19 citations · 26 across the 6 of their papers we have counts for
7 papers
AutoDFT: A Closed-Loop Multi-Agent Framework for Autonomous DFT Calculations
Penghui Yang, Zhonghan Zhang, Yue Li +6
Density functional theory (DFT) serves as the basis for computational discovery in materials science and chemistry, yet each calculation demands extensive human effort: adjusting a…
MATAI: A Generalist Machine Learning Framework for Property Prediction and Inverse Design of Advanced Alloys
Yanchen Deng, Chendong Zhao, Yixuan Li +10
The discovery of advanced metallic alloys is hindered by vast composition spaces, competing property objectives, and real-world constraints on manufacturability. Here we introduce…
Sailor2: Sailing in South-East Asia with Inclusive Multilingual LLMs
Longxu Dou, Qian Liu, Fan Zhou +38
Sailor2 is a family of cutting-edge multilingual language models for South-East Asian (SEA) languages, available in 1B, 8B, and 20B sizes to suit diverse applications. Building on…
LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification
Penghui Yang, Cunxiao Du, Fengzhuo Zhang +4
As Large Language Models (LLMs) can now process extremely long contexts, efficient inference over these extended inputs has become increasingly important, especially for emerging a…
Dual-Head Knowledge Distillation: Enhancing Logits Utilization with an Auxiliary Head
Penghui Yang, Chen-Chen Zong, Sheng-Jun Huang +2
Traditional knowledge distillation focuses on aligning the student's predicted probabilities with both ground-truth labels and the teacher's predicted probabilities. However, the t…
FLAIN: Mitigating Backdoor Attacks in Federated Learning via Flipping Weight Updates of Low-Activation Input Neurons
Binbin Ding, Penghui Yang, Sheng-Jun Huang
Federated learning (FL) enables multiple clients to collaboratively train machine learning models under the coordination of a central server, while maintaining privacy. However, th…
Multi-Label Knowledge Distillation
Penghui Yang, Ming-Kun Xie, Chen-Chen Zong +4
Existing knowledge distillation methods typically work by imparting the knowledge of output logits or intermediate feature maps from the teacher network to the student network, whi…