Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2607. 11228v1 Announce Type: cross Abstract: While Large Vision-Language Models (LVLMs) demonstrate remarkable capabilities, they remain highly susceptible to embedded social biases.
arXiv:2607. 11276v1 Announce Type: cross Abstract: Ensuring the quality of educational materials requires more than standard proofreading: textbooks must be audited for factual accuracy, domain-specific technical correctness, and linguistic quality simultaneously -- a task that general-purpose grammar checkers cannot address.
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:2605. 01143v2 Announce Type: replace Abstract: Large Language Model (LLM)-powered agents demonstrate strong capabilities in autonomous task execution, tool use, and multi-step reasoning.
arXiv:2607. 10466v1 Announce Type: new Abstract: Survival models can model time-to-event outcomes using partially observed data.
arXiv:2607. 10491v1 Announce Type: new Abstract: Retrieval-augmented generation grounds large language models in external evidence, but most pipelines still treat retrieved passages as deterministic and mutually consistent context.
arXiv:2607. 10592v1 Announce Type: new Abstract: Many geometric statistics and manifold learning pipelines routinely produce observations -- such as tangent vectors or local frames -- whose natural home is a varying family of fibers attached to different points of a base manifold, rather than a single shared vector space.
arXiv:2607. 10951v1 Announce Type: new Abstract: We introduce Sticky Jump Diffusions (SJDs), continuous-time Markov processes on $\mathbb R^d$ whose discrete anchors are token embeddings.
arXiv:2607. 11310v1 Announce Type: new Abstract: Physics-Informed Neural Networks (PINNs) provide a meshless approach for solving partial differential equations (PDEs), but suffer severe degradation in stiff and shock-dominated problems, where small PDE residuals can correspond to globally inaccurate solutions.
arXiv:2607. 11374v1 Announce Type: new Abstract: Graph Foundation Models (GFMs) have emerged as a promising paradigm for learning transferable representations across diverse graph domains.
arXiv:2607. 11475v1 Announce Type: new Abstract: Safety alignment in large language models can be fragile under fine-tuning, as even benign task adaptation may increase harmful compliance.
arXiv:2607. 09787v1 Announce Type: cross Abstract: LiDAR semantic segmentation is a key perception task in autonomous driving, where false predictions can affect downstream planning and safety-critical decision-making.
arXiv:2512. 19311v2 Announce Type: replace-cross Abstract: This paper studies the training-testing discrepancy (a.
arXiv:2607. 09697v1 Announce Type: new Abstract: Existing safety mechanisms for multimodal large language models (MLLMs) face a fundamental trade-off between safety and utility.
arXiv:2607. 10365v1 Announce Type: cross Abstract: Vision Transformers (ViTs) are difficult to interpret because current methods of relevance propagation and attention flow do not fully consider some key architectural features, such as the uneven importance of attention heads and residual connections.
arXiv:2607. 10305v1 Announce Type: cross Abstract: Byzantine-robust aggregation rules such as multi-Krum assume a central coordinator, and decentralising them is obstructed by the rules themselves: they are globally coupled, non-associative, and discontinuous, so an ulpscale perturbation can flip the selected subset, moving the output by a non-vanishing amount.
arXiv:2607. 11606v1 Announce Type: cross Abstract: We study how little extra information is needed to make adversarial language learning possible.
arXiv:2607. 11548v1 Announce Type: cross Abstract: Spatial football metrics such as pitch control assume access to the positions of all 22 players, yet the most widely available source of positional data -- the broadcast main camera -- shows only 10-16 of them at any moment.
arXiv:2607. 11701v1 Announce Type: cross Abstract: Quantitative Structure-Activity Relationship ($\mathtt{QSAR}$) modeling is a foundational computational methodology in early-stage drug discovery, heavily relied upon for predicting compound toxicity, bioavailability, and therapeutic potential.
arXiv:2601. 09776v2 Announce Type: replace Abstract: As black box models and pretrained models gain traction in time series applications, understanding and explaining their predictions becomes increasingly vital, especially in high-stakes domains where interpretability and trust are essential.