Copertina

MaD-Mix: Multi-Modal Data Mixtures via Latent Space Coupling for Vision-Language Model Training

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Xie, Wanyun, Tonin, Francesco, Cevher, Volkan
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Chameleon: A Flexible Data-mixing Framework for Language Model Pretraining and Finetuning
di: Xie, Wanyun, et al.
Pubblicazione: (2025)

Stable Nonconvex-Nonconcave Training via Linear Interpolation
di: Pethick, Thomas, et al.
Pubblicazione: (2023)

Efficient Large Language Model Inference with Neural Block Linearization
di: Erdogan, Mete, et al.
Pubblicazione: (2025)

SAMPa: Sharpness-aware Minimization Parallelized
di: Xie, Wanyun, et al.
Pubblicazione: (2024)

Optimistic Dual Averaging Unifies Modern Optimizers
di: Pethick, Thomas, et al.
Pubblicazione: (2026)

Training Deep Learning Models with Norm-Constrained LMOs
di: Pethick, Thomas, et al.
Pubblicazione: (2025)

Improving SAM Requires Rethinking its Optimization Formulation
di: Xie, Wanyun, et al.
Pubblicazione: (2024)

Membership Inference Attacks against Large Vision-Language Models
di: Li, Zhan, et al.
Pubblicazione: (2024)

Accelerating Spectral Clustering under Fairness Constraints
di: Tonin, Francesco, et al.
Pubblicazione: (2025)

HeNCler: Node Clustering in Heterophilous Graphs via Learned Asymmetric Similarity
di: Achten, Sonny, et al.
Pubblicazione: (2024)

MaD Physics: Evaluating information seeking under constraints in physical environments
di: Jain, Moksh, et al.
Pubblicazione: (2026)

Generalized Gradient Norm Clipping & Non-Euclidean $(L_0,L_1)$-Smoothness
di: Pethick, Thomas, et al.
Pubblicazione: (2025)

Faster Inference of Flow-Based Generative Models via Improved Data-Noise Coupling
di: Davtyan, Aram, et al.
Pubblicazione: (2026)

Quantum-PEFT: Ultra parameter-efficient fine-tuning
di: Koike-Akino, Toshiaki, et al.
Pubblicazione: (2025)

MaD-Scientist: AI-based Scientist solving Convection-Diffusion-Reaction Equations Using Massive PINN-Based Prior Data
di: Kang, Mingu, et al.
Pubblicazione: (2024)

ESLM: Risk-Averse Selective Language Modeling for Efficient Pretraining
di: Bal, Melis Ilayda, et al.
Pubblicazione: (2025)

Adversarial Training for Defense Against Label Poisoning Attacks
di: Bal, Melis Ilayda, et al.
Pubblicazione: (2025)

Linear Attention for Efficient Bidirectional Sequence Modeling
di: Afzal, Arshia, et al.
Pubblicazione: (2025)

Easy Data Unlearning Bench
di: Rinberg, Roy, et al.
Pubblicazione: (2026)

Learning Equilibria from Data: Provably Efficient Multi-Agent Imitation Learning
di: Freihaut, Till, et al.
Pubblicazione: (2025)

Split the Differences, Pool the Rest: Provably Efficient Multi-Objective Imitation
di: Sheebaelhamd, Ziyad, et al.
Pubblicazione: (2026)

High-Dimensional Kernel Methods under Covariate Shift: Data-Dependent Implicit Regularization
di: Chen, Yihang, et al.
Pubblicazione: (2024)

Learning with Norm Constrained, Over-parameterized, Two-layer Neural Networks
di: Liu, Fanghui, et al.
Pubblicazione: (2024)

IL-SOAR : Imitation Learning with Soft Optimistic Actor cRitic
di: Viel, Stefano, et al.
Pubblicazione: (2025)

Imitation Learning in Discounted Linear MDPs without exploration assumptions
di: Viano, Luca, et al.
Pubblicazione: (2024)

Matching Multiple Experts: On the Exploitability of Multi-Agent Imitation Learning
di: Bergerault, Antoine, et al.
Pubblicazione: (2026)

MT-NAM: An Efficient and Adaptive Model for Epileptic Seizure Detection
di: Afzal, Arshia, et al.
Pubblicazione: (2025)

Training Neural Networks at Any Scale
di: Pethick, Thomas, et al.
Pubblicazione: (2025)

Learning in Feature Spaces via Coupled Covariances: Asymmetric Kernel SVD and Nyström method
di: Tao, Qinghua, et al.
Pubblicazione: (2024)

Transformers Learn Latent Mixture Models In-Context via Mirror Descent
di: D'Angelo, Francesco, et al.
Pubblicazione: (2026)

Adversarial Training Should Be Cast as a Non-Zero-Sum Game
di: Robey, Alexander, et al.
Pubblicazione: (2023)

Provably avoiding over-optimization in Direct Preference Optimization without knowing the data distribution
di: Barla, Adam, et al.
Pubblicazione: (2026)

Leveraging the Context through Multi-Round Interactions for Jailbreaking Attacks
di: Cheng, Yixin, et al.
Pubblicazione: (2024)

MixMax: Distributional Robustness in Function Space via Optimal Data Mixtures
di: Thudi, Anvith, et al.
Pubblicazione: (2024)

Revisiting SMoE Language Models by Evaluating Inefficiencies with Task Specific Expert Pruning
di: Sarkar, Soumajyoti, et al.
Pubblicazione: (2024)

Multi-agent imitation learning with function approximation: Linear Markov games and beyond
di: Viano, Luca, et al.
Pubblicazione: (2026)

MergeMix: Optimizing Mid-Training Data Mixtures via Learnable Model Merging
di: Wang, Jiapeng, et al.
Pubblicazione: (2026)

Revisiting Character-level Adversarial Attacks for Language Models
di: Rocamora, Elias Abad, et al.
Pubblicazione: (2024)

μP$^2$: Effective Sharpness Aware Minimization Requires Layerwise Perturbation Scaling
di: Haas, Moritz, et al.
Pubblicazione: (2024)

Addressing Label Shift in Distributed Learning via Entropy Regularization
di: Wu, Zhiyuan, et al.
Pubblicazione: (2025)