相关论文: Procrustean Bed for AI-Driven Retrosynthesis: A Un…

The evaluation of clustering algorithms can involve running them on a variety of benchmark problems, and comparing their outputs to the reference, ground-truth groupings provided by experts. Unfortunately, many research papers and graduate…

Neutral-atom quantum computing is among the most promising platforms for scalable quantum computation, and compilation toolchains are crucial for leveraging capabilities such as qubit shuttling and parallel gate execution. An important…

A composable infrastructure is defined as resources, such as compute, storage, accelerators and networking, that are shared in a pool and that can be grouped in various configurations to meet application requirements. This freedom to 'mix…

Recent advances in large language models (LLMs) and agent system designs have empowered agents with unprecedented levels of capability. However, existing agent benchmarks are showing a trend of rapid ceiling-hitting by newly developed…

The rise of multi-paradigm languages challenges traditional classification methods, leading to practical software engineering issues like interoperability defects. This systematic literature review (SLR) maps the formal foundations of…

We present the design and implementation of a RAG-based AI system benchmarking (RAGPerf) framework for characterizing the system behaviors of RAG pipelines. To facilitate detailed profiling and fine-grained performance analysis, RAGPerf…

In recent years, Artificial Intelligence has become a powerful partner for complex tasks such as data analysis, prediction, and problem-solving, yet its lack of transparency raises concerns about its reliability. In sensitive domains such…

The accelerating pace of research on autoregressive generative models has produced thousands of papers, making manual literature surveys and reproduction studies increasingly impractical. We present a fully open-source, reproducible…

AI agents hold the potential to revolutionize scientific productivity by automating literature reviews, replicating experiments, analyzing data, and even proposing new directions of inquiry; indeed, there are now many such agents, ranging…

Modern deterministic retrieval pipelines prioritize achieving state-of-the-art performance but often lack interpretability in decision-making. These models face challenges in assessing uncertainty, leading to overconfident predictions. To…

Deep learning recommendation systems must provide high quality, personalized content under strict tail-latency targets and high system loads. This paper presents RecPipe, a system to jointly optimize recommendation quality and inference…

Unstructured urban environments present unique challenges for scene understanding and generalization due to their complex and diverse layouts. We introduce SynthGenNet, a self-supervised student-teacher architecture designed to enable…

We study whether a structured recurrent state can serve as a compact associative backbone for language modeling while still supporting exact retrieval. We introduce UniMatrix, a Universal Transformer style family that reuses a shared…

Retrieval-augmented generation (RAG) has become the standard way to ground large language models in external knowledge, but many systems still organize evidence as flat chunks and retrieve it through largely unstructured search. This weak…

Although an ever-growing number of applications employ deep learning based systems for prediction, decision-making, or state estimation, almost no certification processes have been established that would allow such systems to be deployed in…

Most large-scale recommender systems follow a multi-stage cascade of retrieval, pre-ranking, ranking, and re-ranking. A key challenge at the pre-ranking stage arises from the heterogeneity of training instances sampled from coarse-grained…

Universal image restoration aims to recover clean images from arbitrary real-world degradations using a single inference model. Despite significant progress, existing all-in-one restoration networks do not scale to multiple degradations. As…

Co-designing efficient machine learning based systems across the whole hardware/software stack to trade off speed, accuracy, energy and costs is becoming extremely complex and time consuming. Researchers often struggle to evaluate and…

Complex information needs may involve set-compositional queries using conjunction, disjunction, and exclusion, yet it remains unclear whether current retrieval paradigms genuinely satisfy such constraints or exploit `semantic shortcuts'. We…

We present RAG Playground, an open-source framework for systematic evaluation of Retrieval-Augmented Generation (RAG) systems. The framework implements and compares three retrieval approaches: naive vector search, reranking, and hybrid…