Large Language Models (LLMs) have revolutionized interactions between human and artificial intelligence (AI) systems, demonstrating state-of-the-art performance across various domains, including scientific discovery and hypothesis generation. However, the absence of a comprehensive and systematic evaluation framework for LLM-driven research idea generation hinders a rigorous understanding of their strengths and limitations. To address this gap, we propose IdeaBench, a benchmark system that provides a structured dataset and evaluation framework for standardizing the assessment of research idea generation by LLMs. Our dataset comprises titles and abstracts from 2,374 influential papers across eight research domains, along with their 29,408 referenced works, creating a context-rich environment that mirrors human researchers' ideation processes. By profiling LLMs as domain-specific researchers and grounding them in similar contextual constraints, we directly leverage the models' knowledge learned from the pre-training stage to generate new research ideas. To systematically evaluate LLMs' research ideation capability and approximate human assessment, we propose a reference-based metric that aligns with human judgment to quantify idea quality with the assistance of LLMs. Through this evaluation, we find that while LLMs excel at generating novel ideas, they may struggle with generating feasible ideas. IdeaBench serves as a critical resource for benchmarking and comparing LLMs, ultimately advancing research on AI's role in automating scientific discovery.

Purpose: in the context of minimally invasive surgery, navigation in the patients abdomen is crucial, but is also more complicated than during open procedures. While the advantages for the patient are numerous, surgeons may not always know where they are in this complex environment, and getting used to this technique takes a lot of practice. Method: we present a novel smart trocar device that provides a global positioning system for the laparoscopic instruments that are inserted through the trocars. We augment current trocars with a camera pointing towards the ceiling. At any point in time, and by using computer vision as well as projective geometry, our smart trocar can provide the position of rigid instruments. Results: with our system, we reach one-millimeter accuracy on translation and half a degree on rotation with the only limitation being the velocity of surgeons movements. But this limitation has not been an obstacle in real practice. Conclusion: the trocar can track specific landmarks found on the ceiling of the OR, and, from these, accurately determine its global position in the OR in real time. Applications of this invention are first, assessment and/or training of surgical skills second, once our system is coupled to a real-time three-dimensional simulator of patient anatomy, we envision that our system can automatically provide surgical guidance during the procedure.

We present a novel 3-D region-based hidden Markov model (rbHMM) for efficient unsupervised 3-D image segmentation. Our contribution is twofold. First, rbHMM employs a more efficient representation of the image data than current state-of-the-art HMM-based approaches that are based on either voxels or rectangular lattices/grids, thus resulting in a faster optimization process. Second, our proposed novel tree-structured parameter estimation algorithm for the rbHMM provides a locally optimal data labeling that is invariant to object rotation, which is a highly valuable property in segmentation tasks, especially in medical imaging where the segmentation results need to be independent of patient positioning in scanners in order to minimize methodological variability in data analysis. We demonstrate the advantages of our proposed technique over grid-based HMMs by validating on synthetic images of geometric shapes as well as both simulated and clinical brain MRI scans. For the geometric shapes data, our method produced consistently accurate segmentation results that were also invariant to object rotation. For the brain MRI data, our white matter and gray matter segmentation resulted in substantially higher robustness and accuracy levels with improved Dice similarity indices of 4.60% (p=0.0022) and 7.71% , respectively.

The functionality of an information kiosk can be extended by allowing it to interact with a smartphone, as demonstrated by the Kimono system, and the user interface can be greatly simplified by "associations" between pieces of information. A kiosk provides information that is relevant to a particular location and can use valuable context information, such as the fact that a user is physically standing in front of the kiosk, to tailor the display. Its graphically rich screen is suitable for presenting information to the user and has a natural input modality requiring the user to simply touch the screen. However, a kiosk lacks mobility and cannot stay with the user as he or she moves about the environment. Also, information provided by the kiosk must be remembered by the user. Finally, it is difficult to add information to the kiosk, and so the kiosk remains an information display device.All this changes when a handset, such as a PDA or smart-phone, can interact with the kiosk. The handset acts like a personalized proxy of the kiosk. It accompanies the user serving as a memory device. It is also an excellent media creation device, capable of taking pictures and recording voice memos as well as short text messages. Associating newly created content with other currently selected content makes for a simpler user interface. Content and its associations can be uploaded to a kiosk allowing others to access to it.