1 citations · 1 across the 7 of their papers we have counts for
13 papers
CLIVO: Differentiable Cluster-Based Instruction Mixing with Learned Validation Objectives
Yuhan Wang, Rui Hu, Batian Di +5
Data selection turns large multimodal instruction pools into compact training subsets tailored to a vision-language model's target capabilities. Effective selection requires both u…
Better Supervision Is Nearby: Neighborhood On-Policy Self-Distillation
Xincheng Wei, Yifan Ding, Yoshua Li +6
On-policy self-distillation (OPSD) trains mathematical reasoning models using a privileged teacher that sees a reference solution and supervises student-sampled prefixes. Standard…
Do Coding Agents Reuse Existing Code or Reinvent the Wheel?
Dongsheng Ma, Sizhe Wang, Xinyi Huang +5
Coding agents are increasingly deployed for iterative development on real repositories, yet existing evaluation barely answers a basic question: \emph{do coding agents reuse existi…
Learning What to Practice: Diagnosis-Guided Self-Evolution for Language Models
Xincheng Wei, Yifan Ding, Fucheng Xiong +6
Self-play supports the self-evolution of language models, but solver performance can plateau or decline across rounds without guidance. Existing unguided methods typically use diff…
From Diagnosis to Correction: Benchmarking and Improving Real-World Table Parsing
Jutao Xiao, Yuan Qu, Dongsheng Ma +7
Recent document parsers achieve table TEDS scores above 93 on OmniDocBench v1.6, yet community feedback and our audit reveal persistent failures on complex real-world tables. To qu…
SAF-OPD: Stable Advantage Fusion for On-Policy Distillation
Yifan Ding, Xincheng Wei, Yoshua Y. Li +7
Reinforcement learning with verifiable rewards (RLVR) broadcasts a single response-level reward to every token, while on-policy distillation (OPD) scores each token against a stron…
Seeing Before Agreeing: Aligning Multi-Agent Consensus with Visual Evidence
Yuhan Wang, Shuochen Chang, Yalin Feng +8
Vision-language models (VLMs) have achieved strong performance on visual question answering (VQA). To mitigate individual hallucinations and blind spots, aggregating diverse perspe…
CiteVQA: Benchmarking Evidence Attribution for Trustworthy Document Intelligence
Dongsheng Ma, Jiayu Li, Zhengren Wang +10
Multimodal Large Language Models (MLLMs) have significantly advanced document understanding, yet current Doc-VQA evaluations score only the final answer and leave the supporting ev…
MinerU2.5-Pro: Pushing the Limits of Data-Centric Document Parsing at Scale
Bin Wang, Tianyao He, Linke Ouyang +40
Current document parsing methods advance primarily through model architecture innovation, while systematic engineering of training data remains underexplored. Yet state-of-the-art…
AgenticOCR: Parsing Only What You Need for Efficient Retrieval-Augmented Generation
Zhengren Wang, Dongsheng Ma, Huaping Zhong +4
The expansion of retrieval-augmented generation (RAG) into multimodal domains has intensified the challenge for processing complex visual documents, such as financial reports. Whil…
Text2VectorSQL: Towards a Unified Interface for Vector Search and SQL Queries
Zhengren Wang, Dongwen Yao, Bozhou Li +7
The proliferation of unstructured data poses a fundamental challenge to traditional database interfaces. While Text-to-SQL has democratized access to structured data, it remains in…
CodeFlowBench: A Multi-turn, Iterative Benchmark for Complex Code Generation
Sizhe Wang, Zhengren Wang, Dongsheng Ma +5
Modern software development demands code that is maintainable, testable, and scalable by organizing the implementation into modular components with iterative reuse of existing code…
RARE: Retrieval-Augmented Reasoning Modeling
Zhengren Wang, Jiayang Yu, Dongsheng Ma +8
Domain-specific intelligence demands specialized knowledge and sophisticated reasoning for problem-solving, posing significant challenges for large language models (LLMs) that stru…