Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2603. 19258v2 Announce Type: replace-cross Abstract: Differentially private (DP) fine-tuning of large language models (LLMs) requires massive compute and full model access, which rules out state-of-the-art proprietary APIs for general users.
arXiv:2604. 08277v3 Announce Type: replace-cross Abstract: We present QARIMA, a quantum state-similarity-based reconstruction of the classical ARIMA modelling pipeline.
arXiv:2605. 24590v2 Announce Type: replace-cross Abstract: Low-light, long-exposure defocus deblurring remains a challenging problem due to the simultaneous presence of severe blur and complex biased noise.
arXiv:2608. 01898v1 Announce Type: new Abstract: Increasing EEG pretraining data scale or model capacity does not consistently improve downstream performance.
arXiv:2608. 02034v1 Announce Type: new Abstract: Multi-step returns accelerate reward propagation in off-policy reinforcement learning, but couple the evaluation of each decision to the suboptimal logged actions that follow it, inducing a pessimistic bias that grows with the horizon.
arXiv:2608. 02052v1 Announce Type: new Abstract: Human mobility prediction models, which forecast the next location in a user's trajectory, are increasingly deployed in urban analytics, navigation, and personalized services.
arXiv:2608. 00056v1 Announce Type: cross Abstract: We propose RSTA, a domain-generalized semantic communication framework enabling source-free V2X collaborative perception under both observation-domain shift and unseen wireless channel conditions.
arXiv:2608. 00073v1 Announce Type: cross Abstract: Rigorous dataset partitioning is a foundational, yet frequently overlooked, prerequisite for reliable deep learning in longitudinal medical imaging.
arXiv:2608. 00701v1 Announce Type: cross Abstract: Reweighting source samples to match a target covariate distribution is a standard response to distribution shift when generalizing evidence from one population to another.
arXiv:2608. 00855v1 Announce Type: cross Abstract: Uncrewed aerial vehicle (UAV)-enabled federated learning (FL) can provide flexible, on-demand edge intelligence for large-scale IoT deployments, but operating in shared unlicensed bands makes uplink update delivery interference-coupled and unreliable.
arXiv:2608. 02375v1 Announce Type: cross Abstract: This paper studies the distributed online control problem over a network of linear time-invariant (LTI) systems in the presence of adversarial disturbances and time-varying convex costs.
arXiv:2510. 27313v3 Announce Type: replace Abstract: Generation novelty is a key indicator of an LLM's ability to generalize, yet measuring it against full pretraining corpora is computationally challenging.
arXiv:2603. 19040v2 Announce Type: replace Abstract: Differentially private wireless federated learning (DPWFL) is a promising framework for protecting sensitive user data.
arXiv:2603. 25538v3 Announce Type: replace Abstract: Automated incident management is critical for microservice reliability.
arXiv:2603. 28067v2 Announce Type: replace Abstract: Digital testing has emerged as a key paradigm for the development and verification of autonomous maritime navigation systems, yet the availability of realistic and diverse safety-critical encounter scenarios remains limited.
arXiv:2608. 00180v1 Announce Type: cross Abstract: Conflicting objectives are general in RL alignment, and training on them data-efficiently is hard.
arXiv:2602. 04718v4 Announce Type: replace Abstract: A central premise in mechanistic interpretability is that meaningful concepts in language models are represented by linear features in activation space.
arXiv:2608. 02168v1 Announce Type: new Abstract: Credit risk detection, particularly mitigating individual fraud, is crucial for maintaining the stability of digital financial ecosystems.
arXiv:2608. 02250v1 Announce Type: new Abstract: Federated learning (FL) is a popular distributed learning framework where multiple clients perform local training and a server aggregates the locally updated models.
arXiv:2608. 02430v1 Announce Type: cross Abstract: We provide new estimates in Wasserstein distance for the asymptotic bias of the unadjusted Langevin algorithm, in the classical setting of log-smooth strongly log-concave measures.