Latest AI/ML News
9894 articles · arXiv cs.LG
arXiv:2609.38916v1 Announce Type: cross Abstract: Any-dimensional machine learning models, such as graph neural networks (GNNs), can be naturally trai…
arXiv:2609.38914v1 Announce Type: cross Abstract: Evaluating interactive agents is expensive. Agent behavior is stochastic, so reliability must be mea…
arXiv:2609.38908v1 Announce Type: cross Abstract: Single-cell transcriptomics enables profiling of cellular states at unprecedented resolution, but it…
arXiv:2609.38899v1 Announce Type: cross Abstract: Video Multimodal Large Language Models (Video-MLLMs) support reasoning over video inputs, yet remain…
arXiv:2609.38887v1 Announce Type: cross Abstract: Real-time voice conversion (VC) systems commonly rely on pretrained speaker embeddings from automati…
arXiv:2609.38880v1 Announce Type: cross Abstract: We study the last iterate of standard tabular temporal-difference (TD) learning from a single trajec…
arXiv:2609.38851v1 Announce Type: cross Abstract: End-to-end accuracy on compositional tasks records how often MLLMs fail, but cannot distinguish whet…
arXiv:2609.38842v1 Announce Type: cross Abstract: Learn-then-differentiate (LTD) estimates gradients by fitting a model to simulation outputs and diff…
arXiv:2609.38835v1 Announce Type: cross Abstract: Optimistic matrix mirror-prox (OMMP) computes $\epsilon$-approximate Nash equilibria in quantum zero…
arXiv:2609.38834v1 Announce Type: cross Abstract: Contrastive learning is a successful paradigm for learning $d$-dimensional geometric representations…
arXiv:2609.38812v1 Announce Type: cross Abstract: Terminal agents rely on self-verification to assess and correct their solutions as they solve tasks…
arXiv:2609.38811v1 Announce Type: cross Abstract: Metal additive manufacturing parts are inspected by X-ray computed tomography, where labelled data i…
arXiv:2609.38795v1 Announce Type: cross Abstract: Block drafters for speculative decoding are commonly trained on corpora written by external models,…
arXiv:2609.38792v1 Announce Type: cross Abstract: We study training LLM judges from natural language feedback, especially for subjective tasks where t…
arXiv:2609.38733v1 Announce Type: cross Abstract: Recent LLM-based approaches to control either invoke a language model to select actions or synthesiz…
arXiv:2609.38680v1 Announce Type: cross Abstract: Text-to-image diffusion models are personalized to a subject by DreamBooth fine-tuning on a handful…
arXiv:2609.38659v1 Announce Type: cross Abstract: We study multi-armed bandits (MAB) with multiple optimal arms, motivated by the fact that many pract…
arXiv:2609.38653v1 Announce Type: cross Abstract: Recent advances in musculoskeletal modeling and reinforcement learning have enabled muscle-actuated…
arXiv:2609.38638v1 Announce Type: cross Abstract: Pickup trucks account for 14% of new light-duty vehicles produced in the United States, yet are amon…
arXiv:2609.38636v1 Announce Type: cross Abstract: We introduce Scene Text Editing with Preserved Style (STEPS), a novel diffusion model architecture f…