Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2606. 27381v1 Announce Type: cross Abstract: Queue overflow, a severe consequence of urban traffic congestion, occurs when vehicle queues exceed intersection capacity, obstructing upstream traffic and triggering cascading gridlocks.
arXiv:2606. 27863v1 Announce Type: cross Abstract: Demand forecasting at the bottom of a retail hierarchy requires predicting tens of thousands of correlated long-horizon series across products, stores, and regions.
arXiv:2606. 27711v1 Announce Type: cross Abstract: We introduce a neural network-based framework for learning time series estimators through a process we term decision-theoretic pretraining.
arXiv:2606. 26519v2 Announce Type: replace Abstract: Large language models (LLMs) can make scientific software easier to use.
arXiv:2606. 28270v1 Announce Type: new Abstract: The transition from static chat bots to autonomous agents--equipped with persistent memory, tool-use protocols, and multi-agent collaboration--has fundamentally expanded the AI threat landscape.
arXiv:2504. 16116v4 Announce Type: replace-cross Abstract: The Web3 ecosystem, underpinned by cryptographic primitives and decentralized consensus, represents a high-stakes environment where software vulnerabilities and incentive misalignments translate directly into financial loss.
arXiv:2507. 18632v2 Announce Type: replace-cross Abstract: Zero-shot domain adaptation is a method for adapting a model to a target domain without utilizing target domain image data.
arXiv:2604. 24155v3 Announce Type: replace-cross Abstract: The project of aligning machine behavior with human values raises a basic problem: whose moral expectations should guide AI decision-making?
arXiv:2510. 10271v2 Announce Type: replace-cross Abstract: Unlike regular tokens derived from existing text corpora, special tokens are artificially created to annotate structured conversations during the fine-tuning process of Large Language Models (LLMs).
arXiv:2606. 28186v1 Announce Type: cross Abstract: Predicting human item difficulty is central to educational assessment, where reliable estimates support fairness and effective test construction.
arXiv:2601. 22709v5 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) achieve strong multimodal performance but are costly to deploy, and post-training quantization often causes significant accuracy loss.
arXiv:2606. 27698v1 Announce Type: cross Abstract: Automatic Speech Recognition systems are notoriously both sensitive to adversarial and benign perturbations.
arXiv:2606. 27685v1 Announce Type: cross Abstract: Pervasive data contamination -- stemming from measurement errors, outliers, or adversarial corruption -- has motivated the development of robust statistical methods.
arXiv:2606. 27793v1 Announce Type: cross Abstract: Long-context language models suffer from position bias, where information in middle positions is underutilized.
arXiv:2606. 27939v1 Announce Type: cross Abstract: Protein language models are standard priors for biological sequence generation, but steering them toward explicit distributional design targets remains largely unexplored.
arXiv:2606. 27440v1 Announce Type: new Abstract: Foundation models for structural biology have achieved remarkable performance in predicting biomolecular structure and show promise for the design of proteins and small molecules.
arXiv:2511. 20196v2 Announce Type: replace Abstract: Multimodal large language models (MLLMs) can inadvertently memorize privacy-sensitive information during training.
arXiv:2606. 28011v1 Announce Type: cross Abstract: We propose an agentic Large Language Model (LLM) framework for active Fault-Tolerant Control (FTC) that transforms fault detection outputs into constraint-aware recovery actions grounded in plant-specific knowledge.
arXiv:2606. 28112v1 Announce Type: cross Abstract: Degradation-aware prompts, conditions, and latent priors are increasingly used in image restoration, yet they are usually judged by a single endpoint: whether the restored image obtains higher PSNR.
arXiv:2606. 28294v1 Announce Type: new Abstract: Preference-based alignment often struggles to capture the reasoning that underlies human judgments.