Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2607. 05306v1 Announce Type: new Abstract: Integrating complex, multi-omics data presents significant challenges.
arXiv:2607. 01983v1 Announce Type: cross Abstract: Robust 3D object detection under adverse weather remains a critical hurdle for autonomous driving.
arXiv:2607. 03392v1 Announce Type: cross Abstract: The ever-increasing collection of personal data has created mounting pressure to develop technologies that protect sensitive aspects of individual identity.
arXiv:2304. 13917v4 Announce Type: replace Abstract: In recent years, there has been a surge in effort to formalize notions of fairness in machine learning.
arXiv:2607. 03166v1 Announce Type: cross Abstract: Template-based contrastive synthesis is scalable, but its candidates often differ only in a few entity-slots while sequence-level optimization spreads supervision over mostly shared templates.
arXiv:2607. 03190v1 Announce Type: cross Abstract: Scenario-based transportation analysis specifies future assumptions through aggregate population targets, whereas generative population synthesis models produce detailed individual-level realizations.
arXiv:2509. 14026v2 Announce Type: replace-cross Abstract: Variational quantum circuits (VQCs) are central to quantum machine learning, while recent progress in Kolmogorov-Arnold networks (KANs) highlights the power of learnable activation functions.
arXiv:2607. 03593v1 Announce Type: cross Abstract: Imaging signatures are quantitative features extracted from medical images that provide clinically meaningful information for tumor diagnosis, characterization, prognosis, and treatment planning.
arXiv:2607. 03598v1 Announce Type: cross Abstract: When a person shares something with a language model, the model often answers the surface of the message rather than what the sender was doing by sending it: share a finished project and it critiques the code; share a raw late-night line and it runs a wellness check.
arXiv:2605. 07961v2 Announce Type: replace Abstract: Federated fine-tuning (FFT) has emerged as a privacy-preserving paradigm for collaboratively adapting large language models (LLMs).
arXiv:2607. 03831v1 Announce Type: cross Abstract: Diffusion models have recently been repurposed for zero-shot classification, giving rise to diffusion classifiers that identify the best-matching text prompt by minimizing the noise-prediction error.
arXiv:2607. 03968v1 Announce Type: cross Abstract: Large language models are increasingly deployed as IDE-integrated coding agents that decompose tasks, generate and edit files, run code, and refine outputs over many turns.
arXiv:2607. 04422v1 Announce Type: cross Abstract: Recent NVFP4 pretraining methods mainly target transformer linear layers, leaving optimizer states, optimizer arithmetic and attention underexplored in 4-bit pipelines.
arXiv:2607. 04339v1 Announce Type: cross Abstract: Large generative models across text-to-text, text-to-image, and image-to-text modalities have been shown to pose significant privacy risks.
arXiv:2607. 04432v1 Announce Type: cross Abstract: A student model trained on pure uniform noise can still inherit its teacher's digit-classification ability, provided the two share initialization.
arXiv:2607. 04645v1 Announce Type: cross Abstract: Safety alignment in large language models is typically evaluated against direct, imperative harmful requests.
arXiv:2607. 04648v1 Announce Type: cross Abstract: Depression screening from large-scale behavioral data is challenged by fragmented circadian indicators, limited interpretability, and the lack of intervention-oriented analysis.
arXiv:2607. 04668v1 Announce Type: cross Abstract: On-device LLM decoding is a hard-barriered CPU-SIMD computation that wants every core for milliseconds per token, while the rest of the OS wants those same cores continuously.
arXiv:2607. 04681v1 Announce Type: cross Abstract: Embodied Chain-of-Thought has emerged as a promising mechanism to enhance robot decision-making and interpretability in black-box Vision-Language Action (VLA) models.
arXiv:2607. 05353v1 Announce Type: cross Abstract: Watermarking methods embed imperceptible and verifiable signals into text generated by large language models (LLMs).