Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2607. 16351v1 Announce Type: cross Abstract: Publicly shareable construction-video benchmarks remain scarce, especially for safety-critical hazards that are rare, dangerous to stage, and difficult to release.
arXiv:2503. 23536v3 Announce Type: replace-cross Abstract: Unlearnable data (ULD) has emerged as an innovative defense technique to prevent machine learning models from learning meaningful patterns from specific data, thus protecting data privacy and security.
arXiv:2607. 17947v1 Announce Type: new Abstract: Existing AI measurement frameworks quantify cognitive capability, task automation, or catastrophic risk, but none measure autonomous agency: the extent to which a system behaves in a self-directed way.
arXiv:2607. 18198v1 Announce Type: new Abstract: Modern generative models typically rely on an adversarial critic, a prescribed noise-to-data path, or an autoregressive factorization.
arXiv:2607. 16514v1 Announce Type: cross Abstract: Image-based dietary assessment promises to replace costly, bias-prone manual recalls, but portion estimation remains a major blocker.
arXiv:2603. 00454v3 Announce Type: replace-cross Abstract: Generative Flow Networks (GFlowNets) enable fine-tuning large language models to approximate reward-proportional posteriors, but they remain prone to mode collapse, manifesting as prefix collapse and length bias.
arXiv:2607. 17990v1 Announce Type: new Abstract: Highly nonlinear chaotic dynamical systems remain difficult to model due to fundamental trade-offs between complexity, expressivity, and data efficiency.
arXiv:2607. 17269v1 Announce Type: new Abstract: Large language models encode world models implicitly in neural weights, which exposes four structural risks in high-precision domains such as medicine and finance: hallucination, frozen knowledge, poor explainability, and poor modifiability.
arXiv:2607. 17188v1 Announce Type: new Abstract: Test-time scaling empowers Large Reasoning Models (LRMs) to tackle complex tasks via extensive Chain-of-Thought (CoT).
arXiv:2607. 17951v1 Announce Type: cross Abstract: Natural-language control offers a promising interface for unmanned aerial vehicles (UAVs), but directly applying self-hosted computer-use agents (SHCUAs) to UAV control introduces a structural mismatch.
arXiv:2607. 17288v1 Announce Type: cross Abstract: High quality temporal graph benchmarks with rich semantics and ground-truth anomaly labels are essential for training graph neural networks, yet remain scarce due to privacy constraints and annotation costs.
arXiv:2602. 00387v4 Announce Type: replace-cross Abstract: Bayesian neural networks promise calibrated uncertainty but require $O(mn)$ parameters for standard mean-field Gaussian posteriors.
arXiv:2607. 16789v1 Announce Type: new Abstract: Real-world perception and decision making are inherently multimodal, integrating complementary signals across modalities.
arXiv:2607. 17166v1 Announce Type: new Abstract: Transformer-based large language models (LLMs) continue to achieve state-of-the-art performance across various natural language processing tasks.
arXiv:2607. 17671v1 Announce Type: new Abstract: Large-scale single-cell perturbation atlases make it possible to ask an inverse question: given an observed transcriptional response, which annotated targets and compounds in a fixed library are most consistent with that response?
arXiv:2607. 18064v1 Announce Type: cross Abstract: Coding agents can now be left alone to improve software against a score.
arXiv:2607. 18063v1 Announce Type: cross Abstract: LLM-based agents process external content, exposing them to prompt injection and multi-turn manipulation.
arXiv:2604. 23716v3 Announce Type: replace Abstract: Information-theoretic (IT) measures are ubiquitous in artificial intelligence: entropy drives decision-tree splits and uncertainty quantification, cross-entropy is the default classification loss, mutual information underpins representation learning and feature selection, and transfer entropy reveals directed influence in dynamical systems.
arXiv:2602. 17743v2 Announce Type: replace Abstract: In-context learning (ICL) allows large language models to adapt to new tasks from a few examples without updating their parameters.
arXiv:2503. 10677v3 Announce Type: replace-cross Abstract: Retrieval-Augmented Generation (RAG) has gained significant attention in recent years for its potential to enhance natural language understanding and generation by combining large-scale retrieval systems with generative models.