Large Language Models (LLMs) present massive inherent knowledge and superior semantic comprehension capability, which have revolutionized various tasks in natural language processing. Despite their success, a critical gap remains in enabling LLMs to perform knowledge graph completion (KGC). Empirical evidence suggests that LLMs consistently perform worse than conventional KGC approaches, even through sophisticated prompt design or tailored instruction-tuning. Fundamentally, applying LLMs on KGC introduces several critical challenges, including a vast set of entity candidates, hallucination issue of LLMs, and under-exploitation of the graph structure. To address these challenges, we propose a novel instruction-tuning-based method, namely FtG. Specifically, we present a \textit{filter-then-generate} paradigm and formulate the KGC task into a multiple-choice question format. In this way, we can harness the capability of LLMs while mitigating the issue casused by hallucinations. Moreover, we devise a flexible ego-graph serialization prompt and employ a structure-text adapter to couple structure and text information in a contextualized manner. Experimental results demonstrate that FtG achieves substantial performance gain compared to existing state-of-the-art methods. The instruction dataset and code are available at \url{https://github.com/LB0828/FtG}.

Current deep learning-based solutions for image analysis tasks are commonly incapable of handling problems to which multiple different plausible solutions exist. In response, posterior-based methods such as conditional Diffusion Models and Invertible Neural Networks have emerged; however, their translation is hampered by a lack of research on adequate validation. In other words, the way progress is measured often does not reflect the needs of the driving practical application. Closing this gap in the literature, we present the first systematic framework for the application-driven validation of posterior-based methods in inverse problems. As a methodological novelty, it adopts key principles from the field of object detection validation, which has a long history of addressing the question of how to locate and match multiple object instances in an image. Treating modes as instances enables us to perform mode-centric validation, using well-interpretable metrics from the application perspective. We demonstrate the value of our framework through instantiations for a synthetic toy example and two medical vision use cases: pose estimation in surgery and imaging-based quantification of functional tissue parameters for diagnostics. Our framework offers key advantages over common approaches to posterior validation in all three examples and could thus revolutionize performance assessment in inverse problems.

We present the BrainScaleS-2 mobile system as a compact analog inference engine based on the BrainScaleS-2 ASIC and demonstrate its capabilities at classifying a medical electrocardiogram dataset. The analog network core of the ASIC is utilized to perform the multiply-accumulate operations of a convolutional deep neural network. At a system power consumption of 5.6 W, we measure a total energy consumption of 192 µJ for the ASIC and achieve a classification time of 276 µs per electrocardiographic patient sample. Patients with atrial fibrillation are correctly identified with a detection rate of (93.7 0.7) % at (14.0 1.0) % false positives. The system is directly applicable to edge inference applications due to its small size, power envelope, and flexible I/O capabilities. It has enabled the BrainScaleS-2 ASIC to be operated reliably outside a specialized lab setting. In future applications, the system allows for a combination of conventional machine learning layers with online learning in spiking neural networks on a single neuromorphic platform.

Photoacoustic tomography (PAT) has the potential to recover morphological and functional tissue properties with high spatial resolution. However, previous attempts to solve the optical inverse problem with supervised machine learning were hampered by the absence of labeled reference data. While this bottleneck has been tackled by simulating training data, the domain gap between real and simulated images remains an unsolved challenge. We propose a novel approach to PAT image synthesis that involves subdividing the challenge of generating plausible simulations into two disjoint problems: (1) Probabilistic generation of realistic tissue morphology, and (2) pixel-wise assignment of corresponding optical and acoustic properties. The former is achieved with Generative Adversarial Networks (GANs) trained on semantically annotated medical imaging data. According to a validation study on a downstream task our approach yields more realistic synthetic images than the traditional model-based approach and could therefore become a fundamental step for deep learning-based quantitative PAT (qPAT).

The team, led by Dr Tobias Buck, will combine cutting-edge methods of machine learning with high-resolution cosmological computer simulations in …

First, the very high variability in the morphology of the tissues can be incompatible with the prior knowledge embedded within the algorithms. Second, the availability of MR images of distorted brains is very scarce, so the methods in the literature have not addressed such cases so far. In this work, we present the first evaluation of state-of-the-art automatic tissue segmentation pipelines on T1-weighted images of brains with different severity of congenital or acquired brain distortion. We compare traditional pipelines and a deep learning model, i.e. a 3D U-Net trained on normal-appearing brains. Unsurprisingly, traditional pipelines completely fail to segment the tissues with strong anatomical distortion. Surprisingly, the 3D U-Net provides useful segmentations that can be a valuable starting point for manual refinement by experts/neuroradiologists.

Neural networks in both biological settings and artificial intelligence distribute computation across their neurons to solve complex tasks. New research now shows how so-called "critical states" can be used to optimize artificial neural networks running on brain-inspired neuromorphic hardware. The study was carried out by scientists from Heidelberg University working within the Human Brain Project, and the Max-Planck-Institute for Dynamics and Self-Organization (MPIDS). The results have been published in Nature Communications. Many computational properties are maximized when the dynamics of a network are at a "critical point", a state where systems can quickly change their overall characteristics in fundamental ways, transitioning e.g. between order and chaos or stability and instability. Therefore, the critical state is widely assumed to be optimal for any computation in recurrent neural networks, which are used in many AI applications.

Neuromorphic computing – brain inspired computing – has long been a tantalizing goal. The human brain does with around 20 watts what supercomputers do with megawatts. While neuromorphic computing progress has been intriguing, it has still not proven very practical. This week neuromorphic computing takes another step forward with a workshop being offered to users from academia, industry and education interested in using two European neuromorphic systems that have been years in development and are coming online for broader use – the BrainScaleS system launching at the Kirchhoff Institute for Physics of Heidelberg University and SpiNNaker, a complementary approach and similarly sized system at the University of Manchester. Ramping up BrainScaleS and SpiNNaker is an important milestone, strengthening Europe's position in hardware development for alternative computing. Both projects are part of the European Human Brain Project, originally funded by the European Commission's Future Emerging Technologies program (2005-2015).