Latest AI/ML News
2784 articles · arXiv cs.CL
arXiv:2609.10745v1 Announce Type: new Abstract: Multimodal entity linking grounds entity mentions in text and images to knowledge-base entries. These…
arXiv:2609.10722v1 Announce Type: new Abstract: Structured extraction from Chinese military news supports intelligence analysis, decision-making, and…
arXiv:2609.10715v1 Announce Type: new Abstract: We introduce NCP-ArchPreview, a latent-space language model that pushes autoregressive pretraining bey…
arXiv:2609.10702v1 Announce Type: new Abstract: Learning from limited text requires models to use context, generalize to new inputs, and retain useful…
arXiv:2606.05538v2 Announce Type: replace-cross Abstract: Mixture-of-Experts (MoE) models achieve strong performance through conditional computation,…
arXiv:2604.27695v2 Announce Type: replace-cross Abstract: Long-term conversational memory requires retrieving evidence scattered across multiple sessi…
arXiv:2604.23036v2 Announce Type: replace-cross Abstract: Despite MoE models leading many benchmarks, supervised fine-tuning (SFT) for the MoE archite…
arXiv:2601.17036v2 Announce Type: replace-cross Abstract: ArXiv recently prohibited the upload of unpublished review papers to its servers in the Comp…
arXiv:2510.15047v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) as agents often fail to improve in new environments. We identif…
arXiv:2609.00335v2 Announce Type: replace Abstract: Following arXiv:2607.25507, this report examines whether phase-derived features improve endpoint p…
arXiv:2608.26697v2 Announce Type: replace Abstract: Synthetic speech offers scalable supervision for automatic speech recognition (ASR), but its benef…
arXiv:2608.08869v2 Announce Type: replace Abstract: Large language models are increasingly used for ordinal classification, yet semantically equivalen…
arXiv:2607.28707v3 Announce Type: replace Abstract: Entropy-based pruning has been proposed as an effective method for compressing Chain-of-Thought (C…
arXiv:2607.25507v2 Announce Type: replace Abstract: Transformer language models are usually analyzed through vector geometry, yet ordered context and…
arXiv:2607.11258v2 Announce Type: replace Abstract: Tree search algorithms enable systematic exploration of the proof space in neural theorem proving.…
arXiv:2607.00890v2 Announce Type: replace Abstract: Open web-scale pre-training corpora remain concentrated in English, limiting multilingual LLM deve…
arXiv:2606.26040v2 Announce Type: replace Abstract: AI translation of literary works is increasingly common. While the content may be rendered adequat…
arXiv:2606.18216v3 Announce Type: replace Abstract: Knowledge distillation transfers a teacher's competence to a small student but is brittle in the s…
arXiv:2606.13945v2 Announce Type: replace Abstract: Rare diseases affect over $300$ million patients across more than $7{,}000$ conditions, yet no sin…
arXiv:2606.12186v2 Announce Type: replace Abstract: Enthymemes, arguments with unstated premises or conclusions, are pervasive in persuasive discourse…