Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2607. 10187v1 Announce Type: new Abstract: Large language models (LLMs) write Unity C\# for game scenes.
arXiv:2605. 14746v2 Announce Type: replace Abstract: While large language models (LLMs) are trained to align with human values, their generations may still violate safety constraints.
arXiv:2604. 16610v2 Announce Type: replace-cross Abstract: Machine learning models often inherit biases from historical data, raising critical concerns about fairness and accountability.
arXiv:2607. 09802v1 Announce Type: new Abstract: The escalating demand for Machine Learning (ML) training resources in recent years has resulted in a substantial gap between the high demand and the available supply.
arXiv:2607. 11364v1 Announce Type: cross Abstract: Generating immersive, synchronized and cinematic audio for long-form textual narratives remains a significant challenge in multi-modal AI.
arXiv:2607. 11334v1 Announce Type: new Abstract: Large language models can produce superficially legal twelve-tone scores that collapse into degenerate textures.
arXiv:2607. 10565v1 Announce Type: cross Abstract: End-to-end motion planning has emerged as a promising paradigm in autonomous driving, directly mapping raw sensor data to control commands via deep neural networks.
arXiv:2511. 17688v2 Announce Type: replace-cross Abstract: Input transformation-based attacks improve adversarial transferability by aggregating gradients over transformed inputs.
arXiv:2607. 09743v1 Announce Type: new Abstract: We investigate whether structured reasoning interventions improve the strategic economic reasoning of large language models, and whether their effects depend on model architecture.
arXiv:2607. 09770v1 Announce Type: new Abstract: Industrial agentic AI systems increasingly exhibit a gap between prototype capability and production deployment.
arXiv:2607. 10992v1 Announce Type: cross Abstract: Perineural invasion (PNI) is a clinically relevant indicator of tumor aggressiveness and can influence surgical decision-making, motivating interest in reliable preoperative assessment.
Transformer-style architectures are increasingly adopted for industrial recommendation systems, yet they inherit a design premise misaligned with the task: generative models rely on per-token autoregressive prediction, which justifies maintaining large intermediate tensors that scale with sequence length. In contrast, recommendation systems produce a single set of relevance scores for each pair without token-level supervision.
As Code Large Language Models (LLMs) become central to modern software engineering, their inherent stochasticity poses significant real-world risks, where even minor errors can lead to severe functional, security, or safety consequences. Reliable automation, therefore, demands the ability to distinguish between confident, well-supported predictions and stochastic guessing.
One year ago, the AISLE roadmap argued that autonomous laboratories operated as isolated islands and proposed a grassroots network organized around five critical dimensions. The field has since moved faster than anticipated.
Production LLM agents such as Claude Code and Codex operate over untrusted content, files, commands, and workspace state, making safety failures directly actionable. Red-teaming must therefore keep pace with evolving models and tools.
We present FoundationGeo, a two-stage framework that explicitly bridges relative and metric prediction via spatial calibration and principled data design. Stage 1 learns a high-fidelity, affine-invariant geometry model by initializing with DINOv3 and training on a curated 10.
When should an intelligent assistant speak up without being asked? Continuous egocentric video offers rich, evolving context that enables a new form of assistance: one that is proactive rather than merely reactive.
Agentic systems increasingly improve themselves by editing skills: prompts, rubrics, plans, tool contracts, examples, validators, and traces. Skill edits are not independent coordinates in a vector space: they are local repairs to structured artifacts whose effects are observed only after rollout, validation, and critique.
Safety alignment in large language models can be fragile under fine-tuning, as even benign task adaptation may increase harmful compliance. Existing defenses mainly follow two directions: they either intervene during or after fine-tuning through retraining or weight modification, which can be costly and may hurt task performance, or they use model-agnostic safety classifiers, which may miss failures specific to a given fine-tuned checkpoint.
A framework for aligning agentic AI with enterprise intent to ensure consistent scenario‑wide autonomous behavior. The post The Three Dimensions of Custom Agentic Alignment: Purpose, Principles and Practices appeared first on Towards Data Science .