PersuaRL: Reinforcement Learning-Driven Multi-Expert Selection for Persuasive Dialogue Generation in Insurance
本文针对保险领域对话生成缺乏说服力的问题，提出基于强化学习的PersuaRL框架，通过多专家模块选择实现更有效的说服性对话。
0 citationsRead paper
Selected work
Representative Papers
Gate-level Implementation and Resource Analysis of Lackadaisical Quantum Walk Search
本文通过构建门级实现框架，解决了缺乏实际量子硬件上执行的懒散量子行走搜索问题，并分析了其资源需求。
0 citationsRead paper
A HamNoSys-Guided Dataset and Baselines for Fine-Grained Isolated Handshape Recognition in Sign Language
This study addresses the lack of large-scale, language-agnostic, fine-grained visual datasets for sign language recognition that support signer-aware evaluation. To bridge this gap, the authors construct a balanced dataset based on the Hamburg Notation System (HamNoSys 4), comprising 144,000 RGB images contributed by 15 signers across 160 handshape classes. They introduce, for the first time, a dual evaluation protocol incorporating both signer-dependent and leave-one-signer-out (LOSO) settings, and establish reproducible benchmarks using diverse models—including ResNet-18, ViT-B/16, graph convolutional networks, and XGBoost. Experiments on the ASL Fingerspelling Dataset A achieve Top-1 accuracy of 82.20%–87.40% under the LOSO protocol, while also revealing a significant performance drop in cross-signer generalization, highlighting a critical challenge in real-world deployment.
0 citationsRead paper
A Word-Level Digital Reader of the Prasthanatrayi with Sankara's Bhasya: Corpus, Method, and an Open, Offline Reading Aid for the Advaita Vedanta Canon
This study addresses word-level readability barriers in the *Triple Canon* and Śaṅkara’s commentary—arising from sandhi, compound formation, and dense scholarly prose—by presenting the first offline, open-source, word-level interactive reading system covering the complete text. The system integrates a rule-based sandhi splitter, an inflectional lexicon, corpus-based lookup tables, and a large language model, enhanced by an adversarial two-pass validation protocol and a human-in-the-loop correction mechanism. It encompasses 13 commentary units, 36,881 root-text tokens, and 95,587 surface forms from the commentary, achieving over 99% agreement with authoritative dictionaries at high-confidence analysis levels. This substantially enhances the readability and searchability of Sanskrit philosophical texts.
0 citationsRead paper
The Multipath Blind Spot: $K$-Agnostic Robust Calibration for Sparse-Anchor Metric Depth from Frozen Foundations
This work addresses the significant performance degradation of existing sparse anchor calibration methods under real-world sensor anomalies—particularly multipath interference—where anchors are present but corrupted by erroneous values. The authors propose MRAC, a training-free, inference-time calibration framework that, for the first time, exposes a structural blind spot in the widely used VI-Depth method under such conditions. MRAC introduces a robust, parameter- and K-value-agnostic mechanism that leverages the base model’s internal consistency to identify reliable anchors, followed by Theil–Sen estimation combined with Median Absolute Deviation (MAD) testing. The entire calibration process completes in approximately 50 microseconds on a CPU and supports arbitrary numbers of anchors. Evaluated on a 320-instance benchmark, MRAC achieves an 84% win rate and reduces AbsRel error by 3.2× (from 0.489 to 0.151) on KITTI multipath scenarios—all without requiring model retraining.
0 citationsRead paper
Recent publications
Latest Papers
PersuaRL: Reinforcement Learning-Driven Multi-Expert Selection for Persuasive Dialogue Generation in Insurance
本文针对保险领域对话生成缺乏说服力的问题，提出基于强化学习的PersuaRL框架，通过多专家模块选择实现更有效的说服性对话。
0 citationsRead paper
Gate-level Implementation and Resource Analysis of Lackadaisical Quantum Walk Search
本文通过构建门级实现框架，解决了缺乏实际量子硬件上执行的懒散量子行走搜索问题，并分析了其资源需求。
0 citationsRead paper
A HamNoSys-Guided Dataset and Baselines for Fine-Grained Isolated Handshape Recognition in Sign Language
This study addresses the lack of large-scale, language-agnostic, fine-grained visual datasets for sign language recognition that support signer-aware evaluation. To bridge this gap, the authors construct a balanced dataset based on the Hamburg Notation System (HamNoSys 4), comprising 144,000 RGB images contributed by 15 signers across 160 handshape classes. They introduce, for the first time, a dual evaluation protocol incorporating both signer-dependent and leave-one-signer-out (LOSO) settings, and establish reproducible benchmarks using diverse models—including ResNet-18, ViT-B/16, graph convolutional networks, and XGBoost. Experiments on the ASL Fingerspelling Dataset A achieve Top-1 accuracy of 82.20%–87.40% under the LOSO protocol, while also revealing a significant performance drop in cross-signer generalization, highlighting a critical challenge in real-world deployment.
0 citationsRead paper
A Word-Level Digital Reader of the Prasthanatrayi with Sankara's Bhasya: Corpus, Method, and an Open, Offline Reading Aid for the Advaita Vedanta Canon
This study addresses word-level readability barriers in the *Triple Canon* and Śaṅkara’s commentary—arising from sandhi, compound formation, and dense scholarly prose—by presenting the first offline, open-source, word-level interactive reading system covering the complete text. The system integrates a rule-based sandhi splitter, an inflectional lexicon, corpus-based lookup tables, and a large language model, enhanced by an adversarial two-pass validation protocol and a human-in-the-loop correction mechanism. It encompasses 13 commentary units, 36,881 root-text tokens, and 95,587 surface forms from the commentary, achieving over 99% agreement with authoritative dictionaries at high-confidence analysis levels. This substantially enhances the readability and searchability of Sanskrit philosophical texts.
0 citationsRead paper
The Multipath Blind Spot: $K$-Agnostic Robust Calibration for Sparse-Anchor Metric Depth from Frozen Foundations
This work addresses the significant performance degradation of existing sparse anchor calibration methods under real-world sensor anomalies—particularly multipath interference—where anchors are present but corrupted by erroneous values. The authors propose MRAC, a training-free, inference-time calibration framework that, for the first time, exposes a structural blind spot in the widely used VI-Depth method under such conditions. MRAC introduces a robust, parameter- and K-value-agnostic mechanism that leverages the base model’s internal consistency to identify reliable anchors, followed by Theil–Sen estimation combined with Median Absolute Deviation (MAD) testing. The entire calibration process completes in approximately 50 microseconds on a CPU and supports arbitrary numbers of anchors. Evaluated on a 320-instance benchmark, MRAC achieves an 84% win rate and reduces AbsRel error by 3.2× (from 0.489 to 0.151) on KITTI multipath scenarios—all without requiring model retraining.
0 citationsRead paper