arXiv subjects

Xiaofeng Jiang

Publications and source records attributed to Xiaofeng Jiang.

5 recordsLinked to original sources

arXiv2026

Bridging Network Fragmentation: A Semantic-Augmented DRL Framework for UAV-aided VANETs

Urban Vehicular Ad-Hoc Networks (VANETs) can become fragmented because buildings obstruct wireless links and vehicle mobility continuously changes the network topology. Unmanned Aerial Vehicles (UAVs) can serve as mobile relays, but Deep Reinforcement Learning (DRL)-based deployment often suffers from inefficient exploration because it lacks road-topology guidance. To address this problem, we propose Semantic-Augmented DRL (SA-DRL), which models network fragmentation over the road topology and aligns a pretrained Large Language Model (LLM) to generate a topology-dependent action prior from dynamic traffic states. The resulting Semantic-Augmented PPO (SA-PPO) algorithm combines this prior with the PPO policy through Logit Fusion, guiding exploration toward promising intersections while retaining adaptation through environmental returns. Simulations driven by real-world urban trajectories show that SA-PPO reaches the final converged reward of Vanilla PPO using only 28.6% of its training episodes. It improves the average number of vehicles in connected components and the average connected-component size by 7.9% and 8.7%, respectively, while reducing UAV energy consumption by 21.3%.

cs.AI↗

arXiv2026

RP-OPSD: Resolution-Privileged On-Policy Self-Distillation for Multimodal Large Language Models

On-Policy Self-Distillation (OPSD) uses privileged information available only to the teacher to provide dense token-level supervision on trajectories generated by the student. However, existing methods often rely on verified solution traces, explanations generated by external models, or manually localized visual evidence, which limits their scalable application to multimodal large language models. To address this issue, we exploit the information gap between high- and low-resolution views of the same image and propose RP-OPSD (Resolution-Privileged On-Policy Self-Distillation for Multimodal Large Language Models). During training, the student policy generates on-policy trajectories from images at one-quarter of the original resolution, while the teacher policy provides supervision using the original-resolution images. By minimizing the divergence between their output distributions along the student trajectories, the student learns the predictive behavior of the teacher under high-resolution inputs, thereby strengthening its low-resolution capability and transferring the learned improvement to original-resolution inference. RP-OPSD requires neither additional human annotations nor external models to generate solution traces but only image--question pairs. Experiments on Qwen3.5-9B show that RP-OPSD achieves a 5.45\% relative improvement in average performance at the original resolution and a $1.78\times$ training speedup over OPSD. These results demonstrate that resolution differences can serve as a simple and scalable source of privileged information, providing an effective and efficient approach to on-policy self-distillation for multimodal large language models.

cs.CV↗

arXiv2026

When TableQA Meets Noise: A Dual Denoising Framework for Complex Questions and Large-scale Tables

Table question answering (TableQA) is a fundamental task in natural language processing (NLP). The strong reasoning capabilities of large language models (LLMs) have brought significant advances in this field. However, as real-world applications involve increasingly complex questions and larger tables, substantial noisy data is introduced, which severely degrades reasoning performance. To address this challenge, we focus on improving two core capabilities: Relevance Filtering, which identifies and retains information truly relevant to reasoning, and Table Pruning, which reduces table size while preserving essential content. Based on these principles, we propose EnoTab, a dual denoising framework for complex questions and large-scale tables. Specifically, we first perform Evidence-based Question Denoising by decomposing the question into minimal semantic units and filtering out those irrelevant to answer reasoning based on consistency and usability criteria. Then, we propose Evidence Tree-guided Table Denoising, which constructs an explicit and transparent table pruning path to remove irrelevant data step by step. At each pruning step, we observe the intermediate state of the table and apply a post-order node rollback mechanism to handle abnormal table states, ultimately producing a highly reliable sub-table for final answer reasoning. Finally, extensive experiments show that EnoTab achieves outstanding performance on TableQA tasks with complex questions and large-scale tables, confirming its effectiveness.

cs.CL↗

arXiv2023

Role of electrodes in study of hydrovoltaic effects

The last decade has witnessed the emergence of hydrovoltaic technology, which can harvest electricity from different forms of water movement, such as raindrops, waves, flows, moisture, and natural evaporation. In particular, the evaporation-induced hydrovoltaic effect received great attention since its discovery in 2017 due to its negative heat emission property. Nevertheless, the influence of electrode reactions in evaporation-induced power generation is not negligible due to the chemical reaction between active metal electrodes and water, which leads to " exceptional " power generation. Herein, we designed a series of experiments based on air-laid paper devices with electrodes of different activities as the top and bottom electrodes. To verify the contribution of electrodes, we compared the output performance of different electrode combinations when the device is partially-wetted and fully-wetted. The device hydrophilicity, salt concentration, and acidity or basicity of solutions are also comprehensively investigated. It is demonstrated that the chemical reaction of active metals (Zn, Cu, Ag, etc.) with different aqueous solutions can generate considerable electrical energy and significantly distort the device performance, especially for Zn electrodes with an output voltage from ~1.26 to ~1.52 V and current from ~1.24 to ~75.69 μA. To promote the long-term development of hydrovoltaic technology, we recommend use of inert electrodes in hydrovoltaic studies, such as Au and Pt, especially in water and moisture environment.

physics.chem-ph↗

arXiv2017

Preconditioned wire array Z-pinches driven by a double pulse current generator

Suppressing of the core-corona structures shows a strong potential as a new breakthrough in the X-ray power production of the wire array Z-pinches. In this letter, the demonstration of suppressing the core-corona structures and its ablation using a novel double pulse current generator "Qin-1" facility is presented. The "Qin-1" facility coupled a ~10 kA 20 ns prepulse generator to a ~ 1 MA 170 ns main current generator. Driven by the prepulse current, the two aluminum wire array were mostly heated to gaseous state rather than the core-corona structures, and the implosion of the aluminum vapors driven by the main current showed no ablation, and no trailing mass. The seeds for the MRT instability formed from the inhomogeneous ablation were suppressed, however, the magneto Rayleigh-Taylor instability during the implosion was still significant and further researches on the generation and development of the magneto Rayleigh-Taylor instabilities of this gasified wire array are needed.

physics.plasm-ph↗