Imagen de Portada

Improving Multimodal Learning Balance and Sufficiency through Data Remixing

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Ma, Xiaoyu, Chen, Hao, Deng, Yongjian
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Balancing Multimodal Learning through Label Space Reshaping
por: Ma, Xiaoyu, et al.
Publicado: (2026)

Mashup Learning: Faster Finetuning by Remixing Past Checkpoints
por: Vaina, Sofia Maria Lo Cicero, et al.
Publicado: (2026)

Seeking the Sufficiency and Necessity Causal Features in Multimodal Representation Learning
por: Chen, Boyu, et al.
Publicado: (2024)

CLIP the Bias: How Useful is Balancing Data in Multimodal Learning?
por: Alabdulmohsin, Ibrahim, et al.
Publicado: (2024)

Data-Centric Machine Learning for Earth Observation: Necessary and Sufficient Features
por: Najjar, Hiba, et al.
Publicado: (2024)

Sufficient Invariant Learning for Distribution Shift
por: Kim, Taero, et al.
Publicado: (2022)

Is In-Context Learning Sufficient for Instruction Following in LLMs?
por: Zhao, Hao, et al.
Publicado: (2024)

Navigating Data Corruption in Machine Learning: Balancing Quality, Quantity, and Imputation Strategies
por: Liu, Qi, et al.
Publicado: (2024)

Improving Influence-based Instruction Tuning Data Selection for Balanced Learning of Diverse Capabilities
por: Dai, Qirun, et al.
Publicado: (2025)

Efficient Ensembles Improve Training Data Attribution
por: Deng, Junwei, et al.
Publicado: (2024)

BalanceBenchmark: A Survey for Multimodal Imbalance Learning
por: Xu, Shaoxuan, et al.
Publicado: (2025)

Towards Explainable Fusion and Balanced Learning in Multimodal Sentiment Analysis
por: Luo, Miaosen, et al.
Publicado: (2025)

Reward Guidance for Reinforcement Learning Tasks Based on Large Language Models: The LMGT Framework
por: Deng, Yongxin, et al.
Publicado: (2024)

Rebalanced Multimodal Learning with Data-aware Unimodal Sampling
por: Jiang, Qingyuan, et al.
Publicado: (2025)

Adaptive Redundancy Regulation for Balanced Multimodal Information Refinement
por: Yang, Zhe, et al.
Publicado: (2025)

Causally Sufficient and Necessary Feature Expansion for Class-Incremental Learning
por: Zhang, Zhen, et al.
Publicado: (2026)

Unifying Invariant and Variant Features for Graph Out-of-Distribution via Probability of Necessity and Sufficiency
por: Chen, Xuexin, et al.
Publicado: (2024)

Occam's Razor for Self Supervised Learning: What is Sufficient to Learn Good Representations?
por: Ibrahim, Mark, et al.
Publicado: (2024)

Action-Sufficient Goal Representations
por: Hyeon, Jinu, et al.
Publicado: (2026)

Balance-aware Sequence Sampling Makes Multi-modal Learning Better
por: Guan, Zhi-Hao
Publicado: (2025)

Meta-TTRL: A Metacognitive Framework for Self-Improving Test-Time Reinforcement Learning in Unified Multimodal Models
por: Tan, Lit Sin, et al.
Publicado: (2026)

Markov Balance Satisfaction Improves Performance in Strictly Batch Offline Imitation Learning
por: Agrawal, Rishabh, et al.
Publicado: (2024)

Unity by Diversity: Improved Representation Learning in Multimodal VAEs
por: Sutter, Thomas M., et al.
Publicado: (2024)

Language Model Embeddings Can Be Sufficient for Bayesian Optimization
por: Nguyen, Tung, et al.
Publicado: (2024)

Dimensional Balance Improves Large Scale Spatiotemporal Prediction Performance
por: Chen, Jing, et al.
Publicado: (2026)

When Does Learning Renormalize? Sufficient Conditions for Power Law Spectral Dynamics
por: Zhang, Yizhou
Publicado: (2025)

Autonomous Drift Learning in Data Streams: A Unified Perspective
por: Yang, Xiaoyu, et al.
Publicado: (2026)

DISCO Balances the Scales: Adaptive Domain- and Difficulty-Aware Reinforcement Learning on Imbalanced Data
por: Zhou, Yuhang, et al.
Publicado: (2025)

Adaptive Unimodal Regulation for Balanced Multimodal Information Acquisition
por: Huang, Chengxiang, et al.
Publicado: (2025)

MEASURE: Multi-scale Minimal Sufficient Representation Learning for Domain Generalization in Sleep Staging
por: Jo, Sangmin, et al.
Publicado: (2025)

Dual-Balancing for Multi-Task Learning
por: Lin, Baijiong, et al.
Publicado: (2023)

Sufficient and Necessary Explanations (and What Lies in Between)
por: Bharti, Beepul, et al.
Publicado: (2024)

Entropy-Guided Data-Efficient Training for Multimodal Reasoning Reward Models
por: Yang, Shidong, et al.
Publicado: (2026)

Implicit Hypergraph Neural Network
por: Choudhuri, Akash, et al.
Publicado: (2025)

Learning Reconfigurable Representations for Multimodal Federated Learning with Missing Data
por: Nguyen, Duong M., et al.
Publicado: (2025)

LearnAlign: Data Selection for LLM Reinforcement Learning with Improved Gradient Alignment
por: Li, Shipeng, et al.
Publicado: (2025)

LANISTR: Multimodal Learning from Structured and Unstructured Data
por: Ebrahimi, Sayna, et al.
Publicado: (2023)

From Incomplete Coarse-Grained to Complete Fine-Grained: A Two-Stage Framework for Spatiotemporal Data Reconstruction
por: Sun, Ziyu, et al.
Publicado: (2024)

Data Whitening Improves Sparse Autoencoder Learning
por: Saraswatula, Ashwin, et al.
Publicado: (2025)

Towards Multimodal Active Learning: Efficient Learning with Limited Paired Data
por: Zhang, Jiancheng, et al.
Publicado: (2025)