Yankai Jiang

Affiliations:
  • Shanghai AI Laboratory, China


According to our database1, Yankai Jiang authored at least 28 papers between 2024 and 2026.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

On csauthors.net:

Bibliography

2026
VITAL: Visual-Semantic Dual Supervision for Enhanced and Interpretable Latent Reasoning in Medical MLLMs.
CoRR, May, 2026

SafeMed-R1: Clinician-Audited Safety and Ethics Alignment for Medical Large Language Models.
CoRR, May, 2026

MolClaw: An Autonomous Agent with Hierarchical Skills for Drug Molecule Evaluation, Screening, and Optimization.
CoRR, April, 2026

MedScope: Incentivizing "Think with Videos" for Clinical Reasoning via Coarse-to-Fine Tool Calling.
CoRR, February, 2026

Beyond Static Tools: Test-Time Tool Evolution for Scientific Reasoning.
CoRR, January, 2026

IBISAgent: Reinforcing Pixel-Level Visual Reasoning in MLLMs for Universal Biomedical Object Referring and Segmentation.
CoRR, January, 2026

2025
SCP: Accelerating Discovery with a Global Web of Autonomous Scientific Agents.
CoRR, December, 2025

Incentivizing Tool-augmented Thinking with Images for Medical Image Analysis.
CoRR, December, 2025

Unleashing Scientific Reasoning for Bio-experimental Protocol Generation via Structured Component-based Reward Mechanism.
CoRR, October, 2025

Think Twice to See More: Iterative Visual Reasoning in Medical VLMs.
CoRR, October, 2025

RareAgent: Self-Evolving Reasoning for Drug Repurposing in Rare Diseases.
CoRR, October, 2025

Mediator-Guided Multi-Agent Collaboration among Open-Source Models for Medical Decision-Making.
CoRR, August, 2025

Enhancing Step-by-Step and Verifiable Medical Reasoning in MLLMs.
CoRR, June, 2025

TK-Mamba: Marrying KAN with Mamba for Text-Driven 3D Medical Image Segmentation.
CoRR, May, 2025

A Data-Efficient Pan-Tumor Foundation Model for Oncology CT Interpretation.
CoRR, February, 2025

From Screens to Scenes: A Survey of Embodied AI in Healthcare.
CoRR, January, 2025

ROFI: a deep learning-based ophthalmic sign-preserving and reversible patient face anonymizer.
npj Digit. Medicine, 2025

From screens to scenes: A survey of embodied AI in healthcare.
Inf. Fusion, 2025

Chiron-o1: Igniting Multimodal Large Language Models towards Generalizable Medical Reasoning via Mentor-Intern Collaborative Search.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2025, 2025

Reasoning-Enhanced Vision-Language Model for Interpretable Diabetic Retinopathy Detection in Ultra-Wide-Field Fundus Images.
Proceedings of the Ophthalmic Medical Image Analysis - 12th International Workshop, 2025

Kernel-based Unsupervised Embedding Alignment for Enhanced Visual Representation in Vision-language Models.
Proceedings of the Forty-second International Conference on Machine Learning, 2025

Unleashing the Potential of Vision-Language Pre-Training for 3D Zero-Shot Lesion Segmentation via Mask-Attribute Alignment.
Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Semantics Versus Identity: A Divide-and-Conquer Approach Towards Adjustable Medical Image De-Identification.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2025

Towards All-in-One Medical Image Re-Identification.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2025

Advancing Generalizable Tumor Segmentation with Anomaly-Aware Open-Vocabulary Attention Maps and Frozen Foundation Diffusion Models.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2025

Flow2Code: Evaluating Large Language Models for Flowchart-based Code Generation Capability.
Proceedings of the Findings of the Association for Computational Linguistics, 2025

2024
CAT: Coordinating Anatomical-Textual Prompts for Multi-Organ and Tumor Segmentation.
Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 2024

ZePT: Zero-Shot Pan-Tumor Segmentation via Query-Disentangling and Self-Prompting.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024


  Loading...