Yifan Peng

Jul 23, 2024 | nature.com | Qiao Jin |Fangyuan Chen |Yiliang Zhou |Justin F. Rousseau |Marc Landsman |Sally Baxter | +5 more

AbstractRecent studies indicate that Generative Pre-trained Transformer 4 with Vision (GPT-4V) outperforms human physicians in medical challenge tasks. However, these evaluations primarily focused on the accuracy of multi-choice questions alone.

May 8, 2024 | nature.com | Manu Gopakumar |Suyeon Choi |Brian Chao |Yifan Peng |Jonghyun Kim |Gordon Wetzstein | +1 more

Emerging spatial computing systems seamlessly superimpose digital information on the physical environment observed by a user, enabling transformative experiences across various domains, such as entertainment, education, communication and training1–3. However, the widespread adoption of augmented-reality (AR) displays has been limited due to the bulky projection optics of their light engines and their inability to accurately portray three-dimensional (3D) depth cues for virtual content, among other factors4,5. Here we introduce a holographic AR system that overcomes these challenges using a unique combination of inverse-designed full-colour metasurface gratings, a compact dispersion-compensating waveguide geometry and artificial-intelligence-driven holography algorithms. These elements are co-designed to eliminate the need for bulky collimation optics between the spatial light modulator and the waveguide and to present vibrant, full-colour, 3D AR content in a compact device form factor. To deliver unprecedented visual quality with our prototype, we develop an innovative image formation model that combines a physically accurate waveguide model with learned components that are automatically calibrated using camera feedback. Our unique co-design of a nanophotonic metasurface waveguide and artificial-intelligence-driven holographic algorithms represents a significant advancement in creating visually compelling 3D AR experiences in a compact wearable device. We develop a method for providing high-quality, holographic, three-dimensional augmented-reality images in a small form factor suitable for incorporation in eyeglass-scale wearables, using high-refraction-index glass waveguides with nanoscale metasurfaces, and incorporating artificial intelligence.

Aug 12, 2023 | arxiv.org | Jian Chen |Yifan Peng |Cong Sun

[Submitted on 12 Aug 2023 ( v1 ), last revised 25 Oct 2024 (this version, v2)] Title:Demonstration-based learning for few-shot biomedical named entity recognition under machine reading comprehension View a PDF of the paper titled Demonstration-based learning for few-shot biomedical named entity recognition under machine reading comprehension, by Leilei Su and 3 other authors View PDF HTML (experimental) Abstract:Although deep learning techniques have shown significant achievements, they...

May 23, 2023 | nature.com | Yifan Peng |Justin F. Rousseau

Evidence-based medicine (EBM) requires the retrieval and ranking of relevant evidence by epistemological strength, to identify the most appropriate evidence to inform guidelines and policies, with a preference for robust evidence from randomized clinical trials (RCTs), systematic reviews, and meta-analyses.