Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2607. 09099v1 Announce Type: new Abstract: While multi-agent debate (MAD) frameworks have shown significant potential in general reasoning, their effectiveness in highly structured, knowledge-heavy legal domains remains under-explored.
arXiv:2607. 08867v1 Announce Type: cross Abstract: Cloud-based deep learning enables large-scale medical image analysis but raises significant privacy concerns when sensitive patient images are outsourced for model development.
arXiv:2607. 09349v1 Announce Type: cross Abstract: Retrieval-augmented generation evaluation checks whether model claims are factually grounded in retrieved documents.
arXiv:2607. 09328v1 Announce Type: cross Abstract: Answering complex questions over long documents frequently requires integrating evidence that the source itself disperses naturally across distant passages.
arXiv:2607. 08843v1 Announce Type: new Abstract: In artificial and biological neural networks, concepts are often encoded as consistent linear directions in representation space.
arXiv:2603. 25029v4 Announce Type: replace Abstract: We study online convex optimization (OCO) with two-point bandit feedback against a non-anticipating adaptive adversary.
arXiv:2607. 09481v1 Announce Type: cross Abstract: Text-guided medical image segmentation leverages clinical semantics to improve lesion delineation, yet many existing models bind cross-modal fusion, supervision, and decoder design into a task-specific architecture.
arXiv:2607. 09065v1 Announce Type: cross Abstract: Software engineering (abbrev.
arXiv:2607. 09113v1 Announce Type: cross Abstract: Data scarcity and class imbalance are persistent challenges in machine learning that degrade model generalization and introduce predictive bias.
arXiv:2607. 09405v1 Announce Type: new Abstract: Similarity search is a primary application of embedding models trained by contrastive learning.
arXiv:2607. 08954v1 Announce Type: cross Abstract: We study nonasymptotic convergence of primal-dual methods for a class of nonconvex constrained optimization problems with a convex-composite structure.
arXiv:2605. 12920v3 Announce Type: replace-cross Abstract: Effective collaboration between embodied agents requires more than acting in a shared environment; it demands communication grounded in each agent's evolving understanding of the world.
arXiv:2607. 09562v1 Announce Type: cross Abstract: Medical Vision-Language Models (VLMs) exhibit strong zero-shot performance, yet their effectiveness still declines on out-of-distribution (OOD) data due to domain shifts and class bias inherited from large-scale pretraining.
arXiv:2607. 08953v1 Announce Type: new Abstract: Algorithmic fairness methods are increasingly used to identify and mitigate bias in machine learning models, yet most approaches are evaluated in isolation and along single demographic axes.
arXiv:2607. 08773v1 Announce Type: new Abstract: In this work we present a rigorous theoretical framework to a foundational problem of AI safety, namely adversarial robustness.
arXiv:2607. 08839v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) are typically designed under the assumption that all modalities available during training will also be accessible at inference.
arXiv:2607. 09450v1 Announce Type: cross Abstract: Pre-trained Vision-Language Models (VLMs) such as CLIP achieve strong zero-shot generalization, but their performance degrades sharply under adversarial perturbations.
arXiv:2607. 09134v1 Announce Type: cross Abstract: Representation alignment (REPA) has been investigated to accelerate diffusion training, but we observe that regularizing intermediate representations in diffusion Transformers (DiT) may implicitly entangle latents and limit generative capacity.
arXiv:2405. 16361v4 Announce Type: replace Abstract: To protect privacy in regulated domains such as healthcare and finance, model owners may allow only remote API access while keeping both the training data and model parameters private.
arXiv:2607. 09480v1 Announce Type: cross Abstract: The human visual system (HVS) employs foveated sampling and eye movements to achieve efficient perception, conserving both metabolic energy and computational resources.