Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2606. 09878v1 Announce Type: new Abstract: Standard benchmarks report aggregate accuracy, but practitioners need to know which specific capabilities a model lacks.
arXiv:2606. 10499v1 Announce Type: cross Abstract: Traffic prediction is fundamental to intelligent transportation systems and urban computing, yet many cities continue to suffer from traffic data scarcity due to limited sensor deployment and uneven urban development.
arXiv:2602. 06411v2 Announce Type: replace Abstract: EEG-based emotion recognition supports affective brain-computer interfaces and mental health monitoring yet remains challenged by signal complexity, subject variability, and limited interpretability.
arXiv:2606. 10569v1 Announce Type: cross Abstract: Standard RLHF pipelines often reduce heterogeneous human judgments into a single scalar reward target.
arXiv:2605. 24197v2 Announce Type: replace Abstract: We study a class of emergent misalignment in multi-agent systems (MAS), with a focus on automated workflows, which we refer to agentic misalignment.
arXiv:2606. 10371v1 Announce Type: cross Abstract: Diffusion-based action generation has become a foundational component of embodied AI, but its reliance on visual conditioning leaves deployed visuomotor policies vulnerable to adversarial manipulation.
arXiv:2606. 10099v1 Announce Type: cross Abstract: The rapid development of large language models (LLMs) has raised concerns about misuse such as plagiarism, misinformation, and automated influence operations, motivating the need for robust detectors.
arXiv:2606. 10953v1 Announce Type: new Abstract: Furnished floor plans are fundamental to real estate visualization, interior design, and architectural workflows.
arXiv:2606. 10595v1 Announce Type: cross Abstract: Federated Learning (FL) has emerged as a promising solution for data hunger in centralized learning.
arXiv:2606. 10173v1 Announce Type: cross Abstract: As AI systems move into operating systems, privacy no longer turns only on whether a model runs locally.
arXiv:2606. 11123v1 Announce Type: new Abstract: Backpropagation (BP) is widely viewed as biologically implausible, in part because it requires feedback weights to be the transpose of forward weights for error propagation.
arXiv:2606. 10126v1 Announce Type: cross Abstract: Personalized persuasive text generation can improve relevance and engagement, but demographic conditioning may also introduce unequal framing across groups.
arXiv:2606. 10703v1 Announce Type: new Abstract: Interpretability methods routinely use population-level summary statistics over observed model behaviour to license claims about the effects of targeted interventions on specific computations; in Pearl's terms, they treat rung-1 associational evidence as if it supported rung-2 interventional conclusions, a move whose validity is rarely tested.
arXiv:2606. 10802v1 Announce Type: cross Abstract: Deep Neural Networks (DNNs) typically require extensive datasets for effective training.
arXiv:2606. 10010v1 Announce Type: cross Abstract: Evaluating text-to-music (TTM) systems remains expensive because music impression (MI) and text alignment (TA) scores rely on human mean opinion scores (MOS).
arXiv:2606. 10932v1 Announce Type: cross Abstract: We present Density Field State Space Models (DF-SSM), a framework for compressing SSMs to a 1-bit scaffold with int8 low-rank correction.
arXiv:2501. 04339v2 Announce Type: replace-cross Abstract: We introduce the Deep Convolutional Interpreter for Time Series (DCIts), a deep-learning architecture for nonlinear multivariate time series that provides sample-specific, locally interpretable descriptions of the underlying interaction structure.
arXiv:2606. 09956v1 Announce Type: cross Abstract: The rapid adoption of LLM-powered code generation has dramatically accelerated software development, yet effective verification methods remain severely underdeveloped.
arXiv:2606. 10321v1 Announce Type: cross Abstract: Neural combinatorial optimization (NCO) trains autoregressive policies to solve routing problems.
arXiv:2603. 29025v3 Announce Type: replace-cross Abstract: Large language models fail when a salient surface cue conflicts with an unstated feasibility constraint.