Related papers: Kimina Lean Server: A High-Performance Lean Server…

Evaluating outputs of large language models (LLMs) is challenging, requiring making -- and making sense of -- many responses. Yet tools that go beyond basic prompting tend to require knowledge of programming APIs, focus on narrow domains,…

In the last few years, research and development on Deep Learning models and techniques for ultra-low-power devices in a word, TinyML has mainly focused on a train-then-deploy assumption, with static models that cannot be adapted to newly…

Synthetic verification techniques such as generating test cases and reward modelling are common ways to enhance the coding capabilities of large language models (LLM) beyond predefined tests. Additionally, code verification has recently…

Optimizing communication performance is imperative for large-scale computing because communication overheads limit the strong scalability of parallel applications. Today's network cards contain rather powerful processors optimized for data…

In this project, we explore the concept of invertibility applied to serialisation and lexing frameworks. Recall that, on one hand, serialisation is the process of taking a data structure and writing it to a bit array while parsing is the…

Reinforcement learning with verifiable rewards (RLVR) has improved the reasoning ability of large language models, yet training remains costly because many rollouts contribute little to optimization, considering the amount of computation…

We report on the experience of developing Merlin, a language server for the OCaml programming language in development since 2013. Merlin is a daemon that connects to your favourite text editor and provides services that require a…

The rapid adoption of machine learning (ML) has underscored the importance of serving ML models with high throughput and resource efficiency. Traditional approaches to managing increasing query demands have predominantly focused on hardware…

As hardware systems grow in complexity, security verification must keep up with them. Recently, artificial intelligence (AI) and large language models (LLMs) have started to play an important role in automating several stages of the…

Large Language Model (LLM) based listwise ranking has shown superior performance in many passage ranking tasks. With the development of Large Reasoning Models (LRMs), many studies have demonstrated that step-by-step reasoning during…

We present a versatile GPU-based parallel version of Logistic Regression (LR), aiming to address the increasing demand for faster algorithms in binary classification due to large data sets. Our implementation is a direct translation of the…

In software development, the predominant emphasis on functionality often supersedes security concerns, a trend gaining momentum with AI-driven automation tools like GitHub Copilot. These tools significantly improve developers' efficiency in…

Parallel computing is very important to accelerate the performance of software systems. Additionally, considering that a recurring challenge is to process high data volumes continuously, stream processing emerged as a paradigm and software…

When large AI models are deployed as cloud-based services, clients have no guarantee that responses are correct or were produced by the intended model. Rerunning inference locally is infeasible for large models, and existing cryptographic…

Reinforcement learning (RL) has become a pivotal technology in the post-training phase of large language models (LLMs). Traditional task-colocated RL frameworks suffer from significant scalability bottlenecks, while task-separated RL…

Fine-tuning large language models (LLMs) is crucial for adapting them to specific tasks, yet it remains computationally demanding and raises concerns about correctness and privacy, particularly in untrusted environments. Although…

Executing complex terminal tasks remains a significant challenge for open-weight LLMs, constrained by two fundamental limitations. First, high-fidelity, executable training environments are scarce: environments synthesized from real-world…

Large Language Models drive a wide range of modern AI applications but impose substantial challenges on large-scale serving systems due to intensive computation, strict latency constraints, and throughput bottlenecks. We introduce…

SaLinA is a simple library that makes implementing complex sequential learning models easy, including reinforcement learning algorithms. It is built as an extension of PyTorch: algorithms coded with \SALINA{} can be understood in few…

Large Language Models (LLMs) generate functionally correct solutions but often fall short in code efficiency, a critical bottleneck for real-world deployment. In this paper, we introduce a novel test-time iterative optimization framework to…