Chimera: Improving Generalist Model with Domain-Specific Experts

Tianshuo Peng^*, Mingsheng Li^*, Jiakang Yuan, Hongbin Zhou, Renqiu Xia, Renrui Zhang, Lei Bai, Song Mao, Bin Wang, Aojun Zhou, Botian Shi, Tao Chen, Bo Zhang, Xiangyu Yue

[Project][Paper]

• a scalable and low-cost multi-modal pipeline designed to boost the ability of existing LMMs with domain-specific experts.

SurveyForge: On the Outline Heuristics, Memory-Driven Generation, and Multi-dimensional Evaluation for Automated Survey Writing

Xiangchao Yan^*, Shiyang Feng^*, Jiakang Yuan, Renqiu Xia, Bin Wang, Bo Zhang, Lei Bai

[Project][Paper]

• Propose SurveyForge which can automatically generate and refine the content of survey.

Image Over Text: Transforming Formula Recognition Evaluation with Character Detection Matching

Bin Wang^*, Fan Wu^*, Linke Ouyang^*, Zhuangcheng Gu, Rui Zhang, Renqiu Xia, Botian Shi, Bo Zhang, Conghui He

[Project][Paper]

• Propose a Character Detection Matching (CDM) metric, ensuring the evaluation objectivity by designing an image-level rather than a LaTeX-level metric score.

GeoX: Geometric Problem Solving Through Unified Formalized Vision-Language Pre-training

Renqiu Xia^*, Mingsheng Li^*, Hancheng Ye, Wenjie Wu, Hongbin Zhou, Jiakang Yuan, Tianshuo Peng, Xinyu Cai, Xiangchao Yan, Bin Wang, Conghui He, Botian Shi, Tao Chen, Junchi Yan, Bo Zhang

[Project][Paper]

• Propose GeoX, a multi-modal large model focusing on geometric understanding and reasoning tasks which reveals the large potential of formalized visual-language pre-training in enhancing geometric problem-solving abilities.

LaTeXNet: A Specialized Model for Converting Visual Tables and Equations to LaTeX Code

Renqiu Xia, Hongbin Zhou, Ziming Feng, Huanxi Liu, Boan Chen, Bo Zhang, Junchi Yan

[Project][Paper]

• Propose LaTeXNet, a specialized model designed to automate the conversion of visual tables and equations into LaTeX code.

Training-Free Adaptive Diffusion with Bounded Difference Approximation Strategy

Hancheng Ye^*, Jiakang Yuan^*, Renqiu Xia, Xiangchao Yan, Tao Chen, Junchi Yan, Botian Shi, Bo Zhang

[Project][Paper]

• Propose AdaptiveDiffusion to adaptively reduce the noise prediction steps during the denoising proces guided by the third-order latent difference.

Once for Both: Single Stage of Importance and Sparsity Search for Vision Transformer Compression

Hancheng Ye, Chong Yu, Peng Ye, Renqiu Xia, Yansong Tang, Jiwen Lu, Tao Chen, Bo Zhang

[Project][Paper]

• Propose OFB, a cost-efficient approach that simultaneously evaluates both importance and sparsity scores for VTC.

ReSimAD: Zero-Shot 3D Domain Transfer for Autonomous Driving with Source Reconstruction and Target Simulation

Bo Zhang^*, Xinyu Cai^*, Jiakang Yuan, Donglin Yang, Jianfei Guo, Xiangchao Yan, Renqiu Xia, Botian Shi, Min Dou, Tao Chen, Si Liu, Junchi Yan, Yu Qiao

[Project][Paper]

• Provide a new perspective and approach of alleviating the domain shifts, by proposing a Reconstruction-Simulation-Perception scheme.

Efficient Architecture Search for Real-Time Instance Segmentation

Renqiu Xia, Dongyuan Zhang, Yixin Dong, Juanping Zhao, Wenlong Liao, Tao He, Junchi Yan

[Project][Paper]

• Propose EASInst，an efficient framework that discover practical backbone and encoder architectures for the improved sparse activation instance segmentation model.

Beyond Theorem Proving: Formulation, Framework and Benchmark for Formal Problem-Solving

Qi Liu, Xinhao Zheng, Renqiu Xia, Xingzhi Qi, Qinxiang Cao, Junchi Yan

[Project][Paper]

• Propose a novel framework, FPS (Formal Problem-Solving), which utilizes existing FTP (formal theorem proving) environments to perform process-verified problem-solving.

TrustGeoGen: Scalable and Formal-Verified Data Engine for Trustworthy Multi-modal Geometric Problem Solving

Daocheng Fu^*, Zijun Chen^*, Renqiu Xia^*, Qi Liu, Yuan Feng, Hongbin Zhou, Renrui Zhang, Shiyang Feng, Peng Gao, Junchi Yan, Botian Shi, Bo Zhang, Yu Qiao

[Project][Paper]

• Propose a scalable data engine called TrustGeoGen for geometric problem generation, with formal verification to provide a principled benchmark.

DocGenome: An Open Large-scale Scientific Document Benchmark for Training and Testing Multi-modal Large Language Models

Renqiu Xia^*, Song Mao^*, Xiangchao Yan^*, Hongbin Zhou, Bo Zhang, Haoyang Peng, Jiahao Pi, Daocheng Fu, Wenjie Wu, Hancheng Ye, Shiyang Feng, Bin Wang, Chao Xu, Conghui He, Pinlong Cai, Min Dou, Botian Shi, Sheng Zhou, Yongwei Wang, Bin Wang, Junchi Yan, Fei Wu, Yu Qiao

[Project][Paper]

• Present DocGenome, a structured document benchmark constructed by annotating 500K scientific documents from 153 disciplines in the arXiv open-access community, using our custom auto-labeling pipeline.

ChartX & ChartVLM: A Versatile Benchmark and Foundation Model for Complicated Chart Reasoning

Renqiu Xia^*, Bo Zhang^*, Hancheng Ye^*, Xiangchao Yan, Qi Liu, Hongbin Zhou, Zijun Chen, Peng Ye, Min Dou, Botian Shi, Junchi Yan, Yu Qiao

[Project][Paper]

• Construct ChartX, a multi-modal evaluation set covering 18 chart types and develop ChartVLM to offer a new perspective on handling multi-modal tasks that strongly depend on interpretable patterns.

StructChart: On the Schema, Metric, and Augmentation for Visual Chart Understanding

Renqiu Xia^*, Haoyang Peng, Hancheng Ye, Mingsheng Li, Xiangchao Yan, Peng Ye, Botian Shi, Yu Qiao, Junchi Yan, Bo Zhang

[Project][Paper]

• Introduce StructChart, a novel framework that leverages Structured Triplet Representations (STR) to achieve a unified and label-efficient approach to chart perception and reasoning tasks.