3 papers
cs.CV2026
Energy-Driven Adaptive Visual Token Pruning for Efficient Vision-Language Models
Jialuo He, Huangxun Chen
Visual token reduction is critical for accelerating Vision-Language Models (VLMs), since visual inputs are represented as token sequences that introduce substantial computational o…
cs.CV2026
Towards Compact and Robust DNNs via Compression-aware Sharpness Minimization
Jialuo He, Huangxun Chen
Sharpness-Aware Minimization (SAM) has recently emerged as an effective technique for improving DNN robustness to input variations. However, its interplay with the compactness requ…
cs.LG2024
FedAA: A Reinforcement Learning Perspective on Adaptive Aggregation for Fair and Robust Federated Learning
Jialuo He, Wei Chen, Xiaojin Zhang
Federated Learning (FL) has emerged as a promising approach for privacy-preserving model training across decentralized devices. However, it faces challenges such as statistical het…