Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2606. 16100v1 Announce Type: cross Abstract: As Large Language Model (LLM) APIs become ubiquitous, users increasingly rely on black-box fingerprinting to verify that providers are serving the advertised premium models.
arXiv:2606. 15250v1 Announce Type: cross Abstract: Radiographic assessment of lower-limb alignment (LLA) is important for predicting joint health and surgical outcomes in total knee arthroplasty.
arXiv:2606. 14765v1 Announce Type: cross Abstract: Self-supervised video representation learning has recently advanced through contrastive learning, masked reconstruction, and predictive representation learning.
arXiv:2606. 14865v1 Announce Type: cross Abstract: Adversarial Training (AT) improves neural network robustness, but most methods train a fixed parameter space from the start.
arXiv:2606. 16090v1 Announce Type: cross Abstract: The power of quantum computing and quantum machine learning relies on harnessing uniquely quantum phenomena as computational resources.
arXiv:2505. 04486v4 Announce Type: replace-cross Abstract: Flow matching models have shown great potential in image generation tasks among probabilistic generative models.
arXiv:2606. 15209v1 Announce Type: new Abstract: Targeted advertising systems can pair audiences selected by advertisers with ad units that expose visible user actions.
arXiv:2606. 15179v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) has emerged as a pivotal technique for improving language models by incorporating external knowledge at inference time.
arXiv:2606. 15447v1 Announce Type: new Abstract: Electronic health record foundation models typically treat ICD diagnosis codes as flat tokens, overlooking the clinically meaningful hierarchical structure that captures disease families, subcategories, and fine-grained diagnostic detail.
arXiv:2606. 15034v1 Announce Type: new Abstract: Computer-use agents are increasingly evaluated by whether they complete realistic desktop and web tasks.
arXiv:2505. 19699v2 Announce Type: replace-cross Abstract: Federated Learning (FL) is a decentralized machine learning paradigm that enables clients to collaboratively train models while preserving data privacy.
arXiv:2606. 14900v1 Announce Type: new Abstract: Multi-source transfer learning faces a fundamental scalability bottleneck: existing approaches require either loading all K source models into memory simultaneously during parameter fusion, requiring O(K) memory, or deploying all models at inference time, making production deployment infeasible.
arXiv:2606. 15074v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used for technical document generation, yet single-model outputs often suffer from over-engineering, security blind spots, and incomplete coverage.
arXiv:2604. 17301v2 Announce Type: replace-cross Abstract: Detecting harmful content in multi turn dialogue requires reasoning over the full conversational context rather than isolated utterances.
arXiv:2606. 16950v1 Announce Type: cross Abstract: Nanopores are versatile single-molecular sensors, but their utility is fundamentally constrained by stochastic translocation dynamics warping any encoded information.
arXiv:2606. 15115v1 Announce Type: new Abstract: Multi-objective optimization (MOO) has emerged as a powerful approach to solving complex optimization problems involving multiple objectives.
arXiv:2606. 14741v1 Announce Type: cross Abstract: We introduce HorusEye, Language as Dynamic Attention for Emergency Visual Analysis.
arXiv:2606. 15054v1 Announce Type: new Abstract: Sparse autoencoders (SAEs) detect features via inner product, so a feature's activation scales with both its directional alignment and the input's norm.
arXiv:2509. 07605v2 Announce Type: replace-cross Abstract: Class imbalance poses a significant challenge to supervised classification, particularly in critical domains like medical diagnostics and anomaly detection where minority class instances are rare.
arXiv:2606. 15610v1 Announce Type: cross Abstract: LLM-as-a-judge systems are now routinely used for open-ended model evaluation, where human preference annotation is costly, slow, and difficult to reproduce.