Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2502. 18959v4 Announce Type: replace Abstract: The architecture of a neural network and the choice of its activation function are both fundamental to its performance.
arXiv:2606. 25627v1 Announce Type: new Abstract: Distributed intelligent systems increasingly need to train across data silos without centralizing raw data.
arXiv:2512. 02080v3 Announce Type: replace-cross Abstract: The integration of Formal Verification tools with Large Language Models (LLMs) offers a path to scale software verification beyond manual workflows.
arXiv:2606. 26057v1 Announce Type: cross Abstract: AI agents are granted access to tools, APIs, and other infrastructure, making them active principals in those systems.
arXiv:2507. 09052v3 Announce Type: replace-cross Abstract: Training data for class-conditional image synthesis often exhibit a long-tailed distribution with limited amount of images for tail classes.
arXiv:2604. 07904v2 Announce Type: replace Abstract: Spatiotemporal neural dynamics and oscillatory synchronization are widely implicated in biological information processing and have been hypothesized to support flexible coordination such as feature binding.
arXiv:2606. 25606v1 Announce Type: cross Abstract: Given the widespread prevalence of depression and its consequential impact on individuals and society, it is crucial to obtain objective measures for early diagnosis and intervention.
arXiv:2606. 25548v1 Announce Type: cross Abstract: Image generative models are trained on massive, largely uncurated internet-scale datasets that contain undesirable visual concepts.
arXiv:2606. 25434v1 Announce Type: new Abstract: Early and scalable detection of mild cognitive impairment (MCI) remains an unresolved clinical challenge.
arXiv:2606. 25750v1 Announce Type: cross Abstract: Safety evaluation of large language models (LLMs) is commonly performed by querying models with unsafe or jailbreak prompts and judging whether their outputs violate a safety policy.
arXiv:2606. 26037v1 Announce Type: cross Abstract: Federated learning has emerged as the foremost approach for decentralized model training with privacy preservation.
arXiv:2602. 14772v2 Announce Type: replace Abstract: The Winner Determination Problem (WDP) in combinatorial auctions is NP-hard, and no existing method reliably predicts which instances will defeat fast greedy heuristics.
arXiv:2606. 19380v3 Announce Type: replace-cross Abstract: Software engineering and deployment are increasingly delegated to AI coding agents.
arXiv:2505. 23866v2 Announce Type: replace Abstract: Deep neural networks have been increasingly used in safety-critical applications such as medical diagnosis and autonomous driving.
arXiv:2606. 24964v1 Announce Type: new Abstract: Understanding the features of large language models (LLMs) is a central goal of interpretability.
arXiv:2606. 25073v1 Announce Type: new Abstract: In cooperative multi-agent reinforcement learning (MARL), from a deployment perspective, it is challenging and expensive to train agents from scratch for each new environment or task.
arXiv:2606. 26071v1 Announce Type: new Abstract: A central goal of safety research is determining whether a model is misaligned.
arXiv:2606. 26079v1 Announce Type: cross Abstract: Standard benchmarks for multimodal large language models (MLLMs) score each item on one canonical ordering and miss whether order-irrelevant shuffling changes the answer, a baseline reliability property called for by emerging AI evaluation guidelines.
arXiv:2606. 25293v1 Announce Type: new Abstract: Positional encodings (PEs) are essential for Transformers.
arXiv:2602. 05704v2 Announce Type: replace Abstract: Understanding the limitations of gradient methods, and stochastic gradient descent (SGD) in particular, is a central challenge in learning theory.