Wei Cheng

LSKA: Location Similarity Based Key Agreement Scheme for Smartphone Networks

2016

With the recent popularization of smartphones, more attention has been given to design dynamic keys for smartphone communications. In this paper, we particularly work to meet the requirement of encrypted information sharing among closely located …

GeoGPT: Understanding and Processing Geospatial Tasks through An Autonomous GPT

2023 · arXiv (Cornell University)

Decision-makers in GIS need to combine a series of spatial algorithms and operations to solve geospatial tasks. For example, in the task of facility siting, the Buffer tool is usually first used to locate areas …

Strategist: Self-improvement of LLM Decision Making via Bi-Level Tree Search

2024 · arXiv (Cornell University)

Traditional reinforcement learning and planning typically requires vast amounts of data and training to develop effective policies. In contrast, large language models (LLMs) exhibit strong generalization and zero-shot capabilities, but struggle with tasks that require …

Attacking High-order Masked Cryptosystem via Deep Learning-based Side-Channel Analysis

2024

Masking is widely considered as an effective countermeasure against side-channel analysis (SCA) due to its provable security and efficiency. However, recent works have demonstrated that the deep learning-based SCA (DL-SCA) can effectively break the cryptographic …

MixLLM: Dynamic Routing in Mixed Large Language Models

2025

Xinyuan Wang, Yanchi Liu, Wei Cheng, Xujiang Zhao, Zhengzhang Chen, Wenchao Yu, Yanjie Fu, Haifeng Chen. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human …

DISC: Dynamic Decomposition Improves LLM Inference Scaling

2025 · arXiv (Cornell University)

Inference scaling methods for LLMs often rely on decomposing problems into steps (or groups of tokens), followed by sampling and selecting the best next steps. However, these steps and their sizes are often predetermined or …

Learning to Align, Aligning to Learn: A Unified Approach for Self-Optimized Alignment

2025 · arXiv (Cornell University)

Alignment methodologies have emerged as a critical pathway for enhancing language model alignment capabilities. While SFT (supervised fine-tuning) accelerates convergence through direct token-level loss intervention, its efficacy is constrained by offline policy trajectory. In contrast, …