Researcher — paper.dinq.me

2026 顶会论文

作者位次 #14/14CVPR 2026Poster· Computer Vision & Pattern Recognition

Evo-1: Lightweight Vision-Language-Action Model with Preserved Semantic Alignment

Tao Lin · Yilei Zhong · Yuxin Du · Jingjing Zhang · Jiting Liu · Yinxinyu Chen · Encheng Gu · Ziyan Liu · Hongyi Cai · Yanwen Zou · Lixing Zou · Zhaoye Zhou · Gen Li · Bo Zhao

对齐与偏好多模态OpenReview 项目页

作者位次 #5/8ACL 2026Poster· Natural Language Processing

G eo L aux: A Benchmark for Evaluating MLLM s’ Geometry Performance on Long-Step Problems Requiring Auxiliary Lines

Yumeng Fu · Jiayin Zhu · Lingling Zhang · Wenjun Wu · Bo Zhao · Shaoxuan Ma · Yushun Zhang · an Jiaotong University)

摘要

Geometry problem solving (GPS) poses significant challenges for Multimodal Large Language Models (MLLMs) in diagram comprehension, knowledge application, long-step reasoning, and auxiliary line construction. However, current benchmarks lack fine-grained evaluation for long-step problems necessita...

评测与基准推理多模态OpenReview 项目页

作者位次 #2/4AAAI 2026Poster· Artificial Intelligence