arXiv subjects

Jiarui Ma

Publications and source records attributed to Jiarui Ma.

4 recordsLinked to original sources

arXiv2026

NetlistBench: Evaluating LLM Reliability in SPICE Netlist Recognition and Manipulation

Large Language Models (LLMs) are increasingly used in circuit design workflows, yet their reliability on simulator-facing SPICE netlist recognition and manipulation remains poorly understood and is rarely separated from high-level design reasoning. Although netlists are textual, they encode structured circuit objects through topology and parameters. We present \textbf{NetlistBench}, a structure-verified benchmark for SPICE netlist recognition and manipulation. NetlistBench contains 2,342 cases across 24 task families, covering parameter and connectivity recognition and edits, hierarchical operations, equivalence judgment, and long-horizon compound editing. Model outputs are evaluated by a deterministic structure-aware oracle. Across six non-thinking LLMs, performance varies substantially with operation-level structural complexity. Simple local edits reach $96\%$--$100\%$ accuracy, while device addition drops to $41\%$--$83\%$ and equivalence judgment to $49\%$--$90\%$. Enabling reasoning substantially improves weaker models but does not eliminate structure-preservation failures, with performance still degrading sharply as the edit horizon increases. NetlistBench identifies netlist reliability as a distinct bottleneck for trustworthy LLM-based circuit design automation.

eess.SY↗

arXiv2025

Average AoI in Pinching Antenna-assisted WPCNs with Probabilistic LoS Blockage

This paper analyzes the age of information (AoI) for a pinching antenna (PA)-assisted wireless powered communication network (WPCN) with probabilistic line-of-sight (LoS) blockage. AoI is a key metric for evaluating the freshness of status updates in IoT networks, and its optimization is crucial for ensuring the performance of time-critical applications. To facilitate analysis and gain useful insights, we consider a representative scenario, where an IoT device harvests energy from a base station (BS) equipped with a PA and transmits data packets to it. The IoT device harvests energy via the PA until its capacitor is fully charged, then transmits status updates using all stored energy. We derive closed-form expressions for the average AoI by analyzing the capacitor charging time, transmission success probability, and inter-arrival time of successful updates. To minimize the average AoI, we formulate an optimization problem of PA position, and propose a one-dimensional search to solve it. The simulation results show that the optimal PA position is the one closest to the IoT device, and this conclusion can be extended to the multi-IoT devices frequency division multiple access (FDMA) scenario. The PA-based systems significantly outperform the conventional fixed-antenna systems.

cs.IT↗

arXiv2025

LLM-empowered Dynamic Prompt Routing for Vision-Language Models Tuning under Long-Tailed Distributions

Pre-trained vision-language models (VLMs), such as CLIP, have demonstrated impressive capability in visual tasks, but their fine-tuning often suffers from bias in class-imbalanced scene. Recent works have introduced large language models (LLMs) to enhance VLM fine-tuning with supplementing semantic information. However, they often overlook inherent class imbalance in VLMs' pre-training, which may lead to bias accumulation in downstream tasks. To address this problem, this paper proposes a Multi-dimensional Dynamic Prompt Routing (MDPR) framework. MDPR constructs a comprehensive knowledge base for classes, spanning five visual-semantic dimensions. During fine-tuning, the dynamic routing mechanism aligns global visual classes, retrieves optimal prompts, and balances fine-grained semantics, yielding stable predictions through logits fusion. Extensive experiments on long-tailed benchmarks, including CIFAR-LT, ImageNet-LT, and Places-LT, demonstrate that MDPR achieves comparable results with current SOTA methods. Ablation studies further confirm the effectiveness of our semantic library for tail classes, and show that our dynamic routing incurs minimal computational overhead, making MDPR a flexible and efficient enhancement for VLM fine-tuning under data imbalance.

cs.CV↗

arXiv2024

LAION-SG: An Enhanced Large-Scale Dataset for Training Complex Image-Text Models with Structural Annotations

Recent advances in text-to-image (T2I) generation have shown remarkable success in producing high-quality images from text. However, existing T2I models show decayed performance in compositional image generation involving multiple objects and intricate relationships. We attribute this problem to limitations in existing datasets of image-text pairs, which lack precise inter-object relationship annotations with prompts only. To address this problem, we construct LAION-SG, a large-scale dataset with high-quality structural annotations of scene graphs (SG), which precisely describe attributes and relationships of multiple objects, effectively representing the semantic structure in complex scenes. Based on LAION-SG, we train a new foundation model SDXL-SG to incorporate structural annotation information into the generation process. Extensive experiments show advanced models trained on our LAION-SG boast significant performance improvements in complex scene generation over models on existing datasets. We also introduce CompSG-Bench, a benchmark that evaluates models on compositional image generation, establishing a new standard for this domain. Our annotations with the associated processing code, the foundation model and the benchmark protocol are publicly available at https://github.com/mengcye/LAION-SG.

cs.CV↗