Related papers: Enhancing Deployment-Time Predictive Model Robustn…

Optimizing scientific software is a difficult task because codebases are often large and complex, and performance can depend upon several factors including the algorithm, its implementation, and hardware among others. Causes of poor…

The rapid advancement of pre-trained language models (PLMs) has demonstrated promising results for various code-related tasks. However, their effectiveness in detecting real-world vulnerabilities remains a critical challenge. While existing…

The multi-commodity flow (MCF) problem is a fundamental topic in network flow and combinatorial optimization, with broad applications in transportation, communication, and logistics, etc. Nowadays, the rapid expansion of allocation systems…

Large model training beyond tens of thousands of GPUs is an uncharted territory. At such scales, disruptions to the training process are not a matter of if, but a matter of when -- a stochastic process degrading training productivity.…

Large language models (LLMs) have demonstrated impressive capabilities in code generation, where the natural language prompt plays a crucial role in conveying user intent to the model. However, prior studies have shown that LLMs are highly…

Memory pressure has emerged as a dominant constraint in scaling the training of large language models (LLMs), particularly in resource-constrained environments. While modern frameworks incorporate various memory-saving techniques, they…

Generative Recommendation has emerged as a promising paradigm, reformulating recommendation as a sequence-to-sequence generation task over hierarchical Semantic IDs. However, existing methods suffer from a critical issue we term Semantic…

Recent advancements in improving the reasoning capabilities of Large Language Models have underscored the efficacy of Process Reward Models (PRMs) in addressing intermediate errors through structured feedback mechanisms. This study analyzes…

Visual Programming has recently emerged as an alternative to end-to-end black-box visual reasoning models. This type of method leverages Large Language Models (LLMs) to generate the source code for an executable computer program that solves…

Large Language Models (LLMs) demonstrate strong potential for automated code generation, yet their ability to iteratively refine solutions using execution feedback remains underexplored. Competitive programming offers an ideal testbed for…

While recent code-specific large language models (LLMs) have greatly enhanced their code generation capabilities, the safety of these models remains under-explored, posing potential risks as insecure code generated by these models may…

Although prompt engineering is central to unlocking the full potential of Large Language Models (LLMs), crafting effective prompts remains a time-consuming trial-and-error process that relies on human intuition. This study investigates…

Language Model Programs, i.e. sophisticated pipelines of modular language model (LM) calls, are increasingly advancing NLP tasks, but they require crafting prompts that are jointly effective for all modules. We study prompt optimization for…

With the decline of Moore's law, optimizing program performance has become a major focus of software research. However, high-level optimizations such as API and algorithm changes remain elusive due to the difficulty of understanding the…

Extreme-scale scientific applications can be more vulnerable to soft errors (transient faults) as high-performance computing systems increase in scale. The common practice to evaluate the resilience to faults of an application is random…

Code runtime optimization-the task of rewriting a given code to a faster one-remains challenging, as it requires reasoning about performance trade-offs involving algorithmic and structural choices. Recent approaches employ code-LLMs with…

Machine learning models trained on code and related artifacts offer valuable support for software maintenance but suffer from interpretability issues due to their complex internal variables. These concerns are particularly significant in…

Software fault prediction model are employed to optimize testing resource allocation by identifying fault-prone classes before testing phases. Several researchers' have validated the use of different classification techniques to develop…

Machine learning models are becoming the primary workhorses for many applications. Production services deploy models through prediction serving systems that take in queries and return predictions by performing inference on machine learning…

Code Smell, similar to a bad smell, is a surface indication of something tainted but in terms of software writing practices. This metric is an indication of a deeper problem lies within the code and is associated with an issue which is…