Skip to content

Research

Page 61 of 166

Xiaomi-GUI-0 Technical Report

research note

Xiaomi-GUI-0 Technical Report

·9 min read·Wanxia Cao, Chengzhen Duan, Pei Fu et al.

Xiaomi-GUI-0 addresses the persistent gap between the high benchmark performance of mobile GUI agents and their practical usability in real-world.

researchmobile-gui-agentsreal-device-trainingerror-driven-data-flywheelreinforcement-learning

Read note → Source paper ↗

A Multi-task Mixture of Experts Framework for Malware Classification, Packing Detection, and Family Attribution

research note

A Multi-task Mixture of Experts Framework for Malware Classification, Packing Detection, and Family Attribution

·8 min read·Jithin S., Roshin Sleeba C., Anvin Mariya P. B. et al.

This paper addresses the challenges of malware classification posed by heterogeneous malware data distributions, the presence of packed binaries, and diverse malware family characteristics

researchmalware-classificationmulti-task-learningmixture-of-expertsstatic-analysis

Read note → Source paper ↗

C$^{2}$R — Cross-sample Consistency Regularization Mitigates Feature Splitting and Absorption in Sparse Autoencoders

research note

C$^{2}$R — Cross-sample Consistency Regularization Mitigates Feature Splitting and Absorption in Sparse Autoencoders

·9 min read·Haoran Jin, Xiting Wang, Shijie Ren et al.

This paper addresses fundamental reliability issues in Sparse Autoencoders (SAEs) used to interpret large language model (LLM) activations by breaking them down into sparse, human-understandable fe…

researchsparse-autoencoderslatent-representationscross-sample-regularizationfeature-splitting

Read note → Source paper ↗

Articles are CC BY 4.0 — feel free to quote with attribution