Latest AI/ML News
9894 articles · arXiv cs.LG
arXiv:2609.39369v1 Announce Type: cross Abstract: Specialized models encode task-oriented behavior, but transferring that behavior to a general langua…
arXiv:2609.39367v1 Announce Type: cross Abstract: Despite the widespread use of Low-Rank Adaptation (LoRA), little is known about its dynamics in cont…
arXiv:2609.39358v1 Announce Type: cross Abstract: A transformer language model performs a bounded amount of computation per token, and recent work by…
arXiv:2609.39351v1 Announce Type: cross Abstract: We study preference-based bandits with general reward function classes, where a learner sequentially…
arXiv:2609.39350v1 Announce Type: cross Abstract: As model sizes continue to scale, distributed training has become inevitable. Automatic parallelizat…
arXiv:2609.39343v1 Announce Type: cross Abstract: Diffusion caching accelerates generation by replacing transformer computation with cached or predict…
arXiv:2609.39341v1 Announce Type: cross Abstract: Does a language model merely predict tokens, or does it understand what it says? We make this questi…
arXiv:2609.39326v1 Announce Type: cross Abstract: Count data pose a challenge for score-matching-based causal discovery: derivatives are unavailable,…
arXiv:2609.39324v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have recently incorporated world models to provide richer dynami…
arXiv:2609.39301v1 Announce Type: cross Abstract: This paper considers a class of multiblock nonconvex and nonsmooth optimization problems arising in…
arXiv:2609.39263v1 Announce Type: cross Abstract: A concept subspace's effect on model behavior does not establish how it relates to the output readou…
arXiv:2609.39259v1 Announce Type: cross Abstract: Modern neural networks scale predictably, yet the mechanisms behind these regularities remain unclea…
arXiv:2609.39229v1 Announce Type: cross Abstract: Automatic evaluation of faithfulness increasingly relies on a large language model acting as a judge…
arXiv:2609.39220v1 Announce Type: cross Abstract: Process reward models (PRMs) have demonstrated notable effectiveness in test-time scaling and reinfo…
arXiv:2609.39212v1 Announce Type: cross Abstract: We study additive regression under a potentially non-product random design on $[0,1]^d$, allowing th…
arXiv:2609.39184v1 Announce Type: cross Abstract: Fiber orientation and compartmental microstructure are central to the characterization of white matt…
arXiv:2609.39173v1 Announce Type: cross Abstract: In this paper, we consider asymptotic properties of the support vector machine (SVM) in high-dimensi…
arXiv:2609.39172v1 Announce Type: cross Abstract: Fingerprint recognition is a widely deployed biometric, but supervised training requires large label…
arXiv:2609.39162v1 Announce Type: cross Abstract: Speaker diarization systems based on speaker embeddings and neural diarization exploit complementary…
arXiv:2609.39151v1 Announce Type: cross Abstract: Does memory-dependent control need nonlinear recurrent dynamics? We study simulated air-hockey defen…