Latest AI/ML News
9894 articles · arXiv cs.LG
arXiv:2311.18029v2 Announce Type: replace Abstract: The current trend in the literature on Time Series Classification is to develop increasingly accur…
arXiv:2610.08789v1 Announce Type: cross Abstract: Flow policies have become a standard policy class for learning robot behaviors from demonstrations,…
arXiv:2610.08773v1 Announce Type: cross Abstract: Web agents complete user requests by reading and acting on pages that third parties write, so an ins…
arXiv:2610.08764v1 Announce Type: cross Abstract: We develop the first feedback design for rapid stabilization of the Kuramoto--Sivashinsky equation w…
arXiv:2610.08738v1 Announce Type: cross Abstract: Diffusion Language Models (DLMs) hold the promise of order-agnostic, parallel text generation. Recen…
arXiv:2610.08722v1 Announce Type: cross Abstract: Many long-horizon agents compact their context on a global rule, usually a token budget, blind to wh…
arXiv:2610.08718v1 Announce Type: cross Abstract: Knowledge that a language model appears to forget during finetuning often remains stored and can be…
arXiv:2610.08717v1 Announce Type: cross Abstract: We study path-flow alignment as a unified training objective for flow matching. Instead of fixing th…
arXiv:2610.08715v1 Announce Type: cross Abstract: The following motif is common in spatiotemporal settings: we have a sequence of covariate and label…
arXiv:2610.08678v1 Announce Type: cross Abstract: Speculative decoding accelerates inference for a large language model (LLM), referred to as the \emp…
arXiv:2610.08652v1 Announce Type: cross Abstract: Diffusion models are increasingly used as surrogates for expensive simulators in weather prediction,…
arXiv:2610.08647v1 Announce Type: cross Abstract: LLM-based agents solve complex multi-step tasks, but sequential execution incurs substantial latency…
arXiv:2610.08626v1 Announce Type: cross Abstract: Diffusion models generate data through a continuum of denoising problems, and are widely observed to…
arXiv:2610.08574v1 Announce Type: cross Abstract: Skin cancer is a major global health concern, and early detection and accurate lesion delineation ar…
arXiv:2610.08571v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) systems are vulnerable to prompt-injection attacks embedded in…
arXiv:2610.08560v1 Announce Type: cross Abstract: Streaming video-language models must decide not only what to answer, but whether the evidence needed…
arXiv:2610.08559v1 Announce Type: cross Abstract: Activation steering has gained popularity as a lightweight inference-time debiasing technique for la…
arXiv:2610.08554v1 Announce Type: cross Abstract: While HCI increasingly examines AI-safety for youth, the literature lacks a comprehensive view of wh…
arXiv:2610.08552v1 Announce Type: cross Abstract: Concept bottleneck models (CBMs) make predictions inspectable and intervenable by routing them throu…
arXiv:2610.08540v1 Announce Type: cross Abstract: Whether alignment gets easier or harder as models grow is often argued from isolated findings, as if…