I Fine-Tuned BERT 47 Times Before I Realized I Was the Problem Fine-tuning BERT looks simple on Hugging Face. Running it in production looks like a different universe. Attempt number 47. Surely the learning rate is the only variable left to change. It was 1:47 AM. The sprint demo was in six hours. I had a BERT model fine-tuned on our customer support ticket dataset. I’d done everything by the book. Pre-trained weights from bert-base-uncased. Hugging Face Transformers. AdamW optimizer. Learning rate […]

Ver mais

Introduction Disclaimer: This article is a cross post from Pytorch Medium Blog Post. One of the most exciting advancements, that has pushed the frontier of the Artificial Intelligence (AI) in recent years, is Deep Reinforcement Learning (DRL). DRL belongs to the family of machine learning algorithms. It assumes that intelligent machines can learn from their actions similar to the way humans learn from experience. Over the recent years we could witness some impressive real-world applications of DRL. The […]

Ver mais

I got interested in ASP.NET Core 3.0 since the first preview and followed it very closely. I started using it since preview2 and will now soon go to production with it (preview9). I compiled this list to have all the new features, improvements and breaking changes that happened during this time for easy access and accessibility.

Ver mais

arXiv:2601.02610v1 Announce Type: cross Abstract: Conformal novelty detection is a classical machine learning task for which uncertainty quantification is essential for providing reliable results. Recent work has shown that the BH procedure applied to conformal p-values controls the false discovery rate (FDR). Unfortunately, the BH procedure can lead to over-optimistic assessments near the rejection threshold, with an increase of false discoveries at the margin as pointed out by Soloff et al. (2024). This issue is solved therein by […]

Ver mais

arXiv:2602.10305v1 Announce Type: new Abstract: Reward shaping has been applied widely to accelerate Reinforcement Learning (RL) agents’ training. However, a principled way of designing effective reward shaping functions, especially for complex continuous control problems, remains largely under-explained. In this work, we propose to automatically learn a reward shaping function for continuous control problems from offline datasets, potentially contaminated by unobserved confounding variables. Specifically, our method builds upon the recently proposed causal Bellman equation to learn a tight upper […]

Ver mais

arXiv:2602.04037v1 Announce Type: new Abstract: Learning domain adaptive policies that can generalize to unseen transition dynamics, remains a fundamental challenge in learning-based control. Substantial progress has been made through domain representation learning to capture domain-specific information, thus enabling domain-aware decision making. We analyze the process of learning domain representations through dynamical prediction and find that selecting contexts adjacent to the current step causes the learned representations to entangle static domain information with varying dynamical properties. Such mixture can […]

Ver mais

Human mobility trajectories are widely studied in public health and social science, where different demographic groups exhibit significantly different mobility patterns. However, existing trajectory generation models rarely capture this heterogeneity because most trajectory datasets lack demographic labels. To address this gap in data, we propose ATLAS, a weakly supervised approach for demographic-conditioned trajectory generation using only (i) individual trajectories without demographic labels, (ii) region-level aggregated mobility features, and (iii) region-level demographic compositions from census data. ATLAS trains a […]

Ver mais

arXiv:2602.13240v1 Announce Type: new Abstract: Code Large Language Models are frequently trained on massive datasets containing restrictively licensed source code. This creates urgent data governance and copyright challenges. Membership Inference Attacks (MIAs) can serve as an auditing mechanism to detect unauthorized data usage in models. While attacks like the Loss Attack provide a baseline, more involved methods like Polarized Augment Calibration (PAC) remain underexplored in the code domain. This paper presents an exploratory study evaluating these methods on […]

Ver mais