Related papers: Composer 2 Technical Report
Assembly-to-source code translation is a critical task in reverse engineering, cybersecurity, and software maintenance, yet systematic benchmarks for evaluating large language models on this problem remain scarce. In this work, we present…
The hallmark of Deep Research agents lies in compositional reasoning, the capacity to aggregate distributed, heterogeneous information into coherent logical insights. However, current agentic systems are often retrieval-heavy but…
Knowledge of quantum mechanical systems is becoming more important for many science and engineering students who are looking to join the emerging quantum workforce. To better prepare a wide range of students for these careers, we must seek…
Computer use agents automate digital tasks by directly interacting with graphical user interfaces (GUIs) on computers and mobile devices, offering significant potential to enhance human productivity by completing an open-ended space of user…
Testing is the most widely employed method to find vulnerabilities in real-world software programs. Compositional analysis, based on symbolic execution, is an automated testing method to find vulnerabilities in medium- to large-scale…
This paper aims to introduce a robust singing voice synthesis (SVS) system to produce very natural and realistic singing voices efficiently by leveraging the adversarial training strategy. On one hand, we designed simple but generic random…
Alignment research focuses on making individual AI systems reliable. Human institutions achieve reliable collective behaviour differently: they mitigate the risk posed by misaligned individuals through organisational structure. Multi-agent…
Reliable Docker-based environment construction is a dominant bottleneck for scaling execution-grounded training and evaluation of software engineering agents. We introduce DockSmith, a specialized agentic Docker builder designed to address…
Symbolic music generation has made significant progress, yet achieving fine-grained and flexible control over composer style remains challenging. Existing training-based methods for composer style conditioning depend on large labeled…
AI agents hold growing promise for accelerating scientific discovery; yet, a lack of frontier evaluations hinders adoption into real workflows. Expert-written benchmarks have proven effective at measuring AI reasoning, but most at this…
New low-precision accelerators, vector instruction sets, and library functions make maximizing accuracy and performance of numerical code increasingly challenging. Two lines of work$\unicode{x2013}$traditional compilers and numerical…
Designing effective agentic systems requires the seamless composition and integration of agents, tools, and models within dynamic and uncertain environments. Most existing methods rely on static, semantic retrieval approaches for tool or…
Deep learning models are widely used across computer vision and other domains. When working on the model induction, selecting the right architecture for a given dataset often relies on repetitive trial-and-error procedures. This procedure…
The design of complex machines stands as both a marker of human intelligence and a foundation of engineering practice. Given recent advances in large language models (LLMs), we ask whether they, too, can learn to create. We approach this…
We introduce Composer's Assistant, a system for interactive human-computer composition in the REAPER digital audio workstation. We consider the task of multi-track MIDI infilling when arbitrary track-measures have been deleted from a…
We propose the expert composer policy, a framework to reliably expand the skill repertoire of quadruped agents. The composer policy links pair of experts via transitions to a sampled target state, allowing experts to be composed…
Music performance synthesis aims to synthesize a musical score into a natural performance. In this paper, we borrow recent advances in text-to-speech synthesis and present the Deep Performer -- a novel system for score-to-audio music…
Code completion is a popular software development tool integrated into all major IDEs. Many neural language models have achieved promising results in completion suggestion prediction on synthetic benchmarks. However, a recent study When…
Can large language model agents develop industry-level mobile applications? We introduce \textbf{SWE-Bench Mobile}, a benchmark for evaluating coding agents on realistic software engineering tasks derived from a production iOS codebase.…
Coding agents are rapidly changing the landscape of software development, moving from inline completion to autonomous systems that edit repositories, open pull requests, respond to issues, and run scheduled or webhook triggered routines…