Researcher — paper.dinq.me

2026 顶会论文

作者位次 #5/6ICLR 2026Poster· Theory / Domain Adaptation and Transfer Learning

Preserve and Sculpt: Manifold-Aligned Fine-tuning of Vision-Language Models for Few-Shot Learning

Dexia Chen · Qianjie Zhu · Weibing Li · Yue Yu · Tong Zhang · Ruixuan Wang

对齐与偏好多模态强化学习与后训练OpenReview

一作ACL 2026Poster· Natural Language Processing

S ci F low-Bench: Evaluating Structure-Aware Scientific Diagram Generation via Inverse Parsing

Tong Zhang · honglin lin · Zhou Liu · an Jiaotong University) · Wentao Zhang

摘要

Scientific diagrams convey explicit structural information, yet modern text-to-image models often produce visually plausible but structurally incorrect results. Existing benchmarks either rely on image-centric or subjective metrics insensitive to structure, or evaluate intermediate symbolic repre...

推理智能体与工具多模态OpenReview 项目页

作者位次 #6/7AAAI 2026Poster· Artificial Intelligence

Cross-Domain Few-Shot Learning via Multi-View Collaborative Optimization with Vision-Language Models

Dexia Chen · Wentao Zhang · Qianjie Zhu · Ping Hu · Weibing Li · Tong Zhang · Ruixuan Wang

多模态OpenReview

Tong Zhang

获取完整研究档案

联系方式

2026 顶会论文

Preserve and Sculpt: Manifold-Aligned Fine-tuning of Vision-Language Models for Few-Shot Learning

S ci F low-Bench: Evaluating Structure-Aware Scientific Diagram Generation via Inverse Parsing

Cross-Domain Few-Shot Learning via Multi-View Collaborative Optimization with Vision-Language Models

常见合作者