Cover Image

Knowledge Composition using Task Vectors with Learned Anisotropic Scaling

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Frederic Z., Albert, Paul, Rodriguez-Opazo, Cristian, Hengel, Anton van den, Abbasnejad, Ehsan
Format:	Preprint
Published:	2024
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

RandLoRA: Full-rank parameter-efficient fine-tuning of large models
by: Albert, Paul, et al.
Published: (2025)

Synergy and Diversity in CLIP: Enhancing Performance Through Adaptive Backbone Ensembling
by: Rodriguez-Opazo, Cristian, et al.
Published: (2024)

Towards Higher Effective Rank in Parameter-efficient Fine-tuning using Khatri--Rao Product
by: Albert, Paul, et al.
Published: (2025)

Premonition: Using Generative Models to Preempt Future Data Changes in Continual Learning
by: McDonnell, Mark D., et al.
Published: (2024)

RanPAC: Random Projections and Pre-trained Models for Continual Learning
by: McDonnell, Mark D., et al.
Published: (2023)

Frame-wise Conditioning Adaptation for Fine-Tuning Diffusion Models in Text-to-Video Prediction
by: Liu, Zheyuan, et al.
Published: (2025)

Points-to-3D: Structure-Aware 3D Generation with Point Cloud Priors
by: Xia, Jiatong, et al.
Published: (2026)

Learning to Reason and Navigate: Parameter Efficient Action Planning with Large Language Models
by: Mohammadi, Bahram, et al.
Published: (2025)

Scaling up Multi-domain Semantic Segmentation with Sentence Embeddings
by: Yin, Wei, et al.
Published: (2022)

Neural Redshift: Random Networks are not Random Functions
by: Teney, Damien, et al.
Published: (2024)

Can You Learn to See Without Images? Procedural Warm-Up for Vision Transformers
by: Shinnick, Zachary, et al.
Published: (2025)

Mysteries of the Deep: Role of Intermediate Representations in Out of Distribution Detection
by: De la Jara, I. M., et al.
Published: (2025)

Let Your Video Listen to Your Music!
by: Zhang, Xinyu, et al.
Published: (2025)

Continual Learning on CLIP via Incremental Prompt Tuning with Intrinsic Textual Anchors
by: Lu, Haodong, et al.
Published: (2025)

Visual Self-supervised Learning Scheme for Dense Prediction Tasks on X-ray Images
by: Halat, Shervin, et al.
Published: (2023)

Hierarchical Process Reward Models are Symbolic Vision Learners
by: Zhang, Shan, et al.
Published: (2025)

ViewFusion: Towards Multi-View Consistency via Interpolated Denoising
by: Yang, Xianghui, et al.
Published: (2024)

Learning to Project for Cross-Task Knowledge Distillation
by: Auty, Dylan, et al.
Published: (2024)

Do We Always Need the Simplicity Bias? Looking for Optimal Inductive Biases in the Wild
by: Teney, Damien, et al.
Published: (2025)

Source-Free Unsupervised Domain Adaptation with Hypothesis Consolidation of Prediction Rationale
by: Shu, Yangyang, et al.
Published: (2024)

Modality-Aware and Anatomical Vector-Quantized Autoencoding for Multimodal Brain MRI
by: Li, Mingjie, et al.
Published: (2026)

On the Value of Cross-Modal Misalignment in Multimodal Representation Learning
by: Cai, Yichao, et al.
Published: (2025)

CLOFAI: A Dataset of Real And Fake Image Classification Tasks for Continual Learning
by: Doherty, William, et al.
Published: (2025)

ProgRoCC: A Progressive Approach to Rough Crowd Counting
by: Jiang, Shengqin, et al.
Published: (2025)

The Devil is in the Distributions: Explicit Modeling of Scene Content is Key in Zero-Shot Video Captioning
by: Tian, Mingkai, et al.
Published: (2025)

Energy-Efficient Uncertainty-Aware Biomass Composition Prediction at the Edge
by: Zawish, Muhammad, et al.
Published: (2024)

Math Blind: Failures in Diagram Understanding Undermine Reasoning in MLLMs
by: Sun, Yanpeng, et al.
Published: (2025)

Mosaic: Compositional Multi-Concept Erasure via Vector Field Blending
by: Ko, Junseok, et al.
Published: (2026)

Seeing the Trees for the Forest: Rethinking Weakly-Supervised Medical Visual Grounding
by: Huy, Ta Duc, et al.
Published: (2025)

HAECcity: Open-Vocabulary Scene Understanding of City-Scale Point Clouds with Superpoint Graph Clustering
by: Rusnak, Alexander, et al.
Published: (2025)

An Innovative Framework for Breast Cancer Detection Using Pyramid Adaptive Atrous Convolution, Transformer Integration, and Multi-Scale Feature Fusion
by: Pour, Ehsan Sadeghi, et al.
Published: (2026)

Rendering-Aware Reinforcement Learning for Vector Graphics Generation
by: Rodriguez, Juan A., et al.
Published: (2025)

Dual Strategies for Test-Time Adaptation
by: Phuong, Nam Nguyen, et al.
Published: (2026)

Interactive Medical Image Analysis with Concept-based Similarity Reasoning
by: Huy, Ta Duc, et al.
Published: (2025)

No Captions, No Problem: Captionless 3D-CLIP Alignment with Hard Negatives via CLIP Knowledge and LLMs
by: Sbrolli, Cristian, et al.
Published: (2024)

Prosody-Enhanced Acoustic Pre-training and Acoustic-Disentangled Prosody Adapting for Movie Dubbing
by: Zhang, Zhedong, et al.
Published: (2025)

Robotic Grasping of Harvested Tomato Trusses Using Vision and Online Learning
by: Bent, Luuk van den, et al.
Published: (2023)

Scaling Properties of Diffusion Models for Perceptual Tasks
by: Ravishankar, Rahul, et al.
Published: (2024)

Caption First, VQA Second: Knowledge Density, Not Task Format, Drives Multimodal Scaling
by: Zou, Hongjian, et al.
Published: (2026)

Auto-Comp: An Automated Pipeline for Scalable Compositional Probing of Contrastive Vision-Language Models
by: Sbrolli, Cristian, et al.
Published: (2026)