training 3D Visual Representations for Robotics
by: Chen, Shizhe, et al.
Published: (2024)

Chapter-Llama: Efficient Chaptering in Hour-Long Videos with LLMs
by: Ventura, Lucas, et al.
Published: (2025)