Cover Image

Proactive Gradient Conflict Mitigation in Multi-Task Learning: A Sparse Training Perspective

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Zhi, Shen, Jiayi, Cao, Congfeng, Dai, Gaole, Zhou, Shiji, Zhang, Qizhe, Zhang, Shanghang, Shutova, Ekaterina
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

Gradient-based Parameter Selection for Efficient Fine-Tuning
by: Zhang, Zhi, et al.
Published: (2023)

NeuroAda: Activating Each Neuron's Potential for Parameter-Efficient Fine-Tuning
by: Zhang, Zhi, et al.
Published: (2025)

MoSA: Mixture of Sparse Adapters for Visual Efficient Tuning
by: Zhang, Qizhe, et al.
Published: (2023)

SpikeGen: Decoupled "Rods and Cones" Visual Representation Processing with Latent Generative Framework
by: Dai, Gaole, et al.
Published: (2025)

Training-free Regional Prompting for Diffusion Transformers
by: Chen, Anthony, et al.
Published: (2024)

Cross-modal Information Flow in Multimodal Large Language Models
by: Zhang, Zhi, et al.
Published: (2024)

CK-Transformer: Commonsense Knowledge Enhanced Transformers for Referring Expression Comprehension
by: Zhang, Zhi, et al.
Published: (2023)

Hummus: A Dataset of Humorous Multimodal Metaphor Use
by: Tong, Xiaoyu, et al.
Published: (2025)

Exploring Sparse Visual Prompt for Domain Adaptive Dense Prediction
by: Yang, Senqiao, et al.
Published: (2023)

MoVE-KD: Knowledge Distillation for VLMs with Mixture of Visual Encoders
by: Cao, Jiajun, et al.
Published: (2025)

MMG-Vid: Maximizing Marginal Gains at Segment-level and Token-level for Efficient Video LLMs
by: Ma, Junpeng, et al.
Published: (2025)

Multimodal Large Language Models for Bioimage Analysis
by: Zhang, Shanghang, et al.
Published: (2024)

SpikeNVS: Enhancing Novel View Synthesis from Blurry Images via Spike Camera
by: Dai, Gaole, et al.
Published: (2024)

Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs
by: Zhang, Qizhe, et al.
Published: (2024)

Continual-MAE: Adaptive Distribution Masked Autoencoders for Continual Test-Time Adaptation
by: Liu, Jiaming, et al.
Published: (2023)

SAN: Hypothesizing Long-Term Synaptic Development and Neural Engram Mechanism in Scalable Model's Parameter-Efficient Fine-Tuning
by: Dai, Gaole, et al.
Published: (2024)

Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs
by: Zhang, Qizhe, et al.
Published: (2025)

Learning from Mistakes: Iterative Prompt Relabeling for Text-to-Image Diffusion Model Training
by: Chen, Xinyan, et al.
Published: (2023)

A Vanilla Multi-Task Framework for Dense Visual Prediction Solution to 1st VCL Challenge -- Multi-Task Robustness Track
by: Chen, Zehui, et al.
Published: (2024)

Unsupervised Spike Depth Estimation via Cross-modality Cross-domain Knowledge Transfer
by: Liu, Jiaming, et al.
Published: (2022)

MoASE++: Mixture of Activation Sparsity Experts with Domain-Adaptive On-policy Distillation for Continual Test Time Adaptation
by: Zhang, Ronyu, et al.
Published: (2026)

Beyond Words: Exploring Cultural Value Sensitivity in Multimodal Models
by: Yadav, Srishti, et al.
Published: (2025)

Mitigating Accuracy-Robustness Trade-off via Balanced Multi-Teacher Adversarial Distillation
by: Zhao, Shiji, et al.
Published: (2023)

Induction Heads as an Essential Mechanism for Pattern Matching in In-context Learning
by: Crosbie, Joy, et al.
Published: (2024)

Learning New Tasks from a Few Examples with Soft-Label Prototypes
by: Singh, Avyav Kumar, et al.
Published: (2022)

Self-Alignment: Improving Alignment of Cultural Values in LLMs via In-Context Learning
by: Choenni, Rochelle, et al.
Published: (2024)

SpikePingpong: Spike Vision-based Fast-Slow Pingpong Robot System
by: Wang, Hao, et al.
Published: (2025)

Decomposing the Neurons: Activation Sparsity via Mixture of Experts for Continual Test Time Adaptation
by: Zhang, Rongyu, et al.
Published: (2024)

LampMark: Proactive Deepfake Detection via Training-Free Landmark Perceptual Watermarks
by: Wang, Tianyi, et al.
Published: (2024)

SparseSSP: 3D Subcellular Structure Prediction from Sparse-View Transmitted Light Images
by: Zheng, Jintu, et al.
Published: (2024)

GCond: Gradient Conflict Resolution via Accumulation-based Stabilization for Large-Scale Multi-Task Learning
by: Limarenko, Evgeny Alves, et al.
Published: (2025)

FlexGaussian: Flexible and Cost-Effective Training-Free Compression for 3D Gaussian Splatting
by: Tian, Boyuan, et al.
Published: (2025)

Take A Shortcut Back: Mitigating the Gradient Vanishing for Training Spiking Neural Networks
by: Guo, Yufei, et al.
Published: (2024)

FastVGGT: Training-Free Acceleration of Visual Geometry Transformer
by: Shen, You, et al.
Published: (2025)

Bidirectional Sparse Attention for Faster Video Diffusion Training
by: Zhan, Chenlu, et al.
Published: (2025)

Meta-Semi: A Meta-learning Approach for Semi-supervised Learning
by: Wang, Yulin, et al.
Published: (2020)

Unprejudiced Training Auxiliary Tasks Makes Primary Better: A Multi-Task Learning Perspective
by: Li, Yuanze, et al.
Published: (2024)

Resolving Token-Space Gradient Conflicts: Token Space Manipulation for Transformer-Based Multi-Task Learning
by: Jeong, Wooseong, et al.
Published: (2025)

Resolving Task Objective Conflicts in Unified Model via Task-Aware Mixture-of-Experts
by: Zhang, Jiaxing, et al.
Published: (2025)

Learning from Different Samples: A Source-free Framework for Semi-supervised Domain Adaptation
by: Huang, Xinyang, et al.
Published: (2024)