Latest AI/ML News
2784 articles · arXiv cs.CL
arXiv:2609.09569v1 Announce Type: new Abstract: News articles often contain omitted temporal expressions, such as day-only or month-only mentions, whi…
arXiv:2609.09561v1 Announce Type: new Abstract: Surveys remain the primary way researchers grasp the lineage of methods within an AI subfield, but the…
arXiv:2609.09554v1 Announce Type: new Abstract: We introduce BuzzASR, a collection of language-specialized fine-tuned Whisper models adapted for autom…
arXiv:2609.09552v1 Announce Type: new Abstract: In this paper, we solve two fundamental obstacles in applying LLMs to critical domains: token efficien…
arXiv:2609.09496v1 Announce Type: new Abstract: Algorithmic outputs now populate the digital environments through which contemporary life is organized…
arXiv:2609.09410v1 Announce Type: new Abstract: While autonomous agents have made significant strides in "deep research" by iteratively navigating the…
arXiv:2609.09363v1 Announce Type: new Abstract: Large language models (LLMs) are prone to hallucinating or misinterpreting facts, which impairs their…
arXiv:2609.09349v1 Announce Type: new Abstract: Modern LLMs demonstrate impressive multilingual performance, yet standard benchmarks primarily reward…
arXiv:2609.09338v1 Announce Type: new Abstract: Speculative decoding is critical for accelerating LLM inference. However, the speedup is fragile: draf…
arXiv:2609.09264v1 Announce Type: new Abstract: Leading benchmarks for formal theorem proving with large language models are small collections drawn f…
arXiv:2609.09166v1 Announce Type: new Abstract: This paper investigates collaborative speculative decoding (CoSD), a distributed large language model…
arXiv:2609.03742v2 Announce Type: replace-cross Abstract: Video lectures are valuable educational resources, but their dense and lengthy formats often…
arXiv:2609.03261v2 Announce Type: replace-cross Abstract: A benchmark score credits final answers, but not the route by which an item can be answered.…
arXiv:2608.11362v2 Announce Type: replace-cross Abstract: The computability of real numbers and functions using Turing Machines has been a central are…
arXiv:2607.27539v3 Announce Type: replace-cross Abstract: Certifying that a deletion did what it declared does not certify that the record left no tra…
arXiv:2607.17139v2 Announce Type: replace-cross Abstract: Code search enhances developer productivity by enabling efficient code reuse. Current code s…
arXiv:2606.29522v2 Announce Type: replace-cross Abstract: Activation steering can reliably change an agent's output by modifying its internal activati…
arXiv:2606.19706v2 Announce Type: replace-cross Abstract: Recent progress in vision-language models has enabled processing of increasingly long video…
arXiv:2606.05743v2 Announce Type: replace-cross Abstract: Despite advances in safety alignment, large language models remain vulnerable to continuousl…
arXiv:2605.08123v3 Announce Type: replace-cross Abstract: We study long-context balanced entropic optimal transport (OT) attention on TPU hardware thr…