collaborators

6 papers

cs.SE2026

Towards Automated Formal Verification of zkEVMs Using LLM-Guided Constraint Synthesis

Shichen Huang, Zhenghe Jiang, Yi Jiang +3

Zero-Knowledge Ethereum Virtual Machines (zkEVMs) secure Ethereum rollups by generating zero-knowledge proofs that guarantee off-chain execution correctness. However, subtle implem…

cs.LG2026

MaxProof: Scaling Mathematical Proof with Generative-Verifier RL and Population-Level Test-Time Scaling

Jiacheng Chen, Xinyu Zhang, Shunkai Zhang +20

We present MaxProof, a population-level test-time scaling framework for competition-level mathematical proof in the MiniMax-M3 series. M3 first trains three proof-oriented capabili…

cs.AI2026

Probabilistic Verification of Neural Networks via Efficient Probabilistic Hull Generation

Jingyang Li, Xin Chen, Hongfei Fu +1

The problem of probabilistic verification of a neural network investigates the probability of satisfying the safe constraints in the output space when the input is given by a proba…

cs.SE2026

Counterexample Guided Branching via Directional Relaxation Analysis in Complete Neural Network Verification

Jingyang Li, Fu Song, Guoqiang Li

Deep Neural Networks demonstrate exceptional performance but remain vulnerable to adversarial perturbations, necessitating formal verification for safety-critical deployment. To ad…

cs.SE2026

SimCert: Probabilistic Certification for Behavioral Similarity in Deep Neural Network Compression

Jingyang Li, Fu Song, Guoqiang Li

Deploying Deep Neural Networks (DNNs) on resource-constrained embedded systems requires aggressive model compression techniques like quantization and pruning. However, ensuring tha…

cs.LG2025

MUC-G4: Minimal Unsat Core-Guided Incremental Verification for Deep Neural Network Compression

Jingyang Li, Guoqiang Li

The rapid development of deep learning has led to challenges in deploying neural networks on edge devices, mainly due to their high memory and runtime complexity. Network compressi…