Ming-Qiao Mo

Code Consistency Preference Optimization Verification for Language Model Alignment

This work proposes a method that generates computationally sound solutions with dependency graphs for execution-consistent preference optimization, and achieves 50.1% accuracy on PhyX multimodal physics reasoning, surpassing DeepSeek-R1 and OpenAI o3-mini.

CompileRover: Revolutionizing Virtual Machine Compiler Optimization with a Tri-Role LLM-Driven Framework

CompileRover employs a sophisticated three-role collaboration mechanism, comprising a referee, an advisor, and an operator, effectively overcoming performance bottlenecks by leveraging comprehensive optimization algorithms and novel methodologies, including control flow analysis, code structure transformations, and dyn...

Though Language Models Err While They Strive: Conformal Prediction for Self-Correcting Scientific Generation

Scientific Feasibility Control SFC is introduced, a graph-structured conformal prediction framework that provides statistical guarantees for scientific reasoning validity through progressive absolute-coherent-factuality validation and decomposes scientific reasoning into atomic absolute-coherent-factuality units.

Dependency-Guided Code Generation: Structured Matrix Decomposition and Consistency-Guided Refinement

This work proposes a dependency-aware code generation framework that explicitly models interactions among code entities through a graph-based representation, and introduces a sparse triplet representation for strong dependencies, significantly improving storage efficiency and computational scalability.

PathSymphony: Harmonizing symbolic planning and Large Language Models for curriculum-guided mathematical reasoning