arXiv:2603.16983v1 Announce Type: new Abstract: Machine learning models for geotechnical hazard prediction can achieve high accuracy while learning physically inconsistent relationships from sparse or biased training data. Current remedies (post-hoc explainability, such as SHAP and LIME, and training-time constraints) either…
This new metric for measuring uncertainty could flag hallucinations and help users know whether to trust an AI model.
With this new technique, a robot could more accurately detect hidden objects or understand an indoor scene using reflected Wi-Fi signals.
arXiv:2502.12855v2 Announce Type: replace-cross Abstract: While large models pre-trained on high-quality data exhibit excellent performance on mathematical reasoning (e.g., GSM8k, MultiArith), it remains challenging to specialize smaller models for these tasks. Common approaches to address this challenge include knowledge distillation…
arXiv:2511.06216v3 Announce Type: replace Abstract: Graph contrastive learning (GCL) learns node and graph representations by contrasting multiple views of the same graph. Existing methods typically rely on fixed, handcrafted views-usually a local and a global perspective, which limits their ability…
arXiv:2603.03818v2 Announce Type: replace Abstract: Continual learning is a long-standing challenge in robot policy learning, where a policy must acquire new skills over time without catastrophically forgetting previously learned ones. While prior work has extensively studied continual learning in relatively…
arXiv:2502.20030v3 Announce Type: replace Abstract: Inspired by the recent successes of Inverse Optimization (IO) across various application domains, we propose a novel offline Reinforcement Learning (ORL) algorithm for continuous state and action spaces, leveraging the convex loss function called “sub-optimality…
arXiv:2506.22342v2 Announce Type: replace Abstract: Epidemic analyses increasingly rely on heterogeneous datasets, many of which are sensitive and require strong privacy protection. Although differential privacy (DP) has become a standard in machine learning and data sharing, its adoption in epidemiological…
arXiv:2603.17569v1 Announce Type: cross Abstract: Graph transformers are the state-of-the-art for learning from graph-structured data and are empirically known to avoid several pitfalls of message-passing architectures. However, there is limited theoretical analysis on why these models perform well in practice.…
arXiv:2603.17893v1 Announce Type: cross Abstract: Methodology bugs in scientific Python code produce plausible but incorrect results that traditional linters and static analysis tools cannot detect. Several research groups have built ML-specific linters, demonstrating that detection is feasible. Yet these tools…
