Latest AI/ML News
2784 articles · arXiv cs.CL
arXiv:2610.03387v2 Announce Type: replace-cross Abstract: Rejection policies must remain useful as candidate sets and tasks change. We compare Laya, J…
arXiv:2607.20791v2 Announce Type: replace-cross Abstract: Recent advances in truncation-based sampling have helped mitigate drawbacks of high-temperat…
arXiv:2607.10162v2 Announce Type: replace-cross Abstract: Sound symbolism, the human tendency to map speech sounds to perceptual qualities such as rou…
arXiv:2606.05761v3 Announce Type: replace-cross Abstract: Persistent AI assistants, such as OpenClaw, accumulate large collections of related memories…
arXiv:2606.05647v2 Announce Type: replace-cross Abstract: AI coding agents are increasingly embedded in real-world software development, collaborating…
arXiv:2605.30557v2 Announce Type: replace-cross Abstract: Spatial reasoning benchmarks typically evaluate whether vision-language models can derive th…
arXiv:2605.12922v2 Announce Type: replace-cross Abstract: Large language models can follow complex instructions in a single turn, yet over long multi-…
arXiv:2604.09945v3 Announce Type: replace-cross Abstract: The rapid adoption of large vision-language models (LVLMs) in recent years has been accompan…
arXiv:2603.08231v2 Announce Type: replace-cross Abstract: Paralinguistic speech tasks are often considered relatively language-agnostic, as they rely…
arXiv:2601.17645v2 Announce Type: replace-cross Abstract: Internet audio-visual clips convey meaning through time-varying sound and motion, which exte…
arXiv:2601.12966v2 Announce Type: replace-cross Abstract: The Lombard effect plays a key role in natural communication, particularly in noisy environm…
arXiv:2409.19979v4 Announce Type: replace-cross Abstract: Large language models (LLMs) have demonstrated prominent reasoning capabilities in recommend…
arXiv:2610.06729v2 Announce Type: replace Abstract: Large language models (LLMs) can generate accurate responses, but these are void of diversity. We…
arXiv:2610.06650v2 Announce Type: replace Abstract: Wikidata is one of the largest open knowledge bases, yet answering a complex question over it stil…
arXiv:2610.06625v2 Announce Type: replace Abstract: Large language models (LLMs) annotate and scale political text or constructs by generating text to…
arXiv:2610.05275v2 Announce Type: replace Abstract: A large part of political discourse on social media is built and expressed at a level of claims: i…
arXiv:2610.04687v2 Announce Type: replace Abstract: Answering questions over imperfect tables requires handling errors that can affect the answer. We…
arXiv:2610.02970v2 Announce Type: replace Abstract: Large language models (LLMs) have shown promising potential for biomedical named entity recognitio…
arXiv:2610.01108v2 Announce Type: replace Abstract: Retrieval-based speculative decoding (SD) drafts tokens by copying continuations from existing tex…
arXiv:2609.40185v2 Announce Type: replace Abstract: Constrained generation aims to sample from language models (LMs) conditioned on hard constraints.…