Latest AI/ML News
9894 articles · arXiv cs.LG
arXiv:2609.39901v1 Announce Type: new Abstract: Goal-conditioned reinforcement learning (GCRL) relies heavily on how target goals are represented to t…
arXiv:2609.39892v1 Announce Type: new Abstract: Looped Transformers repeatedly apply the same set of Transformer layers, giving them a recurrent archi…
arXiv:2609.39888v1 Announce Type: new Abstract: Neural trajectory predictors can reach low prediction error while violating dynamics, actuator limits,…
arXiv:2609.39877v1 Announce Type: new Abstract: Algorithmic recourse provides individuals who have received undesirable outcomes from machine learning…
arXiv:2609.39866v1 Announce Type: new Abstract: Open-weight LLMs are released not only as fixed products but also as substrates for downstream fine-tu…
arXiv:2609.39859v1 Announce Type: new Abstract: Masked diffusion language models (dLLMs) have shown strong potential for faster inference through para…
arXiv:2609.39855v1 Announce Type: new Abstract: We study the width required for a randomly initialized hidden layer of a neural network to achieve ran…
arXiv:2609.39848v1 Announce Type: new Abstract: Foundation models are increasingly adopted across a wide range of applications, often serving as core…
arXiv:2609.39839v1 Announce Type: new Abstract: Class-Incremental Learning (CIL) aims to continuously learn new classes without forgetting previously…
arXiv:2609.39837v1 Announce Type: new Abstract: Policy mirror descent (PMD) enjoys fast convergence in regularized Markov decision processes (MDPs), b…
arXiv:2609.39833v1 Announce Type: new Abstract: Extreme rainfall events are increasing in intensity and frequency as climate change accelerates. While…
arXiv:2609.39818v1 Announce Type: new Abstract: In many high-stakes settings, human decision-makers can acquire support information before making a de…
arXiv:2609.39816v1 Announce Type: new Abstract: Fast matrix multiplication saves multiplications through exact cancellation, but rounding sums that mi…
arXiv:2609.39813v1 Announce Type: new Abstract: Low-precision training rounds tensors that the backward pass reads again, often for several gradients;…
arXiv:2609.39810v1 Announce Type: new Abstract: Source-Free Universal Domain Adaptation (SF-UniDA) extends Universal Domain Adaptation by removing acc…
arXiv:2609.39801v1 Announce Type: new Abstract: Post-training quantization (PTQ) has become a widely adopted technique for reducing the memory footpri…
arXiv:2609.39800v1 Announce Type: new Abstract: We analyse allocation, admission and post-write retention in finite-horizon linear-Gaussian noisy recu…
arXiv:2609.39798v1 Announce Type: new Abstract: Building on a probabilistic perspective in which adversarial examples arise from the overlap between a…
arXiv:2609.39792v1 Announce Type: new Abstract: Distinguishing periodic from chaotic dynamics in a time series is a fundamental challenge in both phys…
arXiv:2609.39789v1 Announce Type: new Abstract: Real-world time series forecasting systems operate under non-stationary data streams, where forecastin…