arXiv subjects

Zihan Dai

Publications and source records attributed to Zihan Dai.

4 recordsLinked to original sources

arXiv2026

TopoEdge: Topology-Grounded Agentic Framework for Edge Networking Code Generation and Repair

TopoEdge is a topology-grounded, edge-deployable framework for end-to-end software-defined networking (SDN) configuration generation and repair, motivated by the brittleness of configuration artefacts under topology variation and by strict operational constraints on latency, privacy, and on-site execution. TopoEdge represents each target topology as a router-level graph and embeds it using a contrastively trained graph neural network (GNN), enabling nearest-neighbour retrieval of a verified reference configuration paired with an executable Python driver (a Topotest/pytest test script that orchestrates the emulated network and checks protocol assertions). The target topology, retrieved reference topology, and reference driver are assembled into a topology-grounded retrieval-augmented generation context (TopoRAG), which grounds a distributed, execution-centric generate--verify--repair loop coordinated by a central controller and realised by three role-specialised agents: (i) a Planning agent that produces a topology-consistent configuration plan and a per-device skeleton; (ii) a Generation agent that materialises executable configuration artefacts, including device configurations and the driver; and (iii) a Verification agent that runs the FRRouting Topotest/pytest harness, compresses failures into a compact trace, and emits localised patch directives for iterative repair.

cs.SE↗

arXiv2025

Governance-Aware Hybrid Fine-Tuning for Multilingual Large Language Models

We present a governance-aware hybrid fine-tuning framework for multilingual, low-resource adaptation of large language models. The core algorithm combines gradient-aligned low-rank updates with structured orthogonal transformations through layer-wise mixing and introduces unitary constraints in selected sub-layers to stabilize deep optimization. In tandem with lightweight, label-free data governance steps, including language identification, near-duplicate removal, and quality filtering, the framework targets accuracy, calibration, and cross-language parity under tight compute budgets. Across XNLI and FLORES, the hybrid approach delivers consistent gains over strong PEFT baselines while maintaining directional balance and improving probability calibration, as shown in Tables II and III. It is more resilient to lightweight orthographic variants, as shown in Table IV, and benefits additively from simple governance steps, as shown in Table V. Training footprint measurements indicate modest overhead and a favorable cost-quality frontier, as shown in Table VI and Figure 2. Together, these results show that hybrid and unitary PEFT provide a stable and accessible path to resource-efficient multilingual adaptation when paired with practical data governance.

cs.CL↗

arXiv2025

Hybrid and Unitary PEFT for Resource-Efficient Large Language Models

Fine-tuning large language models (LLMs) remains a computational bottleneck due to their scale and memory demands. This paper presents a comprehensive evaluation of parameter-efficient fine-tuning (PEFT) techniques, including LoRA, BOFT, LoRA-GA, and uRNN, and introduces a novel hybrid strategy that dynamically integrates BOFT's orthogonal stability with LoRA-GA's gradient-aligned rapid convergence. By computing per-layer adaptive updates guided by gradient norms, the hybrid method achieves superior convergence efficiency and generalization across diverse tasks. We also explore, for the first time, the adaptation of unitary RNN (uRNN) principles to Transformer-based LLMs, enhancing gradient stability through structured unitary constraints. Across GLUE, GSM8K, MT-Bench, and HumanEval, using models ranging from 7B to 405B parameters, the hybrid approach yields consistent gains across three independent runs per task and model, approaching the quality of full fine-tuning while reducing training time by approximately 2.1 times and peak memory usage by nearly 50 percent, indicating practical significance under resource constraints. A compact multilingual and low-resource study on XNLI and FLORES, using 32 examples per language, further demonstrates consistent gains under the same budget with a small and stable footprint. These results indicate a practical and scalable path toward accessible LLM fine-tuning under resource constraints.

cs.CL↗

arXiv2025

Spiking Neural Networks with Random Network Architecture

The spiking neural network, known as the third generation neural network, is an important network paradigm. Due to its mode of information propagation that follows biological rationality, the spiking neural network has strong energy efficiency and has advantages in complex high-energy application scenarios. However, unlike the artificial neural network (ANN) which has a mature and unified framework, the SNN models and training methods have not yet been widely unified due to the discontinuous and non-differentiable property of the firing mechanism. Although several algorithms for training spiking neural networks have been proposed in the subsequent development process, some fundamental issues remain unsolved. Inspired by random network design, this work proposes a new architecture for spiking neural networks, RanSNN, where only part of the network weights need training and all the classic training methods can be adopted. Compared with traditional training methods for spiking neural networks, it greatly improves the training efficiency while ensuring the training performance, and also has good versatility and stability as validated by benchmark tests.

cs.NE↗