Verilog code generation has emerged as a critical application for Large Language Models (LLMs) in Electronic Design Automation (EDA). However, existing benchmarks suffer from data contamination issues where training datasets overlap with evaluation problems, leading to artificially inflated performance. Additionally, periodically creating new benchmark problems is often too cost-prohibitive to be maintained by humans. In this paper, we propose LiveVerilogEval, a dynamic framework that automatically generates novel evaluation problems from existing RTL designs. LiveVerilogEval addresses both challenges by automatically generating mutated variants of valid Verilog designs while maintaining semantic correctness. Our experimental results demonstrate significant performance degradation across state-of-the-art LLMs when evaluated on LiveVerilogEval-enhanced benchmarks compared to traditional static benchmarks, revealing that LLM-based Verilog generation remains challenging and confirming the effectiveness of our contamination-free evaluation approach.

Formal verification is a major bottleneck in integrated circuit (IC) design due to the inefficiency and inaccuracy of manual assertion writing and the limitations of existing automation approaches. While large language models (LLMs) offer a promising alternative for assertion generation, their effectiveness has been constrained by the scarcity of high-quality, formally verified training data. To address these challenges, we propose AutoAssert, an framework of automated assertion generation leveraging formal equivalence checking into the assertion generation pipeline, and introduce TrustAssert, a public dataset containing 110K formally verified assertions. By fine-tuning LLMs on TrustAssert, we achieve substantial improvements across four representative hardware modules. Our approach significantly outperforms GPT-4 in terms of the ratio of non-trivial assertions generated, syntactic correctness, and functional verification accuracy.

The seafloor is a complex environment and it is challenging to conduct detailed mapping, soil composition sampling, and habitat characterization missions in this benthic region. As a step toward overcoming these challenges, we present a quadruped robot capable of walking on the seafloor and maneuvering via midfluid swimming. SELQIE, the Seafloor Environment Legged Quadruped Intelligent Explorer, is capable of walking underwater at speeds up to$0.2 ~\mathrm{m} / \mathrm{s}$, swimming at over$0.16 ~\mathrm{m} / \mathrm{s}$, and transitioning between modes. We also introduce a path planning algorithm that can account for both swimming and walking gaits to efficiently navigate around or over obstacles, and demonstrate the robot executing such a multi-modal trajectory.

As we build our legged robots smaller and cheaper, stable and agile control without expensive inertial sensors becomes increasingly important. We seek to enable versatile dynamic behaviors on robots with limited modes of state feedback, specifically proprioceptive-only sensing. This work uses model-based trajectory optimization methods to design open-loop stable motion primitives. We specifically design running gaits for a single-legged planar robot, and can generate motion primitives in under 3 seconds, approaching online-capable speeds. A direct-collocation-formulated optimization generated axial force profiles for the direct-drive robot to achieve desired running speed and apex height. When implemented in hardware, these trajectories produced open-loop stable running. Further, the measured running achieved the desired speed within 10% of the speed specified for the optimization in spite of having no control loop actively measuring or controlling running speed. Additionally, we examine the shape of the optimized force profile and observe features that may be applicable to open-loop stable running in general.

OBJECTIVE: A research prototype Physician Workstation (PWS) incorporating a graphical user interface and a drug ordering module was compared with the existing hospital information system in an academic Veterans Administration General Medical Clinic. Physicians in the intervention group received recommendations for drug substitutions to reduce costs and were alerted to potential drug interactions. The objective was to evaluate the effect of the PWS on user satisfaction, on health-related outcomes, and on costs. DESIGN: A one-year, two-period, randomized controlled trial with 37 subjects. MEASUREMENTS: Differences in the reliance on noncomputer sources of information, in user satisfaction, in the cost of prescribed medications, and in the rate of clinically relevant drug interactions were assessed. RESULTS: The study subjects logged onto the workstation an average of 6.53 times per provider and used it to generate 2.8% of prescriptions during the intervention period. On a five-point scale (5 = very satisfied, 1 = very dissatisfied), user satisfaction declined in the PWS group (3.44 to 2.98 p = 0.008), and increased in the control group (3.23 to 3.72, p < 0.0001). CONCLUSION: The intervention physicians did not use the PWS frequently enough to influence information-seeking behavior, health outcomes, or cost. The study design did not determine whether the poor usage resulted from satisfaction with the control system, problems using the PWS intervention, or the functions provided by the PWS intervention. Evaluative studies should include provisions to improve the chance of successful implementation as well as to yield maximum information if a negative study occurs.