Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2602. 21819v3 Announce Type: replace-cross Abstract: Reconstructing dynamic visual experiences from brain activity provides a compelling avenue for exploring the neural mechanisms of human visual perception.
arXiv:2608. 14646v1 Announce Type: cross Abstract: Interpretable representation learning remains a key challenge in modern neural computation, particularly when models are expected not only to perform but also to explain their reasoning.
arXiv:2608. 14654v1 Announce Type: cross Abstract: Federated Learning (FL) is a collaborative paradigm that enables multiple devices to train a global model while preserving local data privacy.
arXiv:2604. 26866v2 Announce Type: replace-cross Abstract: Large language models (LLMs) acquire most of their factual knowledge during the pre-training stage, through next token prediction.
arXiv:2602. 21219v2 Announce Type: replace-cross Abstract: Large Language Model (LLM) personalization holds great promise for tailoring responses by leveraging personal context and history.
arXiv:2601. 11496v3 Announce Type: replace-cross Abstract: AI agents increasingly mediate bargaining, negotiation and persuasion for people and firms.
arXiv:2608. 15310v1 Announce Type: cross Abstract: Multimodal data collected by heterogeneous devices are used for collaborative training, where federated learning (FL) serves as a key paradigm for effective distributed modeling with data privacy preservation.
arXiv:2510. 15042v3 Announce Type: replace-cross Abstract: In the 3D medical image domain, vision-language pre-training is used to create vision-language encoders (VLEs) that can support radiologists by retrieving patients with similar abnormalities, predicting likelihoods of abnormality, or, with downstream adaptation, generating radiological reports.
arXiv:2608. 15660v1 Announce Type: cross Abstract: Federated learning (FL) enables privacy-preserving distributed model training but faces challenges from heterogeneous model architectures and limited communication resources at the network edge.
arXiv:2608. 16340v1 Announce Type: cross Abstract: The combination of traditional statistical models and neural network (NN) components into semi-structured hybrid models is an intriguing approach to construct models that, ideally, combine traditional interpretability with the unprecedented flexibility of NNs.
arXiv:2608. 16347v1 Announce Type: cross Abstract: Direct communication between AI systems relies on natural language as an intermediate layer, incurring encoding/decoding overhead, token cost, and latency.
arXiv:2608. 16454v1 Announce Type: cross Abstract: Terahertz time-domain spectroscopy (THz-TDS) based on air-plasma generation and balanced air-biased coherent detection offers gap-free broadband coverage, but individual continuous-scan traces are strongly affected by pulse-to-pulse fluctuations and electronic noise.
arXiv:2510. 22819v3 Announce Type: replace Abstract: The convergence analysis of online learning algorithms is central to machine learning theory, where the last-iterate convergence is particularly important, as it captures the learner's actual decisions and describes the evolution of the learning process over time.
arXiv:2509. 21514v4 Announce Type: replace Abstract: Research on Knowledge Tracing (KT) models traditionally focuses on improving predictive accuracy.
arXiv:2601. 10161v3 Announce Type: replace-cross Abstract: Named Entity Recognition (NER) and Personally Identifiable Information (PII) anonymization are critical tasks in Natural Language Processing (NLP) for information extraction and privacy preservation.
arXiv:2608. 14876v1 Announce Type: cross Abstract: Agentic coding assistants are finding widespread use, not just in new code development but in quickly ingesting and leveraging third-party code.
arXiv:2608. 16664v1 Announce Type: cross Abstract: We study the Random Quadratic Form (RQF) on a sphere in the presence of random Brownian forcing.
arXiv:2608. 15153v1 Announce Type: cross Abstract: Differentially private federated learning must balance privacy protection against model accuracy and training efficiency.
arXiv:2507. 19894v2 Announce Type: replace Abstract: With the rapid advancement of generative models, privacy, copyright, safety, and reliability risks have attracted growing attention.
arXiv:2608. 15980v1 Announce Type: cross Abstract: Preference benchmarks are built by hiring annotators, and the identity of those annotators is treated as an implementation detail.