Academic
arXiv:2602.17809v1 Announce Type: new Abstract: Parameter-efficient fine-tuning methods such as LoRA enable practical adaptation of large language models but provide no principled uncertainty estimates, leading …
arXiv:2602.17827v1 Announce Type: new Abstract: Generative Flow Networks (GFlowNets) are a flexible family of amortized samplers trained to generate discrete and compositional objects with probability …
arXiv:2602.17829v1 Announce Type: new Abstract: Inferring causal relations in timeseries data with delayed effects is a fundamental challenge, especially when the underlying system exhibits complex …
arXiv:2602.17832v1 Announce Type: new Abstract: Stochastic Optimal Control provides a unified mathematical framework for solving complex decision-making problems, encompassing paradigms such as maximum entropy reinforcement …
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 …
