Researcher — paper.dinq.me

2026 顶会论文

一作ECCV 2026Poster

ChronoFlow Policy: Unifying Past-Future Interaction Flow in Visuomotor Policy Learning

Bokai Lin · Yifu Xu · Xinyu Zhan · Hongjie Fang · Jialin Tian · Fu-Cheng Zhang · Yong-Lu Li · Cewu Lu · Lixin Yang

Embodied AI, Robotics & Autonomous DrivingOpenReview

一作SIGIR 2026Oral· Information Retrieval (Full)

Cross-Domain Interest Representation Learning for Scenario- and Task-Aware Recommendation

Bokai Lin · Naijun Gao · Yucen Gao · Heng Chang · Cheng Hu · Zhinan Zhang · Xiaofeng Gao

摘要

Many internet companies operate multiple flagship applications, each of which can be regarded as a distinct business domain, covering areas such as video, reading, and gaming. Within each domain, diverse recommendation scenarios coexist, and users engage in various tasks with heterogeneous behavi...

多模态代码对齐与偏好OpenReview

作者位次 #2/7IROS 2026Poster· Sensing and Predicting Human Motion for Robots

LIDEA: Human-To-Robot Imitation Learning Via Implicit Feature Distillation and Explicit Geometry Alignment

Yifu Xu · Bokai Lin · Xinyu Zhan · Hongjie Fang · Yong-Lu Li · Cewu Lu · Lixin Yang

对齐与偏好强化学习与后训练数据与预训练Imitation LearningDatasets for Human MotionData Sets for Robot LearningOpenReview

Bokai Lin

获取完整研究档案

联系方式

2026 顶会论文

ChronoFlow Policy: Unifying Past-Future Interaction Flow in Visuomotor Policy Learning

Cross-Domain Interest Representation Learning for Scenario- and Task-Aware Recommendation

LIDEA: Human-To-Robot Imitation Learning Via Implicit Feature Distillation and Explicit Geometry Alignment

常见合作者