Microsoft Research Asia – Shanghai
News & features
CausCell：虚拟细胞进入“白盒时代”
编者按：在生命科学研究中，逼真且可解释的细胞模型一直备受期待。但现有的单细胞 AI 建模多依赖于深度神经网络等“黑盒”方法，难以解开高维组学数据背后的生物学因果机制。近日，微软亚洲研究院（上海）与同济大学合作在 《自然-通讯》（Nature Communications）杂志上发表了最新成果 CausCell。这一框架首次将结构因果模型与扩散模型深度融合，实现了细胞尺度的因果解耦表征与可控的反事实…
OPA-DPO：多模态大模型幻觉难题的高效解决方案
编者按：在视觉多模态大语言模型的快速发展中，幻觉问题一直是研究者们关注的焦点。模型生成与输入图像不一致甚至虚假的内容，不仅影响用户体验，也阻碍了多模态技术在实际场景中的落地。对此，微软亚洲研究院和香港中文大学的联合研究团队从直接偏好优化（DPO）入手，提出了 On-Policy Alignment (OPA)-DPO 算法，可通过确保训练数据与初始策略（reference policy）的一致性，…
Metasurface: Unlocking the future of wireless sensing and communication
| Lili Qiu and Hao Pan
Metasurfaces explore engineered 2D materials that manipulate electromagnetic and mechanical waves, offering advances in wireless tech. They can power indoor GPS, extend 5G/6G coverage, and enable wireless sensing and imaging.
创新智能表面，解锁无线通信与无线感知的未来
编者按：无线通信与无线感知技术正在悄然改变着人类认知和联系世界的方式，让我们的生活更智能、更便捷。从智能设备的无缝连接到智能家居的便捷管理，从自动驾驶的精准导航到智慧医疗的实时监测，无线技术应用的重要性如今愈发凸显。微软亚洲研究院（上海）的研究员们发挥奇思妙想，在无线通信与无线感知研究领域中不断探索、创新，通过将超表面技术与 GNSS、毫米波、微波炉加热、音频传播的研究相结合，为解决现实问题提供了…
Research Focus: Week of December 2, 2024
Can a new SOS-RMT protocol enable more efficient CL-MPC?; A fair-by-design, cloud-based algorithmic trading platform; LLM2CLIP unlocks richer visual representation; New technique enhances Low-Rank Adaptation’s expressiveness, generalization capabilities.
Innovations in AI: Brain-inspired design for more capable and sustainable technology
| Dongsheng Li, Dongqi Han, and Yansen Wang
Researchers and their collaborators are drawing inspiration from the brain to develop more sustainable AI models. Projects like CircuitNet and CPG-PE improve performance and energy efficiency by mimicking the brain’s neural patterns.
Research Focus: Week of August 26, 2024
Learn what’s next for AI at Research Forum on Sept. 3; WizardArena simulates human-annotated chatbot games; MInference speeds pre-filling for long-context LLMs via dynamic sparse attention; Reef: Fast succinct non-interactive zero-knowledge regex proofs.
Synergizing habits and goals with variational Bayes: A new framework for biological and artificial embodied agents
| Dongqi Han
The Bayesian behavior framework synergizes habits and goals through variational Bayesian methods, offering new insights on sensorimotor behavior and comprehension of actions.
“If life is a marathon, then health is the key to its duration.” Health is not only the foundation of happiness and societal progress but also a pivotal aspect of the intelligent era. AI’s integration into healthcare represents a transformative…