Copertina

Navigating Scaling Laws: Compute Optimality in Adaptive Model Training

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Anagnostidis, Sotiris, Bachmann, Gregor, Schlag, Imanol, Hofmann, Thomas
Natura:	Preprint
Pubblicazione:	2023
Soggetti:	Machine Learning Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Towards Meta-Pruning via Optimal Transport
di: Theus, Alexander, et al.
Pubblicazione: (2024)

FlexiDiT: Your Diffusion Transformer Can Easily Generate High-Quality Samples with Less Compute
di: Anagnostidis, Sotiris, et al.
Pubblicazione: (2025)

Exploring Magnitude Preservation and Rotation Modulation in Diffusion Transformers
di: Bill, Eric Tillman, et al.
Pubblicazione: (2025)

MegaPortrait: Revisiting Diffusion Control for High-fidelity Portrait Generation
di: Yang, Han, et al.
Pubblicazione: (2024)

Energy Scaling Laws for Diffusion Models: Quantifying Compute in Image Generation
di: Iyengar, Aniketh, et al.
Pubblicazione: (2025)

IC-Portrait: In-Context Matching for View-Consistent Personalized Portrait
di: Yang, Han, et al.
Pubblicazione: (2025)

Training a Computer Vision Model for Commercial Bakeries with Primarily Synthetic Images
di: Schmitt, Thomas H., et al.
Pubblicazione: (2024)

Getting ViT in Shape: Scaling Laws for Compute-Optimal Model Design
di: Alabdulmohsin, Ibrahim, et al.
Pubblicazione: (2023)

ScaMo: Exploring the Scaling Law in Autoregressive Motion Generation Model
di: Lu, Shunlin, et al.
Pubblicazione: (2024)

Adaptive Training Meets Progressive Scaling: Elevating Efficiency in Diffusion Models
di: Li, Wenhao, et al.
Pubblicazione: (2023)

Variance-Aware Adaptive Weighting for Diffusion Model Training
di: Sun, Nanlong, et al.
Pubblicazione: (2026)

Scaling Laws for Black box Adversarial Attacks
di: Liu, Chuan, et al.
Pubblicazione: (2024)

Towards Large-Scale Training of Pathology Foundation Models
di: ai, kaiko., et al.
Pubblicazione: (2024)

AdaDeDup: Adaptive Hybrid Data Pruning for Efficient Large-Scale Object Detection Training
di: Kang, Feiyang, et al.
Pubblicazione: (2025)

Revisiting Compositionality in Dual-Encoder Vision-Language Models: The Role of Inference
di: Miranda, Imanol, et al.
Pubblicazione: (2026)

Class Adaptive Conformal Training
di: Marani, Badr-Eddine, et al.
Pubblicazione: (2026)

Adaptive Non-uniform Timestep Sampling for Accelerating Diffusion Model Training
di: Kim, Myunsoo, et al.
Pubblicazione: (2024)

Training Feature Attribution for Vision Models
di: Bacha, Aziz, et al.
Pubblicazione: (2025)

RB-Modulation: Training-Free Personalization of Diffusion Models using Stochastic Optimal Control
di: Rout, Litu, et al.
Pubblicazione: (2024)

Graph Neural Networks for Surgical Scene Segmentation
di: Li, Yihan, et al.
Pubblicazione: (2025)

Simplifying CLIP: Unleashing the Power of Large-Scale Models on Consumer-level Computers
di: Liu, Hongbo
Pubblicazione: (2024)

Reinforce Adjoint Matching: Scaling RL Post-Training of Diffusion and Flow-Matching Models
di: Bergmeister, Andreas, et al.
Pubblicazione: (2026)

Revisiting Class-Incremental Learning with Pre-Trained Models: Generalizability and Adaptivity are All You Need
di: Zhou, Da-Wei, et al.
Pubblicazione: (2023)

On Domain-Adaptive Post-Training for Multimodal Large Language Models
di: Cheng, Daixuan, et al.
Pubblicazione: (2024)

How much is a noisy image worth? Data Scaling Laws for Ambient Diffusion
di: Daras, Giannis, et al.
Pubblicazione: (2024)

TinyTrain: Resource-Aware Task-Adaptive Sparse Training of DNNs at the Data-Scarce Edge
di: Kwon, Young D., et al.
Pubblicazione: (2023)

Data Scaling Laws for End-to-End Autonomous Driving
di: Naumann, Alexander, et al.
Pubblicazione: (2025)

Adding simple structure at inference improves Vision-Language Compositionality
di: Miranda, Imanol, et al.
Pubblicazione: (2025)

BiVLC: Extending Vision-Language Compositionality Evaluation with Text-to-Image Retrieval
di: Miranda, Imanol, et al.
Pubblicazione: (2024)

Adaptive Retention & Correction: Test-Time Training for Continual Learning
di: Chen, Haoran, et al.
Pubblicazione: (2024)

dynActivation: A Trainable Activation Family for Adaptive Nonlinearity
di: Bachmann, Alois
Pubblicazione: (2026)

Learning Images Across Scales Using Adversarial Training
di: Wolski, Krzysztof, et al.
Pubblicazione: (2024)

Wild Visual Navigation: Fast Traversability Learning via Pre-Trained Models and Online Self-Supervision
di: Mattamala, Matías, et al.
Pubblicazione: (2024)

From Isolation to Integration: Building an Adaptive Expert Forest for Pre-Trained Model-based Class-Incremental Learning
di: Liu, Ruiqi, et al.
Pubblicazione: (2026)

Scaling Laws for Task-Optimized Models of the Primate Visual Ventral Stream
di: Gokce, Abdulkadir, et al.
Pubblicazione: (2024)

Towards Fair Class-wise Robustness: Class Optimal Distribution Adversarial Training
di: Zhi, Hongxin, et al.
Pubblicazione: (2025)

Sharpness-Aware Minimization with Adaptive Regularization for Training Deep Neural Networks
di: Zou, Jinping, et al.
Pubblicazione: (2024)

Taming the Long Tail: Rebalancing Adversarial Training via Adaptive Perturbation
di: Zhang, Lilin, et al.
Pubblicazione: (2026)

Model Steering: Learning with a Reference Model Improves Generalization Bounds and Scaling Laws
di: Wei, Xiyuan, et al.
Pubblicazione: (2025)

How Well Does GPT-4o Understand Vision? Evaluating Multimodal Foundation Models on Standard Computer Vision Tasks
di: Ramachandran, Rahul, et al.
Pubblicazione: (2025)