Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2608. 06727v1 Announce Type: new Abstract: Transformer models for high-dimensional omics analysis process thousands of genes or pathways, although only a subset requires deep computation.
arXiv:2608. 06732v1 Announce Type: new Abstract: Recent text-to-video (T2V) generation models enable fake news videos to be synthesized from scratch, shifting the threat beyond cheap fakes assembled from existing footage.
arXiv:2608. 06871v1 Announce Type: new Abstract: Complex systems, core objects of study in artificial life, model diverse phenomena through nonlinear, feedback-driven interactions that produce emergent behavior, with applications from population dynamics and biology to economic policy and strategic decision-making.
arXiv:2608. 06912v1 Announce Type: new Abstract: The top-$k$ operation is a fundamental building block of modern sparse computation, enabling token routing, expert activation, memory selection, and attention pruning.
arXiv:2608. 06949v1 Announce Type: new Abstract: Prior benchmarking work has shown that a single large language model (LLM), forced to make life-or-death resource-allocation decisions, exhibits measurable demographic bias.
arXiv:2608. 07007v1 Announce Type: new Abstract: Federated Learning (FL) enables collaborative machine learning (ML) across distributed clients while preserving privacy.
arXiv:2608. 06748v1 Announce Type: cross Abstract: Probabilistic long-term time-series forecasting commonly relies on trained models.
arXiv:2608. 07430v1 Announce Type: cross Abstract: Diffusion Large Language Models (DLLMs) replace autoregressive next-token prediction with iterative parallel denoising, yet their internal safety mechanisms remain poorly understood.
arXiv:2608. 07446v1 Announce Type: cross Abstract: Rapid adoption of large language models (LLMs) in enterprise settings has introduced operational, security, and governance risks.
arXiv:2608. 06429v1 Announce Type: cross Abstract: Interpretability methods for large language models (LLMs) describe internal state but do not directly test whether that state is causally sufficient to produce the observed behavior.
arXiv:2608. 06536v1 Announce Type: cross Abstract: Nonadiabatic dynamics needs an excited-state gradient and an interstate nonadiabatic coupling matrix element (NACME) at every nuclear geometry, and a double-hybrid functional's accuracy has been unavailable for the coupling.
arXiv:2608. 06469v1 Announce Type: cross Abstract: Collaborative machine learning among financial institutions must be both group-fair and robust against deliberate adversarial manipulation.
arXiv:2608. 06946v1 Announce Type: cross Abstract: In gossip learning, a network of nodes trains a shared model collaboratively, without a central coordinator, by repeatedly exchanging parts of their local models.
arXiv:2603. 27723v2 Announce Type: replace Abstract: Multimodal-attributed graphs (MAGs) are a fundamental data structure for multimodal graph learning (MGL), enabling both graph-centric and modality-centric tasks.
arXiv:2608. 06674v1 Announce Type: cross Abstract: Adversarial vulnerabilities remain a major concern for the safe deployment of neural networks, particularly in object detection, a core task embedded in many safety-critical systems.
arXiv:2608. 06865v1 Announce Type: cross Abstract: The malicious use of generative artificial intelligence to create highly realistic deepfake videos raises serious ethical concerns and poses substantial challenges to AI safety.
arXiv:2608. 06613v1 Announce Type: cross Abstract: Self-supervised 3D medical foundation models are increasingly used as general-purpose feature extractors, yet their sensitivity to MRI artifacts remains poorly understood.
arXiv:2608. 06929v1 Announce Type: cross Abstract: Regional image editing has attracted considerable attention for its spatial controllability.
arXiv:2608. 07063v1 Announce Type: cross Abstract: Content provenance standards, such as C2PA, are increasingly used to attach signed records of origin, editing history, and rights to digital images.
arXiv:2608. 06545v1 Announce Type: new Abstract: Distributionally robust Markov decision processes provide a principled framework for sequential decision making under model uncertainty.