Related papers: GoAutoBash: Golang-based Multi-Thread Automatic Pu…

Automatic machine learning performs predictive modeling with high performing machine learning tools without human interference. This is achieved by making machine learning applications parameter-free, i.e. only a dataset is provided while…

Existing LLMs exhibit remarkable performance on various NLP tasks, but still struggle with complex real-world tasks, even equipped with advanced strategies like CoT and ReAct. In this work, we propose the CoAct framework, which transfers…

The proliferation of Large Language Models (LLMs) in recent years has realized many applications in various domains. Being trained with a huge of amount of data coming from various sources, LLMs can be deployed to solve different tasks,…

This paper presents a comprehensive evaluation of GitHub Copilot's deployment and impact on developer productivity at Zoominfo, a leading Go-To-Market (GTM) Intelligence Platform. We describe our systematic four-phase approach to evaluating…

As Graph Neural Networks (GNNs) become popular, libraries like PyTorch-Geometric (PyG) and Deep Graph Library (DGL) are proposed; these libraries have emerged as the de facto standard for implementing GNNs because they provide…

Dynamic parallelism on GPUs allows GPU threads to dynamically launch other GPU threads. It is useful in applications with nested parallelism, particularly where the amount of nested parallelism is irregular and cannot be predicted…

Long-horizon household tasks demand robust high-level planning and sustained reasoning capabilities, which are largely overlooked by existing embodied AI benchmarks that emphasize short-horizon navigation or manipulation and rely on fixed…

Data-flow is a natural approach to parallelism. However, describing dependencies and control between fine-grained data-flow tasks can be complex and present unwanted overheads. TALM (TALM is an Architecture and Language for Multi-threading)…

Large scale cloud data analytics applications are often CPU bound. Most of these cycles are wasted: benchmarks written in C++ run 10-51 times faster than frameworks such as Naiad and Spark. However, calling faster implementations from those…

Time-critical data aggregation in Internet of Things (IoT) networks demands efficient, collision-free scheduling to minimize latency for applications like smart cities and industrial automation. Traditional heuristic methods, with two-phase…

The Generator-Evaluator (G-E) framework, i.e., evaluating K sequences from a generator and selecting the top-ranked one according to evaluator scores, is a foundational paradigm in tasks such as Recommender Systems (RecSys) and Natural…

Beyond scratch coding, exploiting large-scale code repositories (e.g., GitHub) for practical tasks is vital in real-world software development, yet current benchmarks rarely evaluate code agents in such authentic, workflow-driven scenarios.…

Exploiting the full computational power of always deeper hierarchical multiprocessor machines requires a very careful distribution of threads and data among the underlying non-uniform architecture. The emergence of multi-core chips and NUMA…

Debugging distributed systems is hard. Most of the techniques that have been developed for debugging such systems use either extensive model checking, or postmortem analysis of logs and traces. Interactive debugging is typically a tool that…

The last improvements in programming languages, programming models, and frameworks have focused on abstracting the users from many programming issues. Among others, recent programming frameworks include simpler syntax, automatic memory…

We present GeoFlow, a method that automatically generates agentic workflows for geospatial tasks. Unlike prior work that focuses on reasoning decomposition and leaves API selection implicit, our method provides each agent with detailed…

Automatically generating scripts (i.e. sequences of key steps described in text) from video demonstrations and reasoning about the subsequent steps are crucial to the modern AI virtual assistants to guide humans to complete everyday tasks,…

This paper aims to develop a framework that enables a robot to execute tasks based on visual information, in response to natural language instructions for Fetch-and-Carry with Object Grounding (FCOG) tasks. Although there have been many…

As code completion task from function-level to repository-level, leveraging contextual information from large-scale codebases becomes a core challenge. However, existing retrieval-augmented generation (RAG) methods typically treat code as…

Deep research agents integrate fragmented evidence through multi-step tool use. BrowseComp offers a text-only testbed for such agents, but existing multimodal benchmarks rarely require both weak visual cues composition and BrowseComp-style…