7 papers
Though Language Models Err While They Strive: Conformal Prediction for Self-Correcting Scientific Generation
Mingqiao Mo, Yunlong Tan, Hao Zhang
Large language models frequently violate fundamental scientific principles when generating technical content, undermining their reliability in scientific applications. We introduce…
Dependency-Guided Code Generation: Structured Matrix Decomposition and Consistency-Guided Refinement
Mingqiao Mo, Yangchen Zeng, Zikai Xiao +7
The increasing complexity of modern software systems has made automated code generation a fundamental task in software engineering. However, existing approaches often fail to adequ…
BlockPilot: Instance-Adaptive Policy Learning for Diffusion-based Speculative Decoding
Hao Zhang, Yiming Hu, Yong Wang +3
Speculative decoding accelerates inference by using a lightweight draft model to generate candidate tokens in parallel, and are then verified by the target model, enabling lossless…
SafeMind: A Risk-Aware Differentiable Control Framework for Adaptive and Safe Quadruped Locomotion
Zukun Zhang, Kai Shu, Mingqiao Mo
Learning-based quadruped controllers achieve impressive agility but typically lack formal safety guarantees under model uncertainty, perception noise, and unstructured contact cond…
ShieldedCode: Learning Robust Representations for Virtual Machine Protected Code
Mingqiao Mo, Yunlong Tan, Hao Zhang +2
Large language models (LLMs) have achieved remarkable progress in code generation, yet their potential for software protection remains largely untapped. Reverse engineering continu…
Self-Supervised Visual Prompting for Cross-Domain Road Damage Detection
Xi Xiao, Zhuxuanzi Wang, Mingqiao Mo +6
The deployment of automated pavement defect detection is often hindered by poor cross-domain generalization. Supervised detectors achieve strong in-domain accuracy but require cost…