논문 리뷰
1.On-Device Training Under 256KB Memory
On-Device Training Under 256KB Memory 논문에 대하여 ...
2.Edge AI: On-Demand Accelerating Deep Neural Network Inference via Edge Computing
Edge AI: On-Demand Accelerating Deep Neural Network Inference via Edge Computing 논문에 대하여...
3.Group Normalization
Group Normalization 논문에 대하여...
4.TinyTL
TinyTL 논문에 관하여...
5.LLM-QAT: Data-Free Quantization Aware Training for Large Language Models
LLM-QAT: Data-Free Quantization Aware Training for Large Language Models 논문에 대하여...
6.SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models
SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models 논문에 대하여...
7.A Survey of Quantization Methods for Efficient Neural Network Inference
A Survey of Quantization Methods for Efficient Neural Network Inference 논문에 대하여...
8.BinaryViT: Pushing Binary Vision Transformers Towards Convolutional Models
BinaryViT: Pushing Binary Vision Transformers Towards Convolutional Models 논문에 대하여...
9.SpecEE: Accelerating Large Language Model Inference with Speculative Early Exiting
SpecEE: Accelerating Large Language Model Inference with Speculative Early Exiting 논문에 대하여...
10.Mix-QViT: Mixed-Precision Vision Transformer Quantization Driven by Layer Importance and Quantization Sensitivity
Mix-QViT: Mixed-Precision Vision Transformer Quantization Driven by Layer Importance and Quantization Sensitivity 논문에 대하여...
11.Explaining NonLinear Classification Decisions with Deep Taylor Decomposition
Explaining NonLinear Classification Decisions with Deep Taylor Decomposition 논문에 대하여...
12.MPQ via Learned Layer-wise Importance
Mixed-Precision Neural Network Quantization via Learned Layer-wise Importance에 대하여...
13.PACT: PARAMETERIZED CLIPPING ACTIVATION FOR QUANTIZED NEURAL NETWORKS
PACT에 관하여...
14.Post-Training Quantization for Vision Transformer
Post-Training Quantization for Vision Transformer 논문에 관하여...
15.PTQ4ViT
Ptq4vit: Post-training quantization for vision transformers with twin uniform quantization 논문에 관하여...
16.FQ-ViT: Post-Training Quantization for Fully Quantized Vision Transformer
FQ-ViT: Post-Training Quantization for Fully Quantized Vision Transformer 논문에 대하여...
17.APQ-ViT: Towards Accurate Post-Training Quantization for Vision Transformer
APQ-ViT: Towards Accurate Post-Training Quantization for Vision Transformer 논문에 대하여...
18.RepQ-ViT: Scale Reparameterization for Post-Training Quantization of Vision Transformers
RepQ-ViT: Scale Reparameterization for Post-Training Quantization of Vision Transformers 논문에 대하여...
19.Hierarchical Reasoning Model
Hierarchical Reasoning Model 논문에 대하여...
20.Less is More: Recursive Reasoning with Tiny Networks
TRM에 대한 내용TRM은 HRM보다 훨씬 더 단순한 재귀적 추론 접근 방식으로, 단 2개의 레이어만 가진 하나의 초소형 네트워크를 사용하면서도 HRM보다 훨씬 더 높은 일반화 성능을 달성.HRM: 27MTRM: 7M1) recursive hierarchical rea
21.Early-Exit Deep Neural Network - A Comprehensive Survey
Early-Exit Deep Neural Network - A Comprehensive Survey 논문에 대하여...
22.Relaxed Recursive Transformers: Effective Parameter Sharing with Layer-wise LoRA
Relaxed Recursive Transformers: Effective Parameter Sharing with Layer-wise LoRA Relaxed RT에 대한 내용 Abstract Contribution 기존 weight unshared model로
23.Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation
Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation 논문에 대하여...
24.DINOv3
DINOv3 논문에 대하여...