Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2607. 01553v1 Announce Type: cross Abstract: Transformers have become general-purpose architectures, but their all-to-all self-attention is poorly matched to graph data, whose interactions are sparse, structured and multi-scale.
arXiv:2607. 01940v1 Announce Type: cross Abstract: Mechanistic interpretability often relies on component-level interventions to discover how a model produces a behavior.
arXiv:2603. 02196v3 Announce Type: replace Abstract: An agent must try new behaviors to explore and improve.
arXiv:2607. 02089v1 Announce Type: cross Abstract: Vision-language models (VLMs) have achieved strong performance across diverse multimodal tasks, yet they remain vulnerable to unreliable reasoning.
arXiv:2607. 01417v1 Announce Type: new Abstract: Conditional inference trees (CIT) and conditional inference forests (CIF) reduce split-selection bias by testing features before choosing split thresholds, but repeated permutation tests and threshold searches can make these methods computationally expensive.
arXiv:2607. 01492v1 Announce Type: new Abstract: Recent work has established a fundamental trilemma between Byzantine robustness, local differential privacy (LDP), and optimization error in distributed learning.
arXiv:2503. 07570v3 Announce Type: replace-cross Abstract: Deep learning, when integrated with a large amount of training data, has the potential to outperform machine learning in terms of high accuracy.
arXiv:2607. 02186v1 Announce Type: new Abstract: Software development is a complex task that demands cooperation among agents with diverse roles.
arXiv:2607. 02104v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used as cheap, scalable judges that compare candidate outputs pairwise -- to rank responses, select models, or triage papers.
arXiv:2607. 02291v1 Announce Type: new Abstract: Conventional reinforcement learning strategies for visual generation typically employ sample-wise reward functions, yet this practice frequently results in reward hacking that degrades image diversity and introduces visual anomalies.
arXiv:2607. 02447v1 Announce Type: new Abstract: Recent research has introduced distributed self-supervised learning (D-SSL) approaches to leverage vast amounts of unlabeled decentralized data.
arXiv:2607. 01902v1 Announce Type: cross Abstract: Reliable confidence estimates are essential in semantic segmentation, especially in safety-critical settings where overconfident errors can mislead downstream decisions.
arXiv:2607. 02201v1 Announce Type: cross Abstract: The rapid deployment of AI systems across high-stakes domains has created urgent demand for standardized evaluation, yet the field remains fragmented across competing risk taxonomies that catalog risks without showing how an audit is executed.
arXiv:2607. 02072v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed in domains requiring guardrails to detect unsafe, off-topic, or adversarial prompts.
arXiv:2607. 01236v1 Announce Type: cross Abstract: As LLM agents gain increasing access to powerful tools, ensuring that their actions are aligned with the user's intent becomes critical.
arXiv:2607. 01951v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly consulted on contested scientific questions, raising the concern that they will sycophantically retreat from established consensus when a user signals doubt -- drifting toward a false balance that treats settled science as one view among several.
arXiv:2607. 01548v1 Announce Type: cross Abstract: Large language models are increasingly used as open-ended search operators in evolutionary optimization.
arXiv:2607. 01365v1 Announce Type: cross Abstract: Given one or more images of a railway crossing, can we leverage visual cues that allow us to robustly estimate how safe it is?
arXiv:2607. 01444v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) models offer inference speedups via selective activation but impose substantial memory requirements because the whole network must remain loaded.
arXiv:2607. 01907v1 Announce Type: cross Abstract: Semi-supervised generative adversarial networks (SSL-GANs) can exploit large unlabeled datasets while retaining a classifier in the discriminator, but their training is often unstable.