Ping An (China)

Recent papers from Ping An (China)

1. WindowQuant: Mixed-Precision KV Cache Quantization Based on Window-Level Similarity for VLMs Inference OptimizationACM Transactions on Architecture and Code Optimization · 2026
2. Reassessing the risk-modifying effects of novel antidiabetic agents on asthma–COPD overlap syndrome: a dose-stratified network meta-analysis of 316,832 adults from 128 randomised trialsEClinicalMedicine · 2026
3. The effect of GLP-1 receptor agonist and SGLT2 inhibitor on infection risk: network meta-analysisClinical Microbiology and Infection · 2026
4. DKGZSL: Leveraging Dynamic Visual-Semantic Knowledge for Generative Zero-Shot LearningIEEE Transactions on Circuits and Systems for Video Technology · 2026
5. Orchestrating Prompt Expertise: Enhancing Knowledge Distillation via Expert-Guided TuningACM Transactions on Asian and Low-Resource Language Information Processing · 2026
6. Knowledge distillation for financial large language models: a systematic review of strategies, applications, and evaluationFrontiers of Information Technology & Electronic Engineering · 2025
7. Atorvastatin pretreatment, ST-segment resolution and long-term prognosis for ST-segment elevation myocardial infarction with primary percutaneous coronary interventionIJC Heart & Vasculature · 2025
8. Inundation Hotspot: An insurance data and machine learning based fine-scale urban flood inundation map of China2025
9. Enhancing Multi-Agent Systems via Reinforcement Learning with LLM-Based Planner and Graph-Based Policy2025
10. ACCon: Angle-Compensated Contrastive Regularizer for Deep Regression2025
11. GDReCo: Fine-grained gene-disease relationship extraction corpusComputer Methods and Programs in Biomedicine · 2025
12. Cocktail: Chunk-Adaptive Mixed-Precision Quantization for Long-Context LLM Inference2025
13. Improving Contextual ASR with Enhanced Phrase-Level Representation Based on MCTC Loss2025
14. EffectiveASR: A Single-Step Non-Autoregressive Mandarin Speech Recognition Architecture with High Accuracy and Inference Speed2025
15. Token-Level Contextual Network with Ladder-Shaped Attention for End-to-End ASR2025
16. Homogeneous Graph Extraction: An Approach to Learning Heterogeneous Graph Embedding2025
17. SPEAK: Speech-Driven Pose and Emotion-Adjustable Talking Head Generation2025
18. Self-Enhanced Reasoning Training: Activating Latent Reasoning in Small Models for Enhanced Reasoning Distillation2025
19. CycleFlow: Leveraging Cycle Consistency in Flow Matching for Speaker Style Adaptation2025
20. LEF-TTS: Lightweight and Efficient End-to-End Text-to-Speech Synthesis With Multi-Stream Generator2025