Imagen de Portada

Progressive Weight Loading: Accelerating Initial Inference and Gradually Boosting Performance on Resource-Constrained Environments

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Kim, Hyunwoo, Lee, Junha, Choi, Mincheol, Lee, Jeonghwan, Cho, Jaeshin
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

Beyond Gaussian Initializations: Signal Preserving Weight Initialization for Odd-Sigmoid Activations
por: Lee, Hyunwoo, et al.
Publicado: (2025)

Robust Weight Initialization for Tanh Neural Networks with Fixed Point Analysis
por: Lee, Hyunwoo, et al.
Publicado: (2024)

Memory-Efficient Acceleration of Block Low-Rank Foundation Models on Resource Constrained GPUs
por: Abillama, Pierre, et al.
Publicado: (2025)

Frictional Q-Learning
por: Kim, Hyunwoo, et al.
Publicado: (2025)

Learning to Transfer Human Hand Skills for Robot Manipulations
por: Park, Sungjae, et al.
Publicado: (2025)

Temporal Dynamic Embedding for Irregularly Sampled Time Series
por: Kim, Mincheol, et al.
Publicado: (2025)

On Accelerating Edge AI: Optimizing Resource-Constrained Environments
por: Sander, Jacob, et al.
Publicado: (2025)

Constant Acceleration Flow
por: Park, Dogyun, et al.
Publicado: (2024)

Revisiting Weight Averaging for Model Merging
por: Choi, Jiho, et al.
Publicado: (2024)

LiteVLM: A Low-Latency Vision-Language Model Inference Pipeline for Resource-Constrained Environments
por: Huang, Jin, et al.
Publicado: (2025)

Sparse Weight Averaging with Multiple Particles for Iterative Magnitude Pruning
por: Choi, Moonseok, et al.
Publicado: (2023)

TRACED: Transition-aware Regret Approximation with Co-learnability for Environment Design
por: Cho, Geonwoo, et al.
Publicado: (2025)

Wafer-Level Etch Spatial Profiling for Process Monitoring from Time-Series with Time-LLM
por: Kim, Hyunwoo, et al.
Publicado: (2026)

Inversion-based Latent Bayesian Optimization
por: Chu, Jaewon, et al.
Publicado: (2024)

Assigning Distinct Roles to Quantized and Low-Rank Matrices Toward Optimal Weight Decomposition
por: Cho, Yoonjun, et al.
Publicado: (2025)

ARCLE: The Abstraction and Reasoning Corpus Learning Environment for Reinforcement Learning
por: Lee, Hosung, et al.
Publicado: (2024)

Learning Equi-angular Representations for Online Continual Learning
por: Seo, Minhyuk, et al.
Publicado: (2024)

Learning to Act Robustly with View-Invariant Latent Actions
por: Jeong, Youngjoon, et al.
Publicado: (2026)

MONAQ: Multi-Objective Neural Architecture Querying for Time-Series Analysis on Resource-Constrained Devices
por: Trirat, Patara, et al.
Publicado: (2025)

RILQ: Rank-Insensitive LoRA-based Quantization Error Compensation for Boosting 2-bit Large Language Model Accuracy
por: Lee, Geonho, et al.
Publicado: (2024)

Rethinking Multimodal Fusion for Time Series: Auxiliary Modalities Need Constrained Fusion
por: Lee, Seunghan, et al.
Publicado: (2026)

TraM : Enhancing User Sleep Prediction with Transformer-based Multivariate Time Series Modeling and Machine Learning Ensembles
por: Kim, Jinjae, et al.
Publicado: (2024)

Generating Multi-Table Time Series EHR from Latent Space with Minimal Preprocessing
por: Cho, Eunbyeol, et al.
Publicado: (2025)

Self-Supervised Pre-Training for Precipitation Post-Processor
por: An, Sojung, et al.
Publicado: (2023)

WiSparse: Boosting LLM Inference Efficiency with Weight-Aware Mixed Activation Sparsity
por: Chen, Lei, et al.
Publicado: (2026)

Adaptive Sparsified Graph Learning Framework for Vessel Behavior Anomalies
por: Kim, Jeehong, et al.
Publicado: (2025)

Fast Training of Sinusoidal Neural Fields via Scaling Initialization
por: Yeom, Taesun, et al.
Publicado: (2024)

Multidimensional Adaptive Coefficient for Inference Trajectory Optimization in Flow and Diffusion
por: Lee, Dohoon, et al.
Publicado: (2024)

Grokfast: Accelerated Grokking by Amplifying Slow Gradients
por: Lee, Jaerin, et al.
Publicado: (2024)

WINA: Weight Informed Neuron Activation for Accelerating Large Language Model Inference
por: Chen, Sihan, et al.
Publicado: (2025)

MetaCLBench: Meta Continual Learning Benchmark on Resource-Constrained Edge Devices
por: Li, Sijia, et al.
Publicado: (2025)

Leveraging Knowledge Distillation for Efficient Deep Reinforcement Learning in Resource-Constrained Environments
por: Meng, Guanlin
Publicado: (2023)

FALQON: Accelerating LoRA Fine-tuning with Low-Bit Floating-Point Arithmetic
por: Choi, Kanghyun, et al.
Publicado: (2025)

Perturb-and-Compare Approach for Detecting Out-of-Distribution Samples in Constrained Access Environments
por: Lee, Heeyoung, et al.
Publicado: (2024)

Latent Bayesian Optimization via Autoregressive Normalizing Flows
por: Lee, Seunghun, et al.
Publicado: (2025)

STEER: Inference-Time Risk Control via Constrained Quality-Diversity Search
por: Yang, Eric, et al.
Publicado: (2026)

NNiT: Width-Agnostic Neural Network Generation with Structurally Aligned Weight Spaces
por: Kim, Jiwoo, et al.
Publicado: (2026)

LION-DG: Layer-Informed Initialization with Deep Gradient Protocols for Accelerated Neural Network Training
por: Kim, Hyunjun
Publicado: (2026)

Aligning Few-Step Generative Models by Amortizing Sample-based Variational Inference
por: Lee, Jaewoo, et al.
Publicado: (2026)

Protein Language Models Diverge from Natural Language: Comparative Analysis and Improved Inference
por: Hart, Anna, et al.
Publicado: (2026)