All Articles
arXiv:2602.17835v1 Announce Type: new Abstract: Supervised fine-tuning (SFT) relies critically on selecting training data that most benefits a model's downstream performance. Gradient-based data selection methods …
arXiv:2602.17846v1 Announce Type: new Abstract: Diffusion models generate high-quality samples but can also memorize training data, raising serious privacy concerns. Understanding the mechanisms governing when …
arXiv:2602.17849v1 Announce Type: new Abstract: Training and serving Large Language Models (LLMs) relies heavily on parallelization and collective operations, which are frequently bottlenecked by network …
arXiv:2602.17853v1 Announce Type: new Abstract: Class imbalance induces systematic bias in deep neural networks by imposing a skewed effective class prior. This work introduces the …
arXiv:2602.17861v1 Announce Type: new Abstract: JAX-Privacy is a library designed to simplify the deployment of robust and performant mechanisms for differentially private machine learning. Guided …
arXiv:2602.17893v1 Announce Type: new Abstract: State space models (SSMs) have recently emerged for modeling long-range dependency in sequence data, with much simplified computational costs than …
arXiv:2602.17898v1 Announce Type: new Abstract: Attention-based regression models are often trained by jointly optimizing Mean Squared Error (MSE) loss and Pearson correlation coefficient (PCC) loss, …
arXiv:2602.17918v1 Announce Type: new Abstract: We study a sequential prediction problem in which an adversary is allowed to inject arbitrarily many adversarial instances in a …
arXiv:2602.17931v1 Announce Type: new Abstract: In environments with sparse or delayed rewards, reinforcement learning (RL) incurs high sample complexity due to the large number of …
arXiv:2602.17934v1 Announce Type: new Abstract: Graph data often contain noisy and spurious correlations that mask the true causal relationships, which are essential for enabling graph …
arXiv:2602.17940v1 Announce Type: new Abstract: We study an algorithm-independent, worst-case lower bound for the Gaussian process (GP) bandit problem in the frequentist setting, where the …
arXiv:2602.17941v1 Announce Type: new Abstract: Graph data is becoming increasingly prevalent due to the growing demand for relational insights in AI across various domains. Organizations …
