arXiv:2602.09309v2 Announce Type: replace-cross Abstract: Every generative model for crystalline materials harbors a critical structure size beyond which its outputs become unreliable; we call this the extrapolation frontier. Despite its consequences for nanomaterial design, this frontier has never been systematically…
arXiv:2506.01318v4 Announce Type: replace Abstract: Machine unlearning (MU) aims to expunge a designated forget set from a trained model without costly retraining, yet the existing techniques overlook two critical blind spots: “over-unlearning” that deteriorates retained data near the forget set,…
arXiv:2506.01318v4 Announce Type: replace Abstract: Machine unlearning (MU) aims to expunge a designated forget set from a trained model without costly retraining, yet the existing techniques overlook two critical blind spots: “over-unlearning” that deteriorates retained data near the forget set,…
arXiv:2605.30462v1 Announce Type: new Abstract: Can a dataset be recognized from the spurious correlations it induces during training? We argue that datasets leave dataset-specific traces in a model’s learned semantic correlation structure: incidental regularities that are predictive within a dataset,…
arXiv:2605.30482v1 Announce Type: new Abstract: Machine learning is increasingly used in mathematical discovery, but in mathematics the desired output is often not a prediction itself, but an explicit construction that can be checked independently. We study this setting through the…
arXiv:2605.30482v1 Announce Type: new Abstract: Machine learning is increasingly used in mathematical discovery, but in mathematics the desired output is often not a prediction itself, but an explicit construction that can be checked independently. We study this setting through the…
arXiv:2605.19233v2 Announce Type: replace-cross Abstract: Unmanned aerial vehicles (UAVs) are cyber-physical systems whose attack surface spans networked avionics and on-board sensor fusion: a compromised GPS or battery module can mimic a benign mission segment and evade naive anomaly detectors. We…
arXiv:2510.01137v3 Announce Type: replace Abstract: Privacy is a central concern when fine-tuning large language models (LLMs) on sensitive data, and differentially private stochastic gradient descent (DP-SGD) — which clips per-sample gradients and adds calibrated Gaussian noise — is the standard…
arXiv:2605.30486v1 Announce Type: new Abstract: Spatio-temporal forecasting on sensor graphs is commonly tackled with a single backbone architecture applied uniformly across all nodes, although graph regions can exhibit different dynamics. Road segments differ in functional class, structure, and traffic behavior,…
arXiv:2512.19673v3 Announce Type: replace Abstract: Existing reinforcement learning (RL) approaches treat large language models (LLMs) as a unified policy, overlooking their internal mechanisms. In this paper, we decompose the LLM-based policy into Internal Layer Policies and Internal Modular Policies via…
