You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
We propose a Circuit Program Evolution} framework, namely CircuitEvo, which iteratively leverages the large language models (LLMs) to evolve circuit programs to…
MIRALab-USTC/LLM-AnDPro’s past year of commit activity
This is the code of our paper "Accurate KV Cache Eviction via Anchor Direction Projection for Efficient LLM Inference", which has been accepted by NeurIPS 2025.
The code for "AttentionPredictor: Temporal Pattern Matters for Efficient LLM Inference", Qingyue Yang, Jie Wang, Xing Li, Zhihai Wang, Chen Chen, Lei Chen, Xian…
The code for "Apollo-MILP: An Alternating Prediction-Correction Neural Solving Framework for Mixed-Integer Linear Programming", Haoyang Liu, Jie Wang, Zijie Gen…
This is the code of paper "De Novo Molecular Generation via Connection-aware Motif Mining". Zijie Geng, Shufang Xie, Yingce Xia, Lijun Wu, Tao Qin, Jie Wang, Yo…