Related papers: DeclareAligner: A Leap Towards Efficient Optimal A…
AI alignment aims to make AI systems behave in line with human intentions and values. As AI systems grow more capable, so do risks from misalignment. To provide a comprehensive and up-to-date overview of the alignment field, in this survey,…
As the complexity of the HPC storage stack rapidly grows, domain scientists face increasing challenges in effectively utilizing HPC storage systems to achieve their desired I/O performance. To identify and address I/O issues, scientists…
AI alignment research is the field of study dedicated to ensuring that artificial intelligence (AI) benefits humans. As machine intelligence gets more advanced, this research is becoming increasingly important. Researchers in the field…
Conformance checking techniques allow us to quantify the correspondence of a process's execution, captured in event data, w.r.t., a reference process model. In this context, alignments have proven to be useful for calculating conformance…
Patient recruitment remains a major bottleneck in clinical trials, calling for scalable and automated solutions. We present TrialMatchAI, an AI-powered recommendation system that automates patient-to-trial matching by processing…
Large Language Models (LLMs) like GPT-4, MedPaLM-2, and Med-Gemini achieve performance competitively with human experts across various medical benchmarks. However, they still face challenges in making professional diagnoses akin to…
Agentic Reinforcement Learning (RL) has empowered Large Language Models (LLMs) to utilize tools like Python interpreters for complex problem-solving. However, for parameter-constrained models (e.g., 4B--7B), the exploration phase is often…
Alignment is the most critical step in building large language models (LLMs) that meet human needs. With the rapid development of LLMs gradually surpassing human capabilities, traditional alignment methods based on human-annotation are…
In AI alignment, extensive latitude must be granted to annotators, either human or algorithmic, to judge which model outputs are `better' or `safer.' We refer to this latitude as alignment discretion. Such discretion remains largely…
Recent improvements in large language models have opened new opportunities for accelerating and automating scientific workflows. In parallel, modern collider analyses are becoming increasingly complex and demand substantial programming and…
With the growing number of devices, sensors and digital systems, data logs may become uncertain due to, e.g., sensor reading inaccuracies or incorrect interpretation of readings by processing programs. At times, such uncertainties can be…
Large language models (LLMs) have exhibited impressive reasoning abilities on a wide range of complex tasks. However, enhancing these capabilities through post-training remains resource intensive, particularly in terms of data and…
Conventionally, AI models are thought to trade off explainability for lower accuracy. We develop a training strategy that not only leads to a more explainable AI system for object classification, but as a consequence, suffers no perceptible…
We formalize AI alignment as a multi-objective optimization problem called $\langle M,N,\varepsilon,\delta\rangle$-agreement, in which a set of $N$ agents (including humans) must reach approximate ($\varepsilon$) agreement across $M$…
The deployment of AI models in clinical practice faces a critical challenge: models achieving expert-level performance on benchmarks can fail catastrophically when confronted with real-world variations in medical imaging. Minor shifts in…
As AI-powered compliance monitoring becomes increasingly important in public governance and industrial safety, the ability to provide verifiable evidence and traceable accountability signals is essential. However, existing video anomaly…
Large language models (LLMs) have demonstrated strong coding capabilities but still struggle to solve competitive programming problems correctly in a single attempt. Execution-based re-ranking offers a promising test-time scaling strategy,…
The rapid adoption of generative artificial intelligence (AI) in educational assessment has created new opportunities for scalable item creation, personalized feedback, and efficient formative evaluation. However, despite advances in…
Visual document retrieval aims to retrieve a set of document pages relevant to a query from visually rich collections. Existing methods often employ Vision-Language Models (VLMs) to encode queries and visual pages into a shared embedding…
Modeling interactive driving behaviors in complex scenarios remains a fundamental challenge for autonomous driving planning. Learning-based approaches attempt to address this challenge with advanced generative models, removing the…