Selected work

Representative Papers

SafeGen: LLM-Driven Assertion Generation and Fault Criticality Evaluation for Functional Safety

Jun 23, 2026

This work addresses the limitations of traditional simulation-based approaches in module-level fault analysis, which are often overly conservative and unable to accurately assess functional safety impacts. The authors propose SafeGen, a novel framework that integrates large language models (LLMs) with document-level hyperknowledge graphs (HyperKGs) to automatically extract verifiable specifications from design and safety documentation, generating semantically precise, design-aware functional safety assertions. By mapping gate-level faults to RTL and leveraging formal property verification (FPV), SafeGen enables semantic-level criticality classification for stuck-at and bridging faults, while supporting end-to-end traceable reasoning across specifications, assertions, and faults. Experimental evaluation on a field-oriented control (FOC) platform demonstrates that the generated assertions outperform those from existing LLM-based methods in quality and provide more semantically interpretable criticality assessments.

0 citationsRead paper

Inference-Time Code Selection via Symbolic Equivalence Partitioning

Apr 07, 2026

This work addresses the limitations of existing Best-of-N code generation approaches, which rely on costly or stochastic external verifiers to identify correct solutions. The authors propose a symbolic equivalence partitioning framework that leverages symbolic execution to group candidate programs by semantic behavior and integrates SMT-encoded domain constraints to refine these partitions. By selecting representative programs from dominant functional clusters, the method improves selection accuracy without requiring additional LLM inference, while simultaneously mitigating path explosion and restricting the search over invalid inputs. Experimental results demonstrate consistent gains: on HumanEval+, average pass@10 accuracy improves from 0.728 to 0.803, and on LiveCodeBench, it rises from 0.516 to 0.604.

0 citationsRead paper

SARL: Label-Free Reinforcement Learning by Rewarding Reasoning Topology

Mar 29, 2026

This work addresses the challenge of reward scarcity in open-domain reasoning, where ambiguous answers often preclude reliable supervision signals for reinforcement learning. To overcome this limitation, the authors propose Structure-Aware Reinforcement Learning (SARL), which innovatively incorporates the small-world properties of complex networks into the reinforcement learning framework. SARL constructs a topological Reasoning Map of inference paths and leverages its local clustering and global efficient connectivity as an unsupervised reward signal, thereby shifting the training paradigm from outcome-oriented to process-oriented. Implemented with PPO/GRPO algorithms on Qwen3-4B, SARL substantially outperforms existing baselines, achieving performance gains of 9.1%–11.6% on mathematical reasoning tasks and 30.4%–34.6% on open-domain tasks, while simultaneously exhibiting lower KL divergence and higher policy entropy.

0 citationsRead paper

Wireless Home Automation Using Social Networking Websites

Jun 23, 2025

Wireless home automation systems (WHAS) suffer from weak security, heterogeneous multi-device control complexity, and poor user interaction. To address these challenges, this paper proposes a novel WHAS architecture integrating social-network-based identity authentication and behavioral sensing. Specifically, it pioneers the fusion of OAuth 2.0—leveraged from platforms such as Twitter—with users’ temporal and frequency-based social-behavioral patterns (e.g., posting habits) to establish a lightweight, verifiable remote device control framework. The system employs API integration, low-power wireless protocols (Wi-Fi/Bluetooth), and real-time behavioral monitoring algorithms to ensure end-to-end secure and controllable home device operations. Experimental evaluation demonstrates that the approach maintains strong authentication assurance while significantly improving usability: misoperation rate decreases by 37% compared to conventional password- or app-based authentication, with average response latency under 800 ms. This work introduces a new trust anchor for identity verification in smart homes and establishes a human-centered interaction paradigm.

0 citationsRead paper

Dual Dielectric Metasurface for Simultaneous Sensing and Reconfigurable Reflections

Jan 23, 2025

To address the limitations of conventional reconfigurable intelligent surfaces (RISs)—namely, passive-only reflection and poor integration of communication and sensing—this paper proposes a dual-functional hybrid RIS (HRIS). The HRIS introduces a novel co-located dual-element metasurface architecture featuring a shared phase center, integrating an interleaved sensing array with orthogonal polarizations and a quarter-wavelength spatial offset to enable native fusion of communication reflection and channel sensing at a subwavelength scale (λ/8). Leveraging a dual-dielectric metasurface, split-ring reflectarrays, and a tunable load matrix, the HRIS supports real-time dual-node channel parameter estimation and dynamic beam steering. Full-wave simulations at 5.5 GHz demonstrate a reflection efficiency exceeding 90%, a sensing resolution of λ/2, channel parameter estimation errors below 5%, and significant antenna size reduction.

