We present RASO, a foundation model designed to Recognize Any Surgical Object, offering robust open-set recognition capabilities across a broad range of surgical procedures and object classes, in both surgical images and videos. RASO leverages a novel weakly-supervised learning framework that generates tag-image-text pairs automatically from large-scale unannotated surgical lecture videos, significantly reducing the need for manual annotations. Our scalable data generation pipeline gathers 2,200 surgical procedures and produces 3.6 million tag annotations across 2,066 unique surgical tags. Our experiments show that RASO achieves improvements of 2.9 mAP, 4.5 mAP, 10.6 mAP, and 7.2 mAP on four standard surgical benchmarks respectively in zero-shot settings, and surpasses state-of-the-art models in supervised surgical action recognition tasks. We will open-source our code, model, and dataset to facilitate further research.

This brief introduces an adaptive continuous-time linear equalizer (CTLE) featuring a sub-sampled delay-locked loop (DLL) based clock recovery circuit. This circuit incorporates an inverse bang-bang phase detector (PD) that samples data at a one-sixteenth rate. A digitally tunable, inverter-based multiphase clock generator produces three clock phases for PD operation. The early and late signals from the PD output are used to estimate the eye opening of the incoming 4-level pulse amplitude modulation (PAM-4) data. Our adaptive algorithm utilizes the averaged early/late signals to digitally tune CTLE parameters, such as degeneration resistance and capacitance. The prototype chip, integrating both the CTLE and clock recovery circuit, is implemented in a 65 nm CMOS process. Post-layout simulations indicate a combined power consumption of 46.8 mW for the CTLE and clock recovery circuit at 40 Gb/s, achieving an energy efficiency of 1.17 pJ/b.

Federated learning is a distributed machine learning setting in which clients train a global model on their local data and share their knowledge with the server in form of the trained model while maintaining privacy of the data. The server aggregates clients' knowledge to create a generalized global model. Two major challenges faced in this process are data heterogeneity and high communication cost. We target the latter and propose a simple approach, BAFL (Federated Learning for Base Ablation) for cost effective communication in federated learning. In contrast to the common practice of employing model compression techniques to reduce the total communication cost, we propose a fine-tuning approach to leverage the feature extraction ability of layers at different depths of deep neural networks. We use a model pretrained on general-purpose large scale data as a global model. This helps in better weight initialization and reduces the total communication cost required for obtaining the generalized model. We achieve further cost reduction by focusing only on the layers responsible for semantic features (data specific information). The clients fine tune only top layers on their local data. Base layers are ablated while transferring the model and clients communicate parameters corresponding to the remaining layers. This results in reduction of communication cost per round without compromising the accuracy. We evaluate the proposed approach using VGG-16 and ResNet-50 models on datasets including WBC, FOOD-101, and CIFAR-10 and obtain up to two orders of reduction in total communication cost as compared to the conventional federated learning. We perform experiments in both IID and Non-IID settings and observe consistent improvements.