Researcher — paper.dinq.me

2026 顶会论文

作者位次 #7/7ICLR 2026Poster· Computer Vision / Vision Models & Multimodal

Breaking the SFT Plateau: Multimodal Structured Reinforcement Learning for Chart-to-Code Generation

Lei Chen · Xuanle Zhao · Zhixiong Zeng · Jing Huang · Liming Zheng · Yufeng Zhong · Lin Ma

多模态强化学习与后训练代码OpenReview

作者位次 #7/7ICLR 2026Poster· Deep Learning / Everything Else

SPECS: Decoupling Multimodal Learning via Self-distilled Preference-based Cold Start

Kun Chen · Peng Shi · Haibo Qiu · Zhixiong Zeng · Siqi Yang · Wenji Mao · Lin Ma

对齐与偏好多模态强化学习与后训练OpenReview

作者位次 #9/10ICLR 2026Poster· Computer Vision / Vision Models & Multimodal

OmniActor: A Generalist GUI and Embodied Agent for 2D&3D Worlds

Longrong Yang · Zhixiong Zeng · Yufeng Zhong · Jing Huang · Liming Zheng · Lei Chen · Haibo Qiu · Zequn Qin · Lin Ma · Xi Li

智能体与工具多模态OpenReview

作者位次 #6/7ICLR 2026Poster· Computer Vision / Image and Video Generation

Scalable Training for Vector-Quantized Networks with 100% Codebook Utilization

Yifan Chang · Jie Qin · Limeng Qiao · Xiaofeng Wang · Zheng Zhu · Lin Ma · Xingang Wang

多模态效率与系统OpenReview

作者位次 #6/6CVPR 2026Poster· Computer Vision & Pattern Recognition

UniComp: Rethinking Video Compression Through Informational Uniqueness

Chao Yuan · Shimin Chen · Minliang Lin · Limeng Qiao · Guanglu Wan · Lin Ma

多模态效率与系统OpenReview 项目页

作者位次 #4/7CVPR 2026Poster· Computer Vision & Pattern Recognition

Cross-Modal Attention Calibration for LVLM Hallucination Mitigation

Jiaming Li · Jiacheng Zhang · Zequn Jie · Lin Ma · Ming Li · Xiaonan Luo · Guanbin Li

安全多模态OpenReview 项目页

作者位次 #11/11CVPR 2026Poster· Computer Vision & Pattern Recognition

Reading or Reasoning? Format Decoupled Reinforcement Learning for Document OCR

Yufeng Zhong · Lei Chen · Zhixiong Zeng · Xuanle Zhao · Deyang Jiang · Liming Zheng · Jing Huang · Haibo Qiu · Peng Shi · Siqi Yang · Lin Ma

推理多模态强化学习与后训练OpenReview 项目页

作者位次 #8/9CVPR 2026Poster· Computer Vision & Pattern Recognition

Perceptual-Evidence Anchored Reinforced Learning for Multimodal Reasoning

Chi Zhang · Haibo Qiu · Qiming ZHANG · Yufei Xu · Zhixiong Zeng · Siqi Yang · Peng Shi · Lin Ma · Jing Zhang

多模态推理OpenReview 项目页

作者位次 #8/8CVPR 2026Poster· Computer Vision & Pattern Recognition

M4V: Multimodal Mamba for Efficient Text-to-Video Generation

Jiancheng Huang · Gengwei Zhang · Zequn Jie · Siyu Jiao · Yinlong Qian · Ling Chen · Yunchao Wei · Lin Ma

多模态效率与系统长上下文与架构OpenReview 项目页

作者位次 #3/4CVPR 2026Poster· Computer Vision & Pattern Recognition

SO(3)-Equivariant ViT-Adapter for Data-Efficient Zero-Shot Sim-to-Real Indoor Panoramic Depth Estimation

Ziyan He · Qiudan Zhang · Lin Ma · Xu Wang

多模态效率与系统OpenReview 项目页

作者位次 #5/6CVPR 2026Spotlight· Computer Vision & Pattern Recognition

OddGridBench: Exposing the Lack of Fine-Grained Visual Discrepancy Sensitivity in Multimodal Large Language Models

Tengjin Weng · Wenhao Jiang · Jingyi Wang · Ming Li · Lin Ma · Zhong Ming

多模态OpenReview 项目页

作者位次 #4/5AAAI 2026Poster· Artificial Intelligence

DBGroup: Dual-Branch Point Grouping for Weakly Supervised 3D Semantic Instance Segmentation

Xuexun Liu · Xiaoxu Xu · Qiudan Zhang · Lin Ma · Xu Wang

OpenReview

作者位次 #7/9AAAI 2026Poster· Artificial Intelligence

X-SAM: From Segment Anything to Any Segmentation

Hao Wang · Limeng Qiao · Zequn Jie · Zhijian Huang · Chengjian Feng · Qingfang Zheng · Lin Ma · Xiangyuan Lan · Xiaodan Liang