Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2606. 02434v1 Announce Type: new Abstract: Precise parametric control over circuit geometry is essential for semiconductor inspection, yet obtaining sufficient real training data remains costly.
arXiv:2606. 00134v1 Announce Type: cross Abstract: Intrusion Detection Systems (IDS) in Internet of Things (IoT) environments face significant challenges due to data heterogeneity, lack of labeled data, and limited model interpretability.
arXiv:2606. 00462v1 Announce Type: cross Abstract: Short-form text rewriting is a constrained variant of paraphrasing in which limited context and high semantic density leave little room for variation.
arXiv:2412. 16209v5 Announce Type: replace Abstract: When using machine learning for imbalanced binary classification problems, it is common to subsample the majority class to create a (more) balanced training dataset.
arXiv:2508. 11931v3 Announce Type: replace Abstract: We present an oracle-efficient, near-optimal algorithm for linear contextual bandits with adversarial losses and stochastic action sets, only requiring a linear optimization oracle for the action sets in each round.
arXiv:2511. 21140v4 Announce Type: replace Abstract: Large language models (LLMs) are widely used as scalable evaluators of model responses in lieu of human annotators.
arXiv:2602. 11852v2 Announce Type: replace Abstract: While state-of-the-art language models (LMs) surpass most humans in certain domains, their reasoning remains largely opaque, reducing trust and increasing the risk of deception and hallucination.
arXiv:2606. 02119v1 Announce Type: cross Abstract: Machine unlearning aims to remove the influence of specific forget training data due to privacy, copyright or bias concerns while maintaining the model performance on the remaining retain data.
arXiv:2606. 00947v1 Announce Type: cross Abstract: Foundation models are increasingly personalized on decentralized private data through federated learning and are now deployed at scale under growing regulatory requirements for post-market monitoring.
arXiv:2512. 12997v2 Announce Type: replace-cross Abstract: CLIP delivers strong zero-shot classification but remains highly vulnerable to adversarial attacks.
arXiv:2508. 17320v3 Announce Type: replace Abstract: Understanding the internal representations of large language models (LLMs) remains a central challenge for interpretability research.
arXiv:2606. 02309v1 Announce Type: new Abstract: Generative models are increasingly used as priors for inverse problems, but their ability to produce realistic images creates a basic trust problem: a plausible reconstruction may be supported by the measurements, or it may be filled in by the prior along unobserved directions.
arXiv:2506. 22666v3 Announce Type: replace-cross Abstract: The rise of API-only access to state-of-the-art LLMs highlights the need for effective black-box jailbreak methods to identify model vulnerabilities in real-world settings.
arXiv:2601. 04539v2 Announce Type: replace-cross Abstract: In recurrent neural networks (RNNs) used to model biological neural networks, noise is typically introduced during training to emulate biological variability and regularize learning.
arXiv:2601. 14323v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models are increasingly deployed in safety-critical robotic applications, yet their security vulnerabilities remain underexplored.
arXiv:2512. 10234v2 Announce Type: replace-cross Abstract: Even LLMs that appear safe during evaluation can still produce harmful responses in deployment.
arXiv:2602. 02557v2 Announce Type: replace-cross Abstract: Recent advances in end-to-end trained omni-models have substantially improved audio capabilities by strengthening text-audio modality alignment.
arXiv:2604. 17415v3 Announce Type: replace-cross Abstract: Reward-based fine-tuning steers a pretrained diffusion or flow-based generative model toward higher-reward samples while remaining close to the pretrained model.
arXiv:2511. 16992v3 Announce Type: replace Abstract: Aligning Large Language Models (LLMs) with human values often involves balancing multiple, conflicting objectives such as helpfulness and harmlessness.
arXiv:2602. 06547v3 Announce Type: replace-cross Abstract: LLM-based coding agents increasingly rely on third-party extensions called skills, which bundle natural language instructions and helper scripts that execute with full user privileges.