Real-Time Spacecraft Pose Estimation Using Mixed-Precision Quantized Neural Network on COTS Reconfigurable MPSoCby Julien Posso,…
ZOBNN: Zero-Overhead Dependable Design of Binary Neural Networks with Deliberately Quantized Parametersby Behnam Ghavami, Mohammad…
OvSW: Overcoming Silent Weights for Accurate Binary Neural Networksby Jingyang Xiang, Zuohui Chen, Siqi Li,…
CLAMP-ViT: Contrastive Data-Free Learning for Adaptive Post-Training Quantization of ViTsby Akshat Ramachandran, Souvik Kundu, Tushar…
Unified Anomaly Detection methods on Edge Device using Knowledge Distillation and Quantizationby Sushovan Jena, Arya…
Deep Fusion Model for Brain Tumor Classification Using Fine-Grained Gradient Preservationby Niful Islam, Mohaiminul Islam…
Q-DiT: Accurate Post-Training Quantization for Diffusion Transformersby Lei Chen, Yuan Meng, Chen Tang, Xinzhu Ma,…
Compensate Quantization Errors: Make Weights Hierarchical to Compensate Each Otherby Yifei Gao, Jie Ou, Lei…
Pruning via Merging: Compressing LLMs via Manifold Alignment Based Layer Mergingby Deyuan Liu, Zhanyue Qin,…
How Many Parameters Does it Take to Change a Light Bulb? Evaluating Performance in Self-Play…