6 papers
Perception, Layout, and Validation: Calibrated Confidence for Reliable Straight-Through Processing of Financial Documents
Yichao Jin, Yushuo Wang, Yuxuan Han +7
Straight-through processing (STP) on extracted key-value fields from financial documents without human review requires a calibrated probability together with a bounded guarantee on…
A Multistage Extraction Pipeline for Long Scanned Financial Documents: An Empirical Study in Industrial KYC Workflows
Yuxuan Han, Yuanxing Zhang, Yushuo Wang +3
Structured information extraction from long, multilingual scanned financial documents is a core requirement in industrial KYC and compliance workflows. These documents are typicall…
Making LLMs Optimize Multi-Scenario CUDA Kernels Like Experts
Yuxuan Han, Meng-Hao Guo, Zhengning Liu +2
Optimizing GPU kernels manually is a challenging and time-consuming task. With the rapid development of LLMs, automated GPU kernel optimization is gradually becoming a tangible rea…
Vectra: A New Metric, Dataset, and Model for Visual Quality Assessment in E-Commerce In-Image Machine Translation
Qingyu Wu, Yuxuan Han, Haijun Li +5
In-Image Machine Translation (IIMT) powers cross-border e-commerce product listings; existing research focuses on machine translation evaluation, while visual rendering quality is…
Ovis2.5 Technical Report
Shiyin Lu, Yang Li, Yu Xia +39
We present Ovis2.5, a successor to Ovis2 designed for native-resolution visual perception and strong multimodal reasoning. Ovis2.5 integrates a native-resolution vision transformer…
TransBench: Benchmarking Machine Translation for Industrial-Scale Applications
Haijun Li, Tianqi Shi, Zifu Shang +13
Machine translation (MT) has become indispensable for cross-border communication in globalized industries like e-commerce, finance, and legal services, with recent advancements in…