Related papers: LibEvolutionEval: A Benchmark and Study for Versio…

The constant introduction of standardized benchmarks in the literature has helped accelerating the recent advances in meta-learning research. They offer a way to get a fair comparison between different algorithms, and the wide range of…

AlphaEvolve (Novikov et al., 2025) is a generic evolutionary coding agent that combines the generative capabilities of LLMs with automated evaluation in an iterative evolutionary framework that proposes, tests, and refines algorithmic…

This paper presents LibMTL, an open-source Python library built on PyTorch, which provides a unified, comprehensive, reproducible, and extensible implementation framework for Multi-Task Learning (MTL). LibMTL considers different settings…

Deep learning frameworks have often focused on either usability or speed, but not both. PyTorch is a machine learning library that shows that these two goals are in fact compatible: it provides an imperative and Pythonic programming style…

Almost all applications stop scaling at some point; those that don't are seldom performant when considering time to solution on anything but aspirational/unicorn resources. Recognizing these tradeoffs as well as greater user functionality…

Large language models (LLMs) for code are increasingly used in software development, but they remain static after pretraining while APIs and software libraries continue to evolve. Model editing offers a lightweight alternative to retraining…

Multiple Instance Learning (MIL) is a powerful framework for weakly supervised learning, particularly useful when fine-grained annotations are unavailable. Despite growing interest in deep MIL methods, the field lacks standardized tools for…

Code large language models (LLMs) enhance programming by understanding and generating code across languages, offering intelligent feedback, bug detection, and code updates through reflection, improving development efficiency and…

How to evaluate Large Language Models (LLMs) in code generation remains an open question. Existing benchmarks have two limitations - data leakage and lack of domain-specific evaluation. The former hurts the fairness of benchmarks, and the…

To evaluate the repository-level code generation capabilities of Large Language Models (LLMs) in complex real-world software development scenarios, many evaluation methods have been developed. These methods typically leverage contextual…

Learning continually from non-stationary data streams is a long-standing goal and a challenging problem in machine learning. Recently, we have witnessed a renewed and fast-growing interest in continual learning, especially within the deep…

Code generation models can help improve many common software tasks ranging from code completion to defect prediction. Most of the existing benchmarks for code generation LLMs focus on code authoring or code completion. Surprisingly, there…

Large Language Models (LLMs) have made tremendous strides in code generation, but existing research fails to account for the dynamic nature of software development, marked by frequent library updates. This gap significantly limits LLMs'…

We introduce CodeEvolve, an open-source framework that couples large language models with island-based evolutionary search for end-to-end algorithmic discovery. CodeEvolve integrates inspiration-based crossover, meta-prompting, and…

Code large language models (Code LLMs) have made significant progress in code generation by translating natural language descriptions into functional code; however, real-world applications often demand stricter adherence to detailed…

While large language models (LLMs) have shown considerable promise in code generation, real-world software development demands advanced repository-level reasoning. This includes understanding dependencies, project structures, and managing…

There is a need for open-source libraries in emission tomography that (i) use modern and popular backend code to encourage community contributions and (ii) offer support for the multitude of reconstruction techniques available in recent…

Continual Learning is an important and challenging problem in machine learning, where models must adapt to a continuous stream of new data without forgetting previously acquired knowledge. While existing frameworks are built on PyTorch, the…

Long contexts of recent LLMs have enabled a new use case: asking models to find security vulnerabilities in entire codebases. To evaluate model performance on this task, we introduce eyeballvul: a benchmark designed to test the…

Python third-party libraries (TPLs) are essential in modern software development, but upgrades often cause compatibility issues, leading to system failures. These issues fall into two categories: version compatibility issues (VCIs) and code…