0 citationsRead paper

Recent publications

Latest Papers

SafeGen: LLM-Driven Assertion Generation and Fault Criticality Evaluation for Functional Safety

Jun 23, 2026

This work addresses the limitations of traditional simulation-based approaches in module-level fault analysis, which are often overly conservative and unable to accurately assess functional safety impacts. The authors propose SafeGen, a novel framework that integrates large language models (LLMs) with document-level hyperknowledge graphs (HyperKGs) to automatically extract verifiable specifications from design and safety documentation, generating semantically precise, design-aware functional safety assertions. By mapping gate-level faults to RTL and leveraging formal property verification (FPV), SafeGen enables semantic-level criticality classification for stuck-at and bridging faults, while supporting end-to-end traceable reasoning across specifications, assertions, and faults. Experimental evaluation on a field-oriented control (FOC) platform demonstrates that the generated assertions outperform those from existing LLM-based methods in quality and provide more semantically interpretable criticality assessments.

0 citationsRead paper

Inference-Time Code Selection via Symbolic Equivalence Partitioning

Apr 07, 2026

This work addresses the limitations of existing Best-of-N code generation approaches, which rely on costly or stochastic external verifiers to identify correct solutions. The authors propose a symbolic equivalence partitioning framework that leverages symbolic execution to group candidate programs by semantic behavior and integrates SMT-encoded domain constraints to refine these partitions. By selecting representative programs from dominant functional clusters, the method improves selection accuracy without requiring additional LLM inference, while simultaneously mitigating path explosion and restricting the search over invalid inputs. Experimental results demonstrate consistent gains: on HumanEval+, average pass@10 accuracy improves from 0.728 to 0.803, and on LiveCodeBench, it rises from 0.516 to 0.604.

0 citationsRead paper

SARL: Label-Free Reinforcement Learning by Rewarding Reasoning Topology

Mar 29, 2026

This work addresses the challenge of reward scarcity in open-domain reasoning, where ambiguous answers often preclude reliable supervision signals for reinforcement learning. To overcome this limitation, the authors propose Structure-Aware Reinforcement Learning (SARL), which innovatively incorporates the small-world properties of complex networks into the reinforcement learning framework. SARL constructs a topological Reasoning Map of inference paths and leverages its local clustering and global efficient connectivity as an unsupervised reward signal, thereby shifting the training paradigm from outcome-oriented to process-oriented. Implemented with PPO/GRPO algorithms on Qwen3-4B, SARL substantially outperforms existing baselines, achieving performance gains of 9.1%–11.6% on mathematical reasoning tasks and 30.4%–34.6% on open-domain tasks, while simultaneously exhibiting lower KL divergence and higher policy entropy.

0 citationsRead paper

Wireless Home Automation Using Social Networking Websites

Jun 23, 2025

Wireless home automation systems (WHAS) suffer from weak security, heterogeneous multi-device control complexity, and poor user interaction. To address these challenges, this paper proposes a novel WHAS architecture integrating social-network-based identity authentication and behavioral sensing. Specifically, it pioneers the fusion of OAuth 2.0—leveraged from platforms such as Twitter—with users’ temporal and frequency-based social-behavioral patterns (e.g., posting habits) to establish a lightweight, verifiable remote device control framework. The system employs API integration, low-power wireless protocols (Wi-Fi/Bluetooth), and real-time behavioral monitoring algorithms to ensure end-to-end secure and controllable home device operations. Experimental evaluation demonstrates that the approach maintains strong authentication assurance while significantly improving usability: misoperation rate decreases by 37% compared to conventional password- or app-based authentication, with average response latency under 800 ms. This work introduces a new trust anchor for identity verification in smart homes and establishes a human-centered interaction paradigm.

0 citationsRead paper

Dual Dielectric Metasurface for Simultaneous Sensing and Reconfigurable Reflections

Jan 23, 2025

To address the limitations of conventional reconfigurable intelligent surfaces (RISs)—namely, passive-only reflection and poor integration of communication and sensing—this paper proposes a dual-functional hybrid RIS (HRIS). The HRIS introduces a novel co-located dual-element metasurface architecture featuring a shared phase center, integrating an interleaved sensing array with orthogonal polarizations and a quarter-wavelength spatial offset to enable native fusion of communication reflection and channel sensing at a subwavelength scale (λ/8). Leveraging a dual-dielectric metasurface, split-ring reflectarrays, and a tunable load matrix, the HRIS supports real-time dual-node channel parameter estimation and dynamic beam steering. Full-wave simulations at 5.5 GHz demonstrate a reflection efficiency exceeding 90%, a sensing resolution of λ/2, channel parameter estimation errors below 5%, and significant antenna size reduction.

0 citationsRead paper