Peilin Zhou

Compliance-to-Code : Enhancing Financial Compliance Checking via Code Generation

Siyuan Li, Jian Chen, Rui Yao, Xuming Hu et autres

Nowadays, regulatory compliance has become a cornerstone of corporate governance, ensuring adherence to systematic legal frameworks. At its core, financial regulations often comprise highly intricate provisions, layered logical structures, and numerous exceptions, which inevitably result in labor-intensive or comprehension challenges. To mitigate …

cn, us, hk (code pays fourni par la source)

Intent-Guided Reasoning for Sequential Recommendation

Yifan Shao, Peilin Zhou

Sequential recommendation systems aim to capture users' evolving preferences from their interaction histories. Recent reasoningenhanced methods have shown promise by introducing deliberate, chain-of-thought-like processes with intermediate reasoning steps. However, these methods rely solely on the next target item as supervision, leading to …

What Matters in LLM-Based Feature Extractor for Recommender? A Systematic Analysis of Prompts, Models, and Adaptation

Kai Shi, Peilin Zhou, Ge Wang, Han Ding et autres

Using Large Language Models (LLMs) to generate semantic features has been demonstrated as a powerful paradigm for enhancing Sequential Recommender Systems (SRS). This typically involves three stages: processing item text, extracting features with LLMs, and adapting them for downstream models. However, existing …

ClimateIQA: A New Dataset and Benchmark to Advance Vision-Language Models in Meteorology Anomalies Analysis

Peilin Zhou, Yining Hua, D Chong, Yaowei Li et autres

Meteorological heatmaps play a vital role in deciphering extreme weather phenomena, yet their inherent complexities-marked by irregular contours, unstructured patterns, and complex color variations-present unique analytical hurdles for state-of-the-art Vision-Language Models (VLMs). Current state-of-the-art models like GPT-4o, Qwen-VL, and LLaVA 1.6 struggle …

hk, cn, us, ae, gb (code pays fourni par la source)

Zero-Parameter Attention Sharing Transformer for Joint Human Activity and Identity Recognition

Shuokang Huang, Po-Yu Chen, Peilin Zhou, Kaihan Li et autres

WiFi-based human sensing is gaining popularity thanks to it not requiring additional devices and it not being as intrusive as cameras. Specifically, human features can be extracted from WiFi Channel State Information (CSI) to recognize human activities, identities, etc. However, most previous …

gb, hk, cn (code pays fourni par la source)

From Web Search towards Agentic Deep Research: Incentivizing Search with Reasoning Agents

Weizhi Zhang, Yangning Li, Yuanchen Bei, Junyu Luo et autres

Information retrieval is a cornerstone of modern knowledge acquisition, enabling billions of queries each day across diverse domains. However, traditional keyword-based search engines are increasingly inadequate for handling complex, multi-step information needs. Our position is that Large Language Models (LLMs), endowed with …

When Large Vision Language Models Meet Multimodal Sequential Recommendation: An Empirical Study

Peilin Zhou, Jing Ren, X. R. Zhou, Yueqi Xie et autres

As multimedia content continues to grow on the web, the integration of visual and textual data has become a crucial challenge for web applications, particularly in recommendation systems. Large Vision Language Models (LVLMs) have demonstrated considerable potential in addressing this challenge across …

cn, hk, ae, au (code pays fourni par la source)

Application of large language models in medicine

Fenglin Liu, Hongjian Zhou, 博司 熊谷, Xinyu Zou et autres

gb, ca, us, cn (code pays fourni par la source)

Characterizing Public Sentiments and Drug Interactions in the COVID-19 Pandemic Using Social Media: Natural Language Processing and Network Analysis

Wanxin Li, Yining Hua, Peilin Zhou, Li Zhou et autres

BACKGROUND: While the COVID-19 pandemic has induced massive discussion of available medications on social media, traditional studies focused only on limited aspects, such as public opinions, and endured reporting biases, inefficiency, and long collection times. OBJECTIVE: Harnessing drug-related data posted on social …

cn, us, hk (code pays fourni par la source)

Power scaling of Raman fiber amplifiers based on spectral modulation of higher-order Stokes

Xiulu Hao, chenchen 期. fan, Yang Li, Jinyong Leng et autres

Raman fiber amplifiers (RFAs), as a new type of laser capable of achieving both high power and special wavelength output, have been widely adopted in energy, environment, and industry. However, the generation of high-order Stokes reduces the conversion efficiency of this laser …

cn (code pays fourni par la source)

Characterizing Public Sentiments and Drug Interactions in the COVID-19 Pandemic Using Social Media: Natural Language Processing and Network Analysis (Preprint)

Wanxin Li, Yining Hua, Peilin Zhou, Li Zhou et autres

BACKGROUND While the COVID-19 pandemic has induced massive discussion of available medications on social media, traditional studies focused only on limited aspects, such as public opinions, and endured reporting biases, inefficiency, and long collection times. OBJECTIVE Harnessing drug-related data posted on social …

The sexual and gender-diverse face more health challenges during COVID-19: A large-scale social media analysis with natural language processing

Zhiyun Zhang, Yining Hua, Peilin Zhou, Shixu Lin et autres

Abstract Background: The COVID-19 pandemic has caused a disproportionate impact on the sex and gender diversity (SGD) community. Compared with non-SGD populations, their social relations and health status are more vulnerable, whereas public health data regarding SGD is scarce. Methods: To analyze …

cn, us, hk (code pays fourni par la source)