Studying the Effects of Collaboration in Interactive Theme Discovery Systems
12月 22, 2025admin NUAI,Committee,ニュース,Uncategorized(0)arXiv:2408.09030v4 Announce Type: replace Abstract: NLP-assisted solutions have gained considerable traction to support qualitative data...
Structured PDF-to-JSON: A Guide to Open-Source Extraction Models in 2026
7月 5, 2026admin NUAI,Committee,ニュース,Uncategorized(0)Most enterprise data still sits inside PDFs, scans, and slide decks. Large language models and...
Structured Outputs vs. Function Calling: Which Should Your Agent Use?
4月 13, 2026admin NUAI,Committee,ニュース,Uncategorized(0)Language models (LMs), at their core, are text-in and text-out systems...
Structure-Aware Chunking for Tabular Data in Retrieval-Augmented Generation
5月 4, 2026admin NUAI,Committee,ニュース,Uncategorized(0)arXiv:2605.00318v1 Announce Type: new Abstract: Tabular documents such as CSV and Excel files are widely...
Stronger Normalization-Free Transformers
12月 12, 2025admin NUAI,Committee,ニュース,Uncategorized(0)arXiv:2512.10938v1 Announce Type: cross Abstract: Although normalization layers have long been viewed as indispensable components...
Stripe, Anthropic, and OpenAI are backing an effort to stop respiratory infections
6月 24, 2026admin NUAI,Committee,ニュース,Uncategorized(0)The common cold comes for us all—often more than once a year. And there is...
StreamTensor: A PyTorch-to-Accelerator Compiler that Streams LLM Intermediates Across FPGA Dataflows
10月 6, 2025admin NUAI,Committee,ニュース,Uncategorized(0)Why treat LLM inference as batched kernels to DRAM when a dataflow compiler can pipe...
Streaming Sequence-to-Sequence Learning with Delayed Streams Modeling
9月 11, 2025admin NUAI,Committee,ニュース,Uncategorized(0)arXiv:2509.08753v1 Announce Type: new Abstract: We introduce Delayed Streams Modeling (DSM), a flexible formulation for...
Stopping Computation for Converged Tokens in Masked Diffusion-LM Decoding
2月 9, 2026admin NUAI,Committee,ニュース,Uncategorized(0)arXiv:2602.06412v1 Announce Type: new Abstract: Masked Diffusion Language Models generate sequences via iterative sampling that...
