Analog circuit sizing is a critical challenge due to increasing circuit complexity and diverse performance requirements. Existing algorithms struggle with poor scalability in highdimensional spaces and frequent convergence to local optima. To address these limitations, we propose MOSTAR, a multi-stage hierarchical Bayesian optimization framework that integrates a local-to-global GNN (L2G-GNN). L2G-GNN identifies circuit substructures and adds symmetric constraints to the circuit. MOSTAR employs additive Gaussian processes and stage-adaptive constrained acquisition function to improve scalability in highdimensional circuits. Furthermore, its dynamic search space adjustment strategy helps avoid local optima during optimization. Experiments show that our L2G-GNN achieves a substructure identification accuracy of 97.22%, and MOSTAR achieves an optimization performance improvement ranging from $1.04 \times$ to $4.13 \times$ on three basic circuits and two high-dimensional circuits, highlighting its efficacy in automating complex analog circuit sizing.

Large Language Model (LLM) agents have demonstrated impressive capabilities for social interaction and are increasingly being deployed in situations where they might engage with both human and artificial agents. These interactions represent a critical frontier for LLM-based agents, yet existing evaluation methods fail to measure how well these capabilities generalize to novel social situations. In this paper, we introduce a method for evaluating the ability of LLM-based agents to cooperate in zero-shot, mixed-motive environments using Concordia, a natural language multi-agent simulation environment. Our method measures general cooperative intelligence by testing an agent's ability to identify and exploit opportunities for mutual gain across diverse partners and contexts. We present empirical results from the NeurIPS 2024 Concordia Contest, where agents were evaluated on their ability to achieve mutual gains across a suite of diverse scenarios ranging from negotiation to collective action problems. Our findings reveal significant gaps between current agent capabilities and the robust generalization required for reliable cooperation, particularly in scenarios demanding persuasion and norm enforcement.

Automatic transistor sizing in circuit design continues to be a formidable challenge. Despite that Bayesian optimization (BO) has achieved significant success, it is circuit-specific, limiting the accumulation and transfer of design knowledge for broader applications. This paper proposes (1) efficient automatic kernel construction, (2) the first transfer learning across different circuits and technology nodes for BO, and (3) a selective transfer learning scheme to ensure only useful knowledge is utilized. These three novel components are integrated into BO with Multi-objective Acquisition Ensemble (MACE) to form Knowledge Alignment and Transfer Optimization (KATO) to deliver state-of-the-art performance: up to 2x simulation reduction and 1.2x design improvement over the baselines.

Yield estimation and optimization have become increasingly important for circuit design as technology nodes scale down. Simple yet well-established minimal norm importance sampling (MNIS) still serves as an industrial standard due to its robustness and reliability. In this study, we generalize the classic MNIS and propose Every Failure Is A Lesson (EFIAL) to utilize every failure sample (instead of one in MNIS) to construct the proposal distribution. EFIAL is completely tuning-free and the update computation complexity is only O(M) (M is the number of failure samples) by utilizing the blessing of dimensionality. The idea of EFIAL is then extended to the state-of-the-art (SOTA) pre-sampling method, onion sampling, to significantly boost efficiency, by up to 9.08x (4.68x on average). Extensive evaluations against SOTA yield estimation methods reveal that EFIAL achieves a speedup of up to 13.54x (5.16x on average) and an accuracy improvement of up to 24.91%.

Convolutional Neural Networks (CNNs) have been widely applied in biomedical image classification, but the classification of upper gastrointestinal diseases, especially gastric cancer, has not been further studied. In this paper, we compare the difference between the medical image and the natural image. We have found that simply making the network structure deeper does not improve the performance of medical image classification model, and sometimes it will be worse. Inspired by the residual connection, we propose a shallow network model, which can converge quickly and achieve high accuracy. In an upper digestive tract classification dataset, we demonstrate the proposed model can achieve high accuracy.

With the continuous development of deep learning technology, the application scope of convolutional neural network (CNN) in image recognition is expanding. The classification of medical images has become a new application field of CNN. How to quickly train the CNN with high accuracy has become an important problem in the process of training. The training method based on error feedback sampling effectively improves the training efficiency by adding the error samples in each epoch to the next epoch while training. This method obtains a higher accuracy rate than the general sampling method in the test of upper digestive tract diseases classification.

Recent work has shown success in using neural network as ranking model in question answering(QA). While the precision of these models has increased significantly over time, most models need long training time, which leads to it cannot be used effectively in practical applications. In this paper, we propose a simple model to accelerate training speed with noise-contrastive estimation. This model mainly inspired by an architecture based entirely on convolutional neural networks and noise-contrastive estimation. We investigate the behavior of the model on the financial dataset which we use in practice and show that it reduces the training times by more than an order of magnitude without affecting the quality of the resulting models. The model is also more efficient and more stable than importance sampling because it requires fewer noise samples to perform well.