Related papers: Hybrid Inlining: A Compositional and Context Sensi…

Compositional generalization-a key open challenge in modern machine learning-requires models to predict unknown combinations of known concepts. However, assessing compositional generalization remains a fundamental challenge due to the lack…

Hybrid approaches that combine data-driven learning with physics-based insight have shown promise for improving the reliability of industrial condition monitoring. This work develops a hybrid condition monitoring framework that integrates…

Text embeddings from Large Language Models (LLMs) have become foundational for numerous applications. However, these models typically operate on raw text, overlooking the rich structural information, such as hyperlinks or citations, that…

In-context learning (ICL) approaches typically leverage prompting to condition decoder-only language model generation on reference information. Just-in-time processing of a context is inefficient due to the quadratic cost of self-attention…

Hybrid sequence models that combine efficient Transformer components with linear sequence modeling blocks are a promising alternative to pure Transformers, but most are still pretrained from scratch and therefore fail to reuse existing…

Static analyses aspire to explore all possible executions in order to achieve soundness. Yet, in practice, they fail to capture common dynamic behavior. Enhancing static analyses with dynamic information is a common pattern, with tools such…

Matching is one of the most widely used study designs for adjusting for measured confounders in observational studies. However, unmeasured confounding may exist and cannot be removed by matching. Therefore, a sensitivity analysis is…

Context-sensitive global analysis of large code bases can be expensive, which can make its use impractical during software development. However, there are many situations in which modifications are small and isolated within a few…

As terminal agents scale to long-horizon, multi-turn workflows, a key bottleneck is not merely limited context length, but the accumulation of noisy terminal observations in the interaction history. Retaining raw observations preserves…

We consider the problem of making expressive static analyzers interactive. Formal static analysis is seeing increasingly widespread adoption as a tool for verification and bug-finding, but even with powerful cloud infrastructure it can take…

To put static program analysis at the fingertips of the software developer, we propose a framework for interactive abstract interpretation. While providing sound analysis results, abstract interpretation in general can be quite costly. To…

Long-context large language models remain computationally expensive to run and often fail to reliably process very long inputs, which makes context compression an important component of many systems. Existing compression approaches…

An interprocedural analysis is precise if it is flow sensitive and fully context-sensitive even in the presence of recursion. Many methods of interprocedural analysis sacrifice precision for scalability while some are precise but limited to…

Critical transitions - abrupt, often irreversible changes in system dynamics - arise across human and natural systems, often with catastrophic consequences. Real-world observations of such shifts remain scarce, preventing the development of…

Recent advances in large language and vision-language models have enabled zero-shot inference, allowing models to solve new tasks without task-specific training. Various adaptation techniques such as prompt engineering, In-Context Learning…

Large language models (LLMs) process entire input contexts indiscriminately, which is inefficient when the information required to answer a query is localized within the context. We present dynamic context cutoff, a novel method enabling…

We introduce a novel method for multilingual transfer that utilizes deep contextual embeddings, pretrained in an unsupervised fashion. While contextual embeddings have been shown to yield richer representations of meaning compared to their…

Large Language Models are increasingly deployed as judges (LaaJ) in code generation pipelines. While attractive for scalability, LaaJs tend to overlook domain specific issues raising concerns about their reliability in critical evaluation…

Machine data is central to observability and diagnosis in modern computing systems, appearing in logs, metrics, telemetry traces, and configuration snapshots. When provided to large language models (LLMs), this data typically arrives as a…

In-context learning enables language models (LM) to adapt to downstream data or tasks by incorporating few samples as demonstrations within the prompts. It offers strong performance without the expense of fine-tuning. However, the…