116 citations · 209 across the 26 of their papers we have counts for
28 papers
Bayesian Learning to Select Fair Classifiers
Saatvik Kher, Hyungrok Do, Judy Zhong +1
Evaluations of classifiers (AI or human or agents) often assume a batch setting in which every agent produces labels on every example in a test set, which can be expensive or impra…
ReDiPPO: Reference-Guided Value Calibration and Discrepancy-Aware Token Reweighting for Mathematical Reasoning
Zhenrong Zhang, Fei Wu, Jun Du +2
Reinforcement learning has emerged as an effective paradigm for enhancing the mathematical reasoning capabilities of large language models. Among existing policy optimization metho…
PEARL: Training Socratic Tutors with Pedagogically Aligned Reinforcement Learning
Qikai Chang, Zhenrong Zhang, Linbo Chen +4
Large Language Models (LLMs) show strong potential as educational tutors. Existing approaches typically train them to solve problems and provide correct answers, but this problem-s…
Step Potential Advantage Estimation: Harnessing Intermediate Confidence and Correctness for Efficient Mathematical Reasoning
Fei Wu, Zhenrong Zhang, Qikai Chang +3
Reinforcement Learning with Verifiable Rewards (RLVR) elicits long chain-of-thought reasoning in large language models (LLMs), but outcome-based rewards lead to coarse-grained adva…
THOR: Tool-Integrated Hierarchical Optimization via RL for Mathematical Reasoning
Qikai Chang, Zhenrong Zhang, Pengfei Hu +6
Large Language Models (LLMs) have made remarkable progress in mathematical reasoning, but still continue to struggle with high-precision tasks like numerical computation and formal…
EquivPruner: Boosting Efficiency and Quality in LLM-Based Search via Action Pruning
Jiawei Liu, Qisi Chen, Jianshu Zhang +2
Large Language Models (LLMs) excel at complex reasoning through search algorithms, yet current strategies often suffer from massive token consumption due to redundant exploration o…
Enhancing the Geometric Problem-Solving Ability of Multimodal LLMs via Symbolic-Neural Integration
Yicheng Pan, Zhenrong Zhang, Pengfei Hu +6
Recent advances in Multimodal Large Language Models (MLLMs) have achieved remarkable progress in general domains and demonstrated promise in multimodal mathematical reasoning. Howe…
MMC: Iterative Refinement of VLM Reasoning via MCTS-based Multimodal Critique
Shuhang Liu, Zhenrong Zhang, Pengfei Hu +7
Visual language models (VLMs) have demonstrated strong performance across diverse multimodal reasoning tasks but still face challenges such as hallucinations, resulting in incorrec…
PRM-BAS: Enhancing Multimodal Reasoning through PRM-guided Beam Annealing Search
Pengfei Hu, Zhenrong Zhang, Qikai Chang +8
Recent work increasingly focuses on improving the reasoning capabilities of Multimodal Large Language Models (MLLMs). Among existing methods, Process Reward Models (PRMs) stand out…
Skeleton and Font Generation Network for Zero-shot Chinese Character Generation
Mobai Xue, Jun Du, Zhenrong Zhang +5
Automatic font generation remains a challenging research issue, primarily due to the vast number of Chinese characters, each with unique and intricate structures. Our investigation…
UniTabNet: Bridging Vision and Language Models for Enhanced Table Structure Recognition
Zhenrong Zhang, Shuhang Liu, Pengfei Hu +4
In the digital era, table structure recognition technology is a critical tool for processing and analyzing large volumes of tabular data. Previous methods primarily focus on visual…
See then Tell: Enhancing Key Information Extraction with Vision Grounding
Shuhang Liu, Zhenrong Zhang, Pengfei Hu +5
In the digital era, the ability to understand visually rich documents that integrate text, complex layouts, and imagery is critical. Traditional Key Information Extraction (KIE) me…
DocMamba: Efficient Document Pre-training with State Space Model
Pengfei Hu, Zhenrong Zhang, Jiefeng Ma +3
In recent years, visually-rich document understanding has attracted increasing attention. Transformer-based pre-trained models have become the mainstream approach, yielding signifi…
SRFUND: A Multi-Granularity Hierarchical Structure Reconstruction Benchmark in Form Understanding
Jiefeng Ma, Yan Wang, Chenyu Liu +6
Accurately identifying and organizing textual content is crucial for the automation of document processing in the field of form understanding. Existing datasets, such as FUNSD and…
Count, Decode and Fetch: A New Approach to Handwritten Chinese Character Error Correction
Pengfei Hu, Jiefeng Ma, Zhenrong Zhang +2
Recently, handwritten Chinese character error correction has been greatly improved by employing encoder-decoder methods to decompose a Chinese character into an ideographic descrip…
HRDoc: Dataset and Baseline Method Toward Hierarchical Reconstruction of Document Structures
Jiefeng Ma, Jun Du, Pengfei Hu +4
The problem of document structure reconstruction refers to converting digital or scanned documents into corresponding semantic structures. Most existing works mainly focus on split…
SEMv2: Table Separation Line Detection Based on Instance Segmentation
Zhenrong Zhang, Pengfei Hu, Jiefeng Ma +6
Table structure recognition is an indispensable element for enabling machines to comprehend tables. Its primary purpose is to identify the internal structure of a table. Neverthele…
Multimodal Tree Decoder for Table of Contents Extraction in Document Images
Pengfei Hu, Zhenrong Zhang, Jianshu Zhang +2
Table of contents (ToC) extraction aims to extract headings of different levels in documents to better understand the outline of the contents, which can be widely used for document…
Multimodal Pre-training Based on Graph Attention Network for Document Understanding
Zhenrong Zhang, Jiefeng Ma, Jun Du +2
Document intelligence as a relatively new research topic supports many business applications. Its main task is to automatically read, understand, and analyze documents. However, du…
Split, embed and merge: An accurate table structure recognizer
Zhenrong Zhang, Jianshu Zhang, Jun Du
Table structure recognition is an essential part for making machines understand tables. Its main task is to recognize the internal structure of a table. However, due to the complex…
Stroke Constrained Attention Network for Online Handwritten Mathematical Expression Recognition
Jiaming Wang, Jun Du, Jianshu Zhang
In this paper, we propose a novel stroke constrained attention network (SCAN) which treats stroke as the basic unit for encoder-decoder based online handwritten mathematical expres…
Episodic Training for Domain Generalization
Da Li, Jianshu Zhang, Yongxin Yang +3
Domain generalization (DG) is the challenging and topical problem of learning models that generalize to novel testing domains with different statistics than a set of known training…
DenseRAN for Offline Handwritten Chinese Character Recognition
Wenchao Wang, Jianshu Zhang, Jun Du +2
Recently, great success has been achieved in offline handwritten Chinese character recognition by using deep learning methods. Chinese characters are mainly logographic and consist…
Attention Based Fully Convolutional Network for Speech Emotion Recognition
Yuanyuan Zhang, Jun Du, Zirui Wang +1
Speech emotion recognition is a challenging task for three main reasons: 1) human emotion is abstract, which means it is hard to distinguish; 2) in general, human emotion can only…