影响力指数
论文质量、代表作、近期表现、广度与样本量置信度综合计算
42.3/100
前 12.8%
全站排名 #8,255
发表论文14 篇
平均评分
年均产出4.7 篇/年
Geng Yuan
研究方向
Sparse training · Energy-efficient deep learning and artificial intelligence systems · Hardware-software co-design for DNN architectures · Emerging devices · DNN model compression · DNN acceleration
11
RFD-LoRA: Robust Federated Distillation for LoRA Fine-Tuning under Heterogeneous and Adversarial Clients
ICLR 2026Rejected
三作14
Forget-It-All: Multi-Concept Machine Unlearning via Concept-Aware Neuron Masking
ICLR 2026Rejected
4
ACE: Exploring Activation Variance for Accurate and Calibration-Efficient LLM Pruning
ICLR 2026Withdrawn
三作11
KerZOO: Kernel Function Informed Zeroth-Order Optimization for Accurate and Accelerated LLM Fine-Tuning
ICLR 2026Desk Rejected
6
From Bits to Chips: An LLM-based Hardware-Aware Quantization Agent for Streamlined Deployment of LLMs
ICLR 2026Rejected
6
Bridging Bag-Level and Instance-Level Uncertainty with Conformalizable MIL
ICLR 2026Rejected
4
Towards Fast LLM Fine-tuning through Zeroth-Order Optimization with Projected Gradient-Aligned Perturbations
ICLR 2026Withdrawn
4
Advancing Physiological Time Series Reconstruction and Imputation via Mixture of Receptive Fields and Experts Fusion
ICLR 2026Withdrawn
通讯5
End-to-End On-Device Quantization-Aware Training for LLMs at Inference Cost
ICLR 2026Withdrawn
通讯