Cover Image

Improve Multi-Modal Embedding Learning via Explicit Hard Negative Gradient Amplifying

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Xue, Youze, Li, Dian, Liu, Gang
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Adaptive Global and Fine-Grained Perceptual Fusion for MLLM Embeddings Compatible with Hard Negative Amplification
by: Hu, Lexiang, et al.
Published: (2026)

Improving Generalization via Meta-Learning on Hard Samples
by: Jain, Nishant, et al.
Published: (2024)

Visual Perturbation and Adaptive Hard Negative Contrastive Learning for Compositional Reasoning in Vision-Language Models
by: Huang, Xin, et al.
Published: (2025)

Active Learning for Finely-Categorized Image-Text Retrieval by Selecting Hard Negative Unpaired Samples
by: Jo, Dae Ung, et al.
Published: (2024)

Supervised Multi-Modal Fission Learning
by: Mao, Lingchao, et al.
Published: (2024)

GNSP: Gradient Null Space Projection for Preserving Cross-Modal Alignment in VLMs Continual Learning
by: Peng, Tiantian, et al.
Published: (2025)

No Hard Negatives Required: Concept Centric Learning Leads to Compositionality without Degrading Zero-shot Capabilities of Contrastive Models
by: Pham, Hai X., et al.
Published: (2026)

Dual-View Inference Attack: Machine Unlearning Amplifies Privacy Exposure
by: Xue, Lulu, et al.
Published: (2025)

Mitigating Visual Knowledge Forgetting in MLLM Instruction-tuning via Modality-decoupled Gradient Descent
by: Wu, Junda, et al.
Published: (2025)

MMP: Towards Robust Multi-Modal Learning with Masked Modality Projection
by: Nezakati, Niki, et al.
Published: (2024)

Explicit Eigenvalue Regularization Improves Sharpness-Aware Minimization
by: Luo, Haocheng, et al.
Published: (2025)

Overcome Modal Bias in Multi-modal Federated Learning via Balanced Modality Selection
by: Fan, Yunfeng, et al.
Published: (2023)

DUNIA: Pixel-Sized Embeddings via Cross-Modal Alignment for Earth Observation Applications
by: Fayad, Ibrahim, et al.
Published: (2025)

PEARL: Input-Agnostic Prompt Enhancement with Negative Feedback Regulation for Class-Incremental Learning
by: Qin, Yongchun, et al.
Published: (2024)

Explicit Mutual Information Maximization for Self-Supervised Learning
by: Chang, Lele, et al.
Published: (2024)

MMCORE: MultiModal COnnection with Representation Aligned Latent Embeddings
by: Li, Zijie, et al.
Published: (2026)

Learning Continuous Face Representation with Explicit Functions
by: Zhang, Liping, et al.
Published: (2021)

Cross-Modal Redundancy and the Geometry of Vision-Language Embeddings
by: Dhimoïla, Grégoire, et al.
Published: (2026)

Modality-Aware SAM: Sharpness-Aware-Minimization Driven Gradient Modulation for Harmonized Multimodal Learning
by: Nowdeh, Hossein R., et al.
Published: (2025)

Mind the Gap: Learning Modality-Agnostic Representations with a Cross-Modality UNet
by: Niu, Xin, et al.
Published: (2026)

NoT: Federated Unlearning via Weight Negation
by: Khalil, Yasser H., et al.
Published: (2025)

XSpecMesh: Quality-Preserving Auto-Regressive Mesh Generation Acceleration via Multi-Head Speculative Decoding
by: Chen, Dian, et al.
Published: (2025)

Diffusion Model Conditioning on Gaussian Mixture Model and Negative Gaussian Mixture Gradient
by: Lu, Weiguo, et al.
Published: (2024)

Balanced Multi-modal Federated Learning via Cross-Modal Infiltration
by: Fan, Yunfeng, et al.
Published: (2023)

MoRA: LoRA Guided Multi-Modal Disease Diagnosis with Missing Modality
by: Shi, Zhiyi, et al.
Published: (2024)

Text-centric Alignment for Multi-Modality Learning
by: Tsai, Yun-Da, et al.
Published: (2024)

Gradient Similarity Surgery in Multi-Task Deep Learning
by: Borsani, Thomas, et al.
Published: (2025)

Deep Learning-Based Multi-Modal Fusion for Robust Robot Perception and Navigation
by: Lai, Delun, et al.
Published: (2025)

MMRL: Multi-Modal Representation Learning for Vision-Language Models
by: Guo, Yuncheng, et al.
Published: (2025)

Learning to Rebalance Multi-Modal Optimization by Adaptively Masking Subnetworks
by: Yang, Yang, 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)

Negative Label Guided OOD Detection with Pretrained Vision-Language Models
by: Jiang, Xue, et al.
Published: (2024)

Flatness and Gradient Alignment Are Both Necessary: Spectral-Aware Gradient-Aligned Exploration for Multi-Distribution Learning
by: Ballas, Aristotelis, et al.
Published: (2026)

Improving OOD Generalization of Pre-trained Encoders via Aligned Embedding-Space Ensembles
by: Peng, Shuman, et al.
Published: (2024)

Modality-Balanced Collaborative Distillation for Multi-Modal Domain Generalization
by: Wang, Xiaohan, et al.
Published: (2025)

BELM: Bidirectional Explicit Linear Multi-step Sampler for Exact Inversion in Diffusion Models
by: Wang, Fangyikang, et al.
Published: (2024)

Target Detection of Safety Protective Gear Using the Improved YOLOv5
by: Liu, Hao, et al.
Published: (2024)

Rehabilitation Exercise Quality Assessment through Supervised Contrastive Learning with Hard and Soft Negatives
by: Karlov, Mark, et al.
Published: (2024)

Improved Alignment of Modalities in Large Vision Language Models
by: Jangra, Kartik, et al.
Published: (2025)

Federated Adaptive Prompt Tuning for Multi-Domain Collaborative Learning
by: Su, Shangchao, et al.
Published: (2022)