Cover Image

inversedMixup: Data Augmentation via Inverting Mixed Embeddings

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Kong, Fanshuang, Zhang, Richong, Sun, Qiyu, Nie, Zhijie, Deng, Ting, Hu, Chunming
Format:	Preprint
Published:	2026
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

LH-Mix: Local Hierarchy Correlation Guided Mixup over Hierarchical Prompt Tuning
by: Kong, Fanshuang, et al.
Published: (2024)

Activated Parameter Locating via Causal Intervention for Model Merging
by: Kong, Fanshuang, et al.
Published: (2024)

A Text is Worth Several Tokens: Text Embedding from LLMs Secretly Aligns Well with The Key Tokens
by: Nie, Zhijie, et al.
Published: (2024)

Towards Better Understanding of Contrastive Sentence Representation Learning: A Unified Paradigm for Gradient
by: Li, Mingxin, et al.
Published: (2024)

MOMA: Masked Orthogonal Matrix Alignment for Zero-Additional-Parameter Model Merging
by: Kong, Fanshuang, et al.
Published: (2024)

Improving General Text Embedding Model: Tackling Task Conflict and Data Imbalance through Model Merging
by: Li, Mingxin, et al.
Published: (2024)

Dynamic Task Vector Grouping for Efficient Multi-Task Prompt Tuning
by: Zhang, Pieyi, et al.
Published: (2025)

CoRect: Context-Aware Logit Contrast for Hidden State Rectification to Resolve Knowledge Conflicts
by: Ma, Xuhua, et al.
Published: (2026)

LM-mixup: Text Data Augmentation via Language Model based Mixup
by: Deng, Zhijie, et al.
Published: (2025)

Lost-in-the-Middle in Long-Text Generation: Synthetic Dataset, Evaluation Framework, and Mitigation
by: Zhang, Junhao, et al.
Published: (2025)

General Table Question Answering via Answer-Formula Joint Generation
by: Wang, Zhongyuan, et al.
Published: (2025)

Tool-Assisted Agent on SQL Inspection and Refinement in Real-World Scenarios
by: Wang, Zhongyuan, et al.
Published: (2024)

Code-Style In-Context Learning for Knowledge-Based Question Answering
by: Nie, Zhijie, et al.
Published: (2023)

EasyRAG: Efficient Retrieval-Augmented Generation Framework for Automated Network Operations
by: Feng, Zhangchi, et al.
Published: (2024)

A Graph-based Verification Framework for Fact-Checking
by: Huang, Yani, et al.
Published: (2025)

When Text Embedding Meets Large Language Model: A Comprehensive Survey
by: Nie, Zhijie, et al.
Published: (2024)

Improving Zero-Shot Cross-Lingual Transfer via Progressive Code-Switching
by: Li, Zhuoran, et al.
Published: (2024)

Implicit Word Reordering with Knowledge Distillation for Cross-Lingual Dependency Parsing
by: Li, Zhuoran, et al.
Published: (2025)

Text2Token: Unsupervised Text Representation Learning with Token Target Prediction
by: An, Ruize, et al.
Published: (2025)

AR-BENCH: Benchmarking Legal Reasoning with Judgment Error Detection, Classification and Correction
by: Li, Yifei, et al.
Published: (2026)

Improving Composed Image Retrieval via Contrastive Learning with Scaling Positives and Negatives
by: Feng, Zhangchi, et al.
Published: (2024)

Easy Dataset: A Unified and Extensible Framework for Synthesizing LLM Fine-Tuning Data from Unstructured Documents
by: Miao, Ziyang, et al.
Published: (2025)

On SkipGram Word Embedding Models with Negative Sampling: Unified Framework and Impact of Noise Distributions
by: Liu, Dezhi, et al.
Published: (2020)

ConvMix: A Mixed-Criteria Data Augmentation Framework for Conversational Dense Retrieval
by: Mo, Fengran, et al.
Published: (2025)

ICON: Improving Inter-Report Consistency in Radiology Report Generation via Lesion-aware Mixup Augmentation
by: Hou, Wenjun, et al.
Published: (2024)

CAARMA: Class Augmentation with Adversarial Mixup Regularization
by: Baali, Massa, et al.
Published: (2025)

Mix-of-Language-Experts Architecture for Multilingual Programming
by: Zong, Yifan, et al.
Published: (2025)

Enhancing Unsupervised Sentence Embeddings via Knowledge-Driven Data Augmentation and Gaussian-Decayed Contrastive Learning
by: Lai, Peichao, et al.
Published: (2024)

Embedding Domain Knowledge for Large Language Models via Reinforcement Learning from Augmented Generation
by: Nie, Chaojun, et al.
Published: (2025)

Adapters Mixup: Mixing Parameter-Efficient Adapters to Enhance the Adversarial Robustness of Fine-tuned Pre-trained Text Classifiers
by: Nguyen, Tuc, et al.
Published: (2024)

Progressively Modality Freezing for Multi-Modal Entity Alignment
by: Huang, Yani, et al.
Published: (2024)

Multimodal Abstractive Summarization of Instructional Videos with Vision-Language Models
by: Nazir, Maham, et al.
Published: (2026)

Leveraging Multi-lingual Positive Instances in Contrastive Learning to Improve Sentence Embedding
by: Zhao, Kaiyan, et al.
Published: (2023)

Boosting Biomedical Concept Extraction by Rule-Based Data Augmentation
by: Shao, Qiwei, et al.
Published: (2024)

CoDAE: Adapting Large Language Models for Education via Chain-of-Thought Data Augmentation
by: Yuan, Shuzhou, et al.
Published: (2025)

KaLM-Embedding: Superior Training Data Brings A Stronger Embedding Model
by: Hu, Xinshuo, et al.
Published: (2025)

Enhancing Cross-lingual Sentence Embedding for Low-resource Languages with Word Alignment
by: Miao, Zhongtao, et al.
Published: (2024)

Bridging the Language Gap: Synthetic Voice Diversity via Latent Mixup for Equitable Speech Recognition
by: Bian, Wesley, et al.
Published: (2025)

Learning to Select: Query-Aware Adaptive Dimension Selection for Dense Retrieval
by: Wu, Zhanyu, et al.
Published: (2026)

SampleMix: A Sample-wise Pre-training Data Mixing Strategey by Coordinating Data Quality and Diversity
by: Xi, Xiangyu, et al.
Published: (2025)