Imagen de Portada

From Fewer Samples to Fewer Bits: Reframing Dataset Distillation as Joint Optimization of Precision and Compactness

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Dinh, My H., Sant, Aditya, Malhotra, Akshay, Patani, Keya, Hamidi-Rad, Shahab
Formato:	Preprint
Publicado:	2026
Materias:	Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Fewer is More: A Deep Graph Metric Learning Perspective Using Fewer Proxies
por: Zhu, Yuehua, et al.
Publicado: (2020)

Fewer Tokens and Fewer Videos: Extending Video Understanding Abilities in Large Vision-Language Models
por: Chen, Shimin, et al.
Publicado: (2024)

FQGA-single: Towards Fewer Training Epochs and Fewer Model Parameters for Image-to-Image Translation Tasks
por: Yang, Cho
Publicado: (2024)

Replacement Learning: Training Neural Networks with Fewer Parameters
por: Zhang, Yuming, et al.
Publicado: (2026)

Few and Fewer: Learning Better from Few Examples Using Fewer Base Classes
por: Lafargue, Raphael, et al.
Publicado: (2024)

Comparing Stochastic and Ray-tracing Datasets in Machine Learning for Wireless Applications
por: Morais, João, et al.
Publicado: (2025)

Replacement Learning: Training Vision Tasks with Fewer Learnable Parameters
por: Zhang, Yuming, et al.
Publicado: (2024)

Partial Channel Network: Compute Fewer, Perform Better
por: Huang, Haiduo, et al.
Publicado: (2025)

Neural Shell Texture Splatting: More Details and Fewer Primitives
por: Zhang, Xin, et al.
Publicado: (2025)

Sculpting Latent Spaces With MMD: Disentanglement With Programmable Priors
por: Fruytier, Quentin, et al.
Publicado: (2025)

Boosting Sclera Segmentation through Semi-supervised Learning with Fewer Labels
por: Wang, Guanjun, et al.
Publicado: (2025)

Polar R-CNN: End-to-End Lane Detection with Fewer Anchors
por: Wang, Shengqi, et al.
Publicado: (2024)

ReGATE: Learning Faster and Better with Fewer Tokens in MLLMs
por: Li, Chaoyu, et al.
Publicado: (2025)

ELIP: Efficient Discriminative Language-Image Pre-training with Fewer Vision Tokens
por: Guo, Yangyang, et al.
Publicado: (2023)

FastLightGen: Fast and Light Video Generation with Fewer Steps and Parameters
por: Shao, Shitong, et al.
Publicado: (2026)

Scaling Artificial Intelligence for Multi-Tumor Early Detection with More Reports, Fewer Masks
por: Bassi, Pedro R. A. S., et al.
Publicado: (2025)

Less is More: Fewer Interpretable Region via Submodular Subset Selection
por: Chen, Ruoyu, et al.
Publicado: (2024)

XNet v2: Fewer Limitations, Better Results and Greater Universality
por: Zhou, Yanfeng, et al.
Publicado: (2024)

LoGS: Visual Localization via Gaussian Splatting with Fewer Training Images
por: Cheng, Yuzhou, et al.
Publicado: (2024)

Faster Training, Fewer Labels: Self-Supervised Pretraining for Fine-Grained BEV Segmentation
por: Busch, Daniel, et al.
Publicado: (2026)

Stronger, Fewer, & Superior: Harnessing Vision Foundation Models for Domain Generalized Semantic Segmentation
por: Wei, Zhixiang, et al.
Publicado: (2023)

Treat Visual Tokens as Text? But Your MLLM Only Needs Fewer Efforts to See
por: Zhang, Zeliang, et al.
Publicado: (2024)

Depth-supervised NeRF: Fewer Views and Faster Training for Free
por: Deng, Kangle, et al.
Publicado: (2021)

Disentanglement in T-space for Faster and Distributed Training of Diffusion Models with Fewer Latent-states
por: Gupta, Samarth, et al.
Publicado: (2025)

Inference Optimal VLMs Need Fewer Visual Tokens and More Parameters
por: Li, Kevin Y., et al.
Publicado: (2024)

A Dataset Similarity Evaluation Framework for Wireless Communications and Sensing
por: Morais, Joao, et al.
Publicado: (2024)

ConeGS: Error-Guided Densification Using Pixel Cones for Improved Reconstruction With Fewer Primitives
por: Baranowski, Bartłomiej, et al.
Publicado: (2025)

Fewer Tokens, Greater Scaling: Self-Adaptive Visual Bases for Efficient and Expansive Representation Learning
por: Young, Shawn, et al.
Publicado: (2025)

Wireless Dataset Similarity: Measuring Distances in Supervised and Unsupervised Machine Learning
por: Morais, João, et al.
Publicado: (2026)

Score-based Conditional Generation with Fewer Labeled Data by Self-calibrating Classifier Guidance
por: Huang, Paul Kuo-Ming, et al.
Publicado: (2023)

Physics-Informed Generative Approaches for Wireless Channel Modeling
por: Wagle, Satyavrat, et al.
Publicado: (2025)

Physics-based Generative Models for Geometrically Consistent and Interpretable Wireless Channel Synthesis
por: Wagle, Satyavrat, et al.
Publicado: (2025)

Fewer Denoising Steps or Cheaper Per-Step Inference: Towards Compute-Optimal Diffusion Model Deployment
por: Du, Zhenbang, et al.
Publicado: (2025)

LWM-CDE: A Representation Space for Wireless Data Reasoning and Transferability
por: Alikhani, Sadjad, et al.
Publicado: (2026)

LWM-Temporal: Sparse Spatio-Temporal Attention for Wireless Channel Representation Learning
por: Alikhani, Sadjad, et al.
Publicado: (2026)

Information-Guided Diffusion Sampling for Dataset Distillation
por: Ye, Linfeng, et al.
Publicado: (2025)

iLLaVA: An Image is Worth Fewer Than 1/3 Input Tokens in Large Multimodal Models
por: Hu, Lianyu, et al.
Publicado: (2024)

Joint Image De-noising and Enhancement for Satellite-Based SAR
por: Hamidi, Shahrokh
Publicado: (2024)

LLaVA Steering: Visual Instruction Tuning with 500x Fewer Parameters through Modality Linear Representation-Steering
por: Bi, Jinhe, et al.
Publicado: (2024)

TextHawk2: A Large Vision-Language Model Excels in Bilingual OCR and Grounding with 16x Fewer Tokens
por: Yu, Ya-Qi, et al.
Publicado: (2024)