Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2605. 13838v3 Announce Type: replace-cross Abstract: Video-guided 3D animation holds immense potential for content creation, offering intuitive and precise control over dynamic assets.
arXiv:2606. 30219v1 Announce Type: new Abstract: LLM evaluation and AI safety face a shared measurement problem: benchmark scores, reward-model signals, and reported safety metrics can improve while the latent properties they are meant to represent remain difficult to verify.
arXiv:2606. 30105v1 Announce Type: new Abstract: Quantitative verification of neural networks requires reasoning about probabilities under substantial uncertainty in both input distributions and their dependence structure.
arXiv:2606. 29126v1 Announce Type: new Abstract: Cooperative multi-agent reinforcement learning (MARL) often relies on communication to mitigate partial observability, yet most existing protocols treat messages as flat dense vectors detached from the structure of the observations they summarize.
arXiv:2606. 28998v1 Announce Type: cross Abstract: Large Language Model (LLM) alignment trains an LLM using preference data to produce outputs that better meet established quality standards.
arXiv:2605. 26542v2 Announce Type: replace-cross Abstract: Tool-using agents increasingly operate in open-ended deployment environments, where they compose file systems, web APIs, code interpreters, and enterprise services at runtime.
arXiv:2606. 30090v1 Announce Type: new Abstract: Efficient tactical knowledge extraction and analysis in real-time strategy (RTS) games micromanagement are constrained by the high-dimensional coupled state-action sequential data and the black-box decision-making process.
arXiv:2606. 28769v1 Announce Type: new Abstract: Emotional body motion expressions are an essential element of non-verbal communication.
arXiv:2606. 30531v1 Announce Type: new Abstract: Tool-augmented language-model agents are often evaluated by whether they select the correct tool, produce valid API arguments, and complete the requested task.
arXiv:2606. 28401v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) have shown strong performance in visual understanding, yet they still suffer from hallucinations, generating content that is not grounded in the image.
arXiv:2503. 19501v2 Announce Type: replace-cross Abstract: Falls among elderly residents in assisted living homes pose significant health risks, often leading to injuries and a decreased quality of life.
arXiv:2509. 21530v2 Announce Type: replace Abstract: Data augmentation is a widely used strategy to improve model robustness and generalization by enriching training datasets with synthetic examples.
arXiv:2504. 17421v2 Announce Type: replace-cross Abstract: Large language models (LMs) offer broad generalization capabilities but require vast amounts of data and computational resources for domain-specific tasks; small models (SMs), in contrast, are more efficient and tailored to specific domains yet lack general-purpose coverage.
arXiv:2606. 28933v1 Announce Type: cross Abstract: Venture capital (VC) investment decisions face distinct challenges, such as multi-source heterogeneous data, non-stationary time series, and the demand for explainable predictions in high-stakes, low-data settings.
arXiv:2602. 02498v2 Announce Type: replace-cross Abstract: Large language models can produce toxic or inappropriate text even for benign inputs, creating risks when deployed at scale.
arXiv:2606. 28739v1 Announce Type: new Abstract: Large language models increasingly act as agents: they call tools, move money, delete records, and send messages on a user's behalf.
arXiv:2410. 01244v2 Announce Type: replace-cross Abstract: We introduce a novel Wasserstein-1 ($W_1$) path-space divergence for stochastic and deterministic dynamics and establish a Wasserstein Uncertainty Propagation (WUP) theorem that bounds the $W_1$ distance between terminal distributions by the proposed divergence, equivalently characterized by a weighted $L^2$ discrepancy between the underlying drifts and the $W_1$ distance between their initial measures.
arXiv:2606. 29586v1 Announce Type: cross Abstract: Vision-language foundation models have shown strong potential in medical image analysis.
Neural networks are known to be susceptible to over-reliance on spurious correlations. However, the precise mechanism by which models exploit shortcut features is not fully understood, and algorithms to mitigate this behavior rely on as yet unjustified assumptions about the learned representations.
Adversarial attacks pose a challenge to the reliability of deep learning models, motivating effective detection methods. Existing techniques often rely on attack-specific assumptions, access to adversarial samples, or knowledge of the underlying classifier (white-box).