arXiv subjects

Zhengtong Li

Publications and source records attributed to Zhengtong Li.

3 recordsLinked to original sources

arXiv2026

LLM-Viterbi: Semantic-Aware Decoding for Convolutional Codes

Traditional wireless communications rely solely on bit-level channel coding for error correction, without exploiting the inherent linguistic structure of the data source. This paper proposes a large language model (LLM) Viterbi decoder that integrates LLM priors into the Viterbi decoding for text transmission over AWGN channels. The proposed decoder maintains multiple candidate paths during the Viterbi decoding and periodically evaluates path reliabilities using a fine-tuned Byte-level T5 (ByT5) language model. By combining channel reliability metrics with semantic probability from the LLM, it outputs the path that maximizes the joint likelihood of channel observations and linguistic coherence. Simulations show that our decoder achieves significant performance gains over conventional Viterbi decoding in terms of both block error rate (BLER) and semantic similarity. For convolutional codes with constraint length 3, it achieves approximately 1.5 dB more coding gain in BLER, with over 50% improvements in semantic similarity. The framework can extend to other structured data sources beyond text.

cs.IT↗

arXiv2026

PhyNiKCE: A Neurosymbolic Agentic Framework for Autonomous Computational Fluid Dynamics

The deployment of autonomous agents for Computational Fluid Dynamics (CFD), is critically limited by the probabilistic nature of Large Language Models (LLMs), which struggle to enforce the strict conservation laws and numerical stability required for physics-based simulations. Reliance on purely semantic Retrieval Augmented Generation (RAG) often leads to "context poisoning," where agents generate linguistically plausible but physically invalid configurations due to a fundamental Semantic-Physical Disconnect. To bridge this gap, this work introduces PhyNiKCE (Physical and Numerical Knowledgeable Context Engineering), a neurosymbolic agentic framework for trustworthy engineering. Unlike standard black-box agents, PhyNiKCE decouples neural planning from symbolic validation. It employs a Symbolic Knowledge Engine that treats simulation setup as a Constraint Satisfaction Problem, rigidly enforcing physical constraints via a Deterministic RAG Engine with specialized retrieval strategies for solvers, turbulence models, and boundary conditions. Validated through rigorous OpenFOAM experiments on practical, non-tutorial CFD tasks using Gemini-2.5-Pro/Flash, PhyNiKCE demonstrates a 96% relative improvement over state-of-the-art baselines. Furthermore, by replacing trial-and-error with knowledge-driven initialization, the framework reduced autonomous self-correction loops by 59% while simultaneously lowering LLM token consumption by 17%. These results demonstrate that decoupling neural generation from symbolic constraint enforcement significantly enhances robustness and efficiency. While validated on CFD, this architecture offers a scalable, auditable paradigm for Trustworthy Artificial Intelligence in broader industrial automation.

cs.AI↗

arXiv2019

Efficient Interfacial Solar Steam Generator with Controlled Macromorphology Derived from Flour via "Dough Figurine" Technology

Solar-driven interface steam generator (SISG) is a most promising technology for seawater desalination and wastewater purification. A shape- and size-controlled, low-cost, eco-friendly solar-absorber material is urgently desired for practical application of SISG. Herein, we proposed a facile, sustainable and scalable approach to produce tailored SISG with controlled macromorphology derived from flour via "dough figurine" technology which is originated from the China Han Dynasty. Three kinds of self-floated flour-based absorbers i.e. near-cylindrical (integrated), near-spherical (loose packing) and powdery (dense packing) absorber used as SISGs were discussed, we found that the macromorphology significantly influences water transport and interfacial thermal management of SISG, the integrated absorber has an overwhelming advantage, which possesses a high evaporation efficiency 71.9% at normal solar illumination. The proposed "dough figurine" technology breaks the limitations of the inherent geometry of reported biomass based SISG, which provides an important guidance for SISG use in remote and impoverished areas.

physics.app-ph↗