Latest AI/ML News
2784 articles · arXiv cs.CL
arXiv:2609.21084v1 Announce Type: cross Abstract: Modern automatic speech recognition (ASR) systems trained on extremely large datasets can produce tr…
arXiv:2609.20995v1 Announce Type: cross Abstract: Natural spoken interaction requires more than streaming ASR, language generation, and speech synthes…
arXiv:2609.20875v1 Announce Type: cross Abstract: Parkinson's disease (PD) often manifests through speech impairments, facilitating accessible, non-in…
arXiv:2609.22081v1 Announce Type: new Abstract: Occupational accident narratives contain valuable information about work situations, unfavourable cond…
arXiv:2609.22043v1 Announce Type: new Abstract: Memory systems for large language models have focused predominantly on efficient retrieval, whereas th…
arXiv:2609.22038v1 Announce Type: new Abstract: We introduce QuranicMMLU, a benchmark for evaluating generative AI on Quranic Arabic across multiple d…
arXiv:2609.22000v1 Announce Type: new Abstract: Computer-use agents (CUAs) have advanced along two separate lines: graphical interaction and software…
arXiv:2609.21992v1 Announce Type: new Abstract: Most work in computational ethics treats annotator disagreement on moral content as noise to be voted…
arXiv:2609.21859v1 Announce Type: new Abstract: Nearly 90% of drugs entering clinical development ultimately fail, despite billions of dollars in inve…
arXiv:2609.21844v1 Announce Type: new Abstract: Long transcripts are costly inputs for downstream NLP systems and often contain irrelevant context. We…
arXiv:2609.21789v1 Announce Type: new Abstract: Most multilingual dysarthria-severity systems either train on a single aetiology-language pair or pool…
arXiv:2609.21673v1 Announce Type: new Abstract: Probabilistic Graphical Models (PGMs), especially Bayesian Networks (BNs), expose directed structure a…
arXiv:2609.21663v1 Announce Type: new Abstract: Word Error Rate (WER), the most commonly used metric for Automatic Speech Recognition (ASR), treats ev…
arXiv:2609.21595v1 Announce Type: new Abstract: In-context learning using Large Language Models (LLMs) offers a compelling path to training-free post-…
arXiv:2609.21554v1 Announce Type: new Abstract: Recent advances in Large Language Models (LLMs) have revolutionized artificial intelligence and how hu…
arXiv:2609.21490v1 Announce Type: new Abstract: Gender bias remains a persistent concern in machine translation (MT), affecting both generated transla…
arXiv:2609.21392v1 Announce Type: new Abstract: Natural audio-visual interaction is emerging as an important interface for AI assistants, allowing use…
arXiv:2609.21378v1 Announce Type: new Abstract: Reinforcement learning has substantially improved large language model (LLM) agents in verifiable doma…
arXiv:2609.21362v1 Announce Type: new Abstract: Conventional tokenizers represent text as characters or statistically derived subwords, overlooking th…
arXiv:2609.21247v1 Announce Type: new Abstract: Large Reasoning Models increasingly use intermediate traces for machine translation, but it remains un…