Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2607. 16247v1 Announce Type: new Abstract: While Vision-Language Models (VLMs) have empowered embodied agents to execute complex household tasks, they struggle to proactively handle dynamically emerging hazards during closed-loop interactions.
arXiv:2607. 16263v1 Announce Type: new Abstract: Antibody expression ranking is a critical task in antibody design, yet its modelling is severely hindered by the scarcity of labeled experimental data.
arXiv:2607. 17800v1 Announce Type: new Abstract: Representation is a central concept in modern machine learning, where it usually refers to internal encodings that support learning and generalization.
arXiv:2511. 14592v3 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) show great promise for autonomous driving, but their suitability for safety-critical scenarios is largely unexplored, raising safety concerns.
arXiv:2607. 17770v1 Announce Type: cross Abstract: Within Explainable Artificial Intelligence, mechanistic interpretability uses Sparse Autoencoders (SAEs) to extract more interpretable features from neural representations.
arXiv:2607. 16251v1 Announce Type: new Abstract: Spatio-Temporal Foundation Models (STFMs) aim to learn generalizable representations of complex dynamical systems across space and time.
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. 16208v1 Announce Type: new Abstract: Graph-grounded multimodal question answering organizes text, tables, and images in a structured evidence graph, yet end-to-end accuracy depends on which multimodal assets are ranked highly enough to enter downstream reasoning; for graph-linked images, single-vector bi-encoder similarity can discard patch- and token-level structure needed for fine-grained alignment.
arXiv:2607. 18034v1 Announce Type: new Abstract: Smart home assistants interpret a wide range of user commands, from explicit device control to underspecified and preference dependent requests.
arXiv:2509. 00078v2 Announce Type: replace-cross Abstract: The emergence of large language models (LLMs) has transformed spoken dialog systems, yet the optimal architecture for real-time on-device voice agents remains an open question.
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:2607. 17913v1 Announce Type: cross Abstract: Distributed Fine-Tuning (DFT) of large-scale Foundation Models (FMs) on resource-constrained edge devices is limited by local compute constraints and communication overhead.
arXiv:2511. 20956v2 Announce Type: replace-cross Abstract: Breast ultrasound (BUS) reporting relies on clinically meaningful lesion descriptors, including BI-RADS category, lesion shape, margin, echogenicity, posterior features, pathology, and histology.
arXiv:2607. 17003v1 Announce Type: cross Abstract: Imitation learning enables learning a policy in an unknown environment with a latent reward signal using expert demonstrations, but it struggles when the imitator's and expert's observations are mismatched and unobserved confounders are present in expert demonstrations.
arXiv:2607. 16652v1 Announce Type: cross Abstract: This position paper argues that claims about explanation stability are scientifically invalid without cross method validation.
arXiv:2607. 16303v1 Announce Type: cross Abstract: Medical Vision-Language Models (Med-VLMs) require reliable reasoning from fine-grained visual evidence, yet existing models can produce plausible clinical answers by relying on language priors or medical templates rather than truly attending to diagnosis-critical regions.
arXiv:2607. 16705v1 Announce Type: cross Abstract: Semi-supervised learning (SSL) is an effective solution for medical image segmentation with limited annotations.
arXiv:2607. 17543v1 Announce Type: new Abstract: In two-player zero-sum games whose Nash equilibria form a convex set, regularized solvers such as Regularized Nash Dynamics (R-NaD) empirically select the maximum-entropy member: the information projection (I-projection) of a uniform reference onto the Nash set.
arXiv:2607. 17575v1 Announce Type: new Abstract: We propose ARBITER, a novel LLM guardrail framework that introduces two key ideas: (i) dual-hypothesis reasoning, a reasoning method for LLM guardrails that explicitly considers both safe and unsafe interpretations of a prompt before making a safety decision, and (ii) multi-component supervised fine-tuning (MC-SFT), a structured training loss for reasoning-based guardrails that decomposes LLM outputs into logical components and weights them according to their importance.
arXiv:2607. 18086v1 Announce Type: new Abstract: Background: LLM judges increasingly score whether clinical language models give overconfident answers under incomplete evidence, yet whether a measured "safety gain" reflects real behavior change or the judge's calibration is unresolved.