Publications

Synthetic network traffic generation has emerged as a promising alternative for various data-driven applications in the networking domain. It enables the creation of synthetic data that preserves real-world characteristics while addressing key challenges such as data scarcity, privacy concerns, and purity constraints associated with real data. In this survey, we provide a comprehensive review of synthetic network traffic generation approaches, covering essential aspects such as data types and generation models. With the rapid advancements in Artificial Intelligence (AI) and Machine Learning (ML), we focus particularly on deep learning (DL)-based techniques while also providing a detailed discussion of statistical methods and their extensions, including commercially available tools. We present a comprehensive comparison of generation approaches and provide an AI tool to apply this comparison for any network traffic dataset.

Large Language Models (LLMs) have demonstrated impressive capabilities in code generation. While an interactive feedback loop can improve performance, writing effective tests is a non-trivial task. Early multi-agent frameworks, such as AgentCoder, automated this process but relied on generated tests as absolute ground truth. This approach is fragile: incorrect code frequently passes faulty or trivial tests, while valid solutions are often degraded to satisfy incorrect assertions. Addressing this limitation, newer methods have largely abandoned test generation in favor of planning and reasoning based on examples. We argue, however, that generated tests remain a valuable signal if we model them as noisy sensors guided by bayesian updates. To this end, we introduce BACE (Bayesian Anchored Co-Evolution), a framework that reformulates synthesis as a Bayesian co-evolutionary process where code and test populations are evolved, guided by belief distributions that are reciprocally updated based on noisy interaction evidence. By anchoring this search on minimal public examples, BACE prevents the co-evolutionary drift typical of self-validating loops. Extensive evaluations on LiveCodeBench v6 (post-March 2025) reveal that BACE achieves superior performance across both proprietary models and open-weight small language models.

The clinical adoption of biomedical vision-language models is hindered by prompt optimization techniques that produce either uninterpretable latent vectors or single textual prompts. This lack of transparency and failure to capture the multi-faceted nature of clinical diagnosis, which relies on integrating diverse observations, limits their trustworthiness in high-stakes settings. To address this, we introduce BiomedXPro, an evolutionary framework that leverages a large language model as both a biomedical knowledge extractor and an adaptive optimizer to automatically generate a diverse ensemble of interpretable, natural-language prompt pairs for disease diagnosis. Experiments on multiple biomedical benchmarks show that BiomedXPro consistently outperforms state-of-the-art prompt-tuning methods, particularly in data-scarce few-shot settings. Furthermore, our analysis demonstrates a strong semantic alignment between the discovered prompts and statistically significant clinical features, grounding the model's performance in verifiable concepts. By producing a diverse ensemble of interpretable prompts, BiomedXPro provides a verifiable basis for model predictions, representing a critical step toward the development of more trustworthy and clinically-aligned AI systems.

Twenty20 International (T20I) cricket’s volatile nature makes static metrics inadequate for strategic decision-making. This paper presents a ball-by-ball, over-by-over analysis to capture the temporal dynamics of T20I matches, utilizing a comprehensive dataset of 1,118 men’s T20Is. Our analysis shows a sharp disconnect between Powerplay runs and later scoring (Pearson’s r = 0.129), but a strong penalty for Powerplay wickets, underscoring the premium on early wicket preservation. We demonstrate that strike-rate progression, not overall strike rate, is the more informative indicator of a batter’s role, some accelerate late (e.g., Kohli), while others sustain high rates from the start (e.g., de Villiers). Contextual analysis further reveals how statistics can mislead: for example, MS Dhoni’s contributions understate his value as a finisher when match situations are considered. Beyond individuals, we find that home advantage …