12 papers
Fast-Slow Efficient Training for Multimodal Large Language Models via Visual Token Pruning
Dingkun Zhang, Shuhan Qi, Yulin Wu +3
Multimodal Large Language Models (MLLMs) suffer from severe training inefficiency issue, which is associated with their massive model sizes and visual token numbers. Existing effor…
Efficient Last-Iterate Convergence in Regret Minimization via Adaptive Reward Transformation
Hang Ren, Yulin Wu, Shuhan Qi +4
Regret minimization is a powerful method for finding Nash equilibria in Normal-Form Games (NFGs) and Extensive-Form Games (EFGs), but it typically guarantees convergence only for t…
MKDTI: Predicting drug-target interactions via multiple kernel fusion on graph attention network
Yuhuan Zhou, Yulin Wu, Weiwei Yuan +2
Drug-target relationships may now be predicted computationally using bioinformatics data, which is a valuable tool for understanding pharmacological effects, enhancing drug develop…
KnobTree: Intelligent Database Parameter Configuration via Explainable Reinforcement Learning
Jiahan Chen, Shuhan Qi, Yifan Li +4
Databases are fundamental to contemporary information systems, yet traditional rule-based configuration methods struggle to manage the complexity of real-world applications with hu…
Determining the upper bound of code distance of quantum stabilizer codes through Monte Carlo method based on fully decoupled belief propagation
Zhipeng Liang, Zicheng Wang, Zhengzhong Yi +3
Code distance is an important parameter for quantum stabilizer codes (QSCs). Directly precisely computing it is an NP-complete problem. However, the upper bound of code distance ca…
Recursive expansion of Tanner graph: a method to construct stabilizer codes with high coding rate
Zhengzhong Yi, Zhipeng Liang, Zicheng Wang +4
Quantum stabilizer codes face the problem of low coding rate. In this article, following the idea of recursively expanding Tanner graph proposed in our previous work, we try to con…
A Generic Multi-Player Transformation Algorithm for Solving Large-Scale Zero-Sum Extensive-Form Adversarial Team Games
Chen Qiu, Yulin Wu, Weixin Huang +3
Many recent practical and theoretical breakthroughs focus on adversarial team multi-player games (ATMGs) in ex ante correlation scenarios. In this setting, team members are allowed…
Improved belief propagation decoding algorithm based on decoupling representation of Pauli operators for quantum LDPC codes
Zhengzhong Yi, Zhipeng Liang, Kaixin Zhong +3
We propose a new method called decoupling representation to represent Pauli operators as vectors over , based on which we propose partially decoupled belief propagation and…
Privacy-Preserving Distributed Machine Learning Made Faster
Zoe L. Jiang, Jiajing Gu, Hongxiao Wang +5
With the development of machine learning, it is difficult for a single server to process all the data. So machine learning tasks need to be spread across multiple servers, turning…
Quantum polar stabilizer codes based on polarization of pure quantum channel don't work for quantum computing
Zhengzhong Yi, Zhipeng Liang, Yulin Wu +1
Inspired by classical polar codes, whose coding rate can asymptotically achieve the Shannon capacity, researchers are trying to find its analogue in quantum information field, whic…
Improved Polar-code-based Efficient Post-processing Algorithm for Quantum Key Distribution
Junbing Fang, Zhengzhong Yi, Jin Li +5
Combined with one-time pad encryption scheme, quantum key distribution guarantees the unconditional security of communication in theory. However, error correction and privacy ampli…
RLCFR: Minimize Counterfactual Regret by Deep Reinforcement Learning
Huale Li, Xuan Wang, Fengwei Jia +4
Counterfactual regret minimization (CFR) is a popular method to deal with decision-making problems of two-player zero-sum games with imperfect information. Unlike existing studies…