activity
20242026
collaborators
Showing cs.CLShow all

6 papers · 1 filter

cs.CL2026

Reinforcement Learning from Denoising Feedback

Qi He, Huan Chen, Ya Guo +3

Policy loss estimation remains a fundamental and long-standing challenge in reinforcement learning (RL) for diffusion language models (DLMs). We introduce Reinforcement Learning fr…

cs.CL2026

Up to 36x Speedup: Mask-based Parallel Inference Paradigm for Key Information Extraction in MLLMs

Xinzhong Wang, Ya Guo, Jing Li +5

Key Information Extraction (KIE) from visually-rich documents (VrDs) is a critical task, for which recent Large Language Models (LLMs) and Multi-Modal Large Language Models (MLLMs)…

cs.CL2025

Keep the General, Inject the Specific: Structured Dialogue Fine-Tuning for Knowledge Injection without Catastrophic Forgetting

Yijie Hong, Xiaofei Yin, Xinzhong Wang +7

Large Vision Language Models have demonstrated impressive versatile capabilities through extensive multimodal pre-training, but face significant limitations when incorporating spec…

cs.CL2025

Unveiling the Deficiencies of Pre-trained Text-and-Layout Models in Real-world Visually-rich Document Information Extraction

Chong Zhang, Yixi Zhao, Yulu Xie +7

Recently developed pre-trained text-and-layout models (PTLMs) have shown remarkable success in multiple information extraction tasks on visually-rich documents (VrDs). However, des…

cs.CL2024

Modeling Layout Reading Order as Ordering Relations for Visually-rich Document Understanding

Chong Zhang, Yi Tu, Yixi Zhao +8

Modeling and leveraging layout reading order in visually-rich documents (VrDs) is critical in document intelligence as it captures the rich structure semantics within documents. Pr…

cs.CL2024

UNER: A Unified Prediction Head for Named Entity Recognition in Visually-rich Documents

Yi Tu, Chong Zhang, Ya Guo +4

The recognition of named entities in visually-rich documents (VrD-NER) plays a critical role in various real-world scenarios and applications. However, the research in VrD-NER face…