Synthetic dialogue generation offers a way to study conversational dynamics in sensitive domains where real data are difficult to access, release, or annotate. The underlying abuse may occur online or offline: threats...
Agentic systems are increasingly composed of heterogeneous agents, prompts, tools, models, skills, composite subsystems, policies, and execution workflows whose configurations evolve across frameworks and runtime...
Logic Tensor Networks (LTN) provide a neurosymbolic framework in which first-order logic is interpreted through tensor operations, enabling logical constraints to be integrated with differentiable learning. However, the...
Learning reliable surgical manipulation policies is bottlenecked by the scarcity of action-labeled demonstrations: teleoperated surgical robot (e.g., dVRK) trajectories with synchronized kinematics are costly to...
Shani et al. (2026) show that LLM representations broadly recover human category boundaries, while failing to reflect fine-grained typicality structure. Their analysis uses cosine similarity over dense model...
AI agents are increasingly used in mathematics research, but it is often unclear how to use them effectively. Towards this, we present an extensive case study of how AI was used to improve bounds on the Grothendieck...
GUI Visual Grounding is a fundamental capability for GUI agents. Existing models typically freeze their parameters after deployment, limiting their ability to adapt to unseen interfaces. Although recent methods attempt...
When a probabilistic predictor answers many conditional-probability queries, are its answers self-consistent, and can this be verified in polynomial time? This problem is of interest for AI safety, where safety is...
The attention mechanism forms the foundation of many modern AI models such as the Transformer. In one subclass of problems where attention is used, inputs and outputs are bound to the probability simplex so that all...
The Workshop on Trustworthy Natural Language Processing (TrustNLP), co-located with major ACL conferences since 2021, has grown from 8 proceedings papers to 41 over six editions, documenting a field-wide transition from...
Existing Multimodal Large Language Models (MLLMs) predominantly rely on image-text pairs for modality alignment pretraining, mapping global image representations to long textual descriptions. However, this image-level...
The Naive Bayes (NB) classifier remains a standard choice for categorical data, yet its widely used smoothing rules, such as Laplace, Lidstone, Krichevsky-Trofimov, and the $m$-estimate, all prescribe a fixed smoothing...
Conditional Independence (CI) tests are the statistical engine of constraint-based causal discovery: in algorithms such as PC (Peter-Clark) and FCI (Fast Causal Inference), skeleton pruning and key orientations follow...
Detecting or attributing a supply-chain disruption is not the same as selecting the intervention that maximizes recoverable net value. We present CriticalSCM-Bench v1, a controlled synthetic benchmark with causal ground...
Modern reinforcement learning (RL) post-training pipelines for large language models (LLMs) increasingly combine rollout workloads across multiple domains and feedback paradigms. Prefix-aware routing improves inference...
Safety alignment in large language models (LLMs) is largely developed in English, assuming these safeguards generalize across multilingual settings. However, this assumption remains underexplored and exposes a...
This paper develops a method for sensor-subset selection for tracking. Prior work showed that low-cost acoustic Received Signal Strength Indicator (RSSI) measurements can be used to recommend subsets of sensor nodes...
We propose that a model's uncertainty about a token is reflected not only in the breadth of its output distribution but also in whether a confident prediction is \emph{fragile} under perturbation of its attention...
Augmentation can corrupt a training example when an image and its annotations receive different random changes. A crop must use the same coordinates for the image, mask, boxes, keypoints, stereo views, video frames, or...
Probabilistic forecasting plays an essential role in risk-sensitive decision-making, particularly in long-horizon settings. However, existing approaches often face a fundamental trade-off between distributional...