Natural Language Processing news and analysis on Web Pulse: 2607 curated articles tracking the latest Natural Language Processing developments, tools, and research, updated continuously from vetted sources.
Researchers from Duke University and NVIDIA introduced FedBPT, a method for efficient federated black-box prompt tuning of large language models, presented at ICML 2024. The approach enables collaborative fine-tuning wit…
Whissle Research Team introduced a meta-aware automatic speech recognition (ASR) model, META-1, that outputs transcription and metadata tokens (emotion, intent, demographics) in a single forward pass at ~200ms latency. B…
Apple has overhauled Siri in iOS 27, introducing Siri AI with personal context understanding, broad world knowledge, onscreen awareness, and app actions. The update makes Siri a competitor to chatbots like Claude and Cha…
A developer built contextcram, a zero-dependency Python library that prioritizes and packs context pieces (system prompts, chat history, documents) into a fixed token budget for LLM applications. It assigns each piece a …
Niixo launched moneasy, a budgeting app that avoids bank login by using Apple Vision Framework and Gemini 2.5 Flash for receipt OCR and Siri for voice entry. Transactions are stored via CloudKit sync without external ser…
Cartesia CEO Karan Goel announced the integration of Sonic 3.5 for text-to-speech and Ink 2 for speech-to-text into a unified voice-agent stack, claiming the company is now the only provider with models for both speaking…
Claude Shannon's 1950 paper 'Prediction and Entropy of Printed English' analyzes the statistical structure of English text, introducing concepts of entropy and redundancy in language. The work laid the foundation for inf…
Facebook launched AI Mode, a new search feature powered by Meta AI that generates conversational answers by synthesizing publicly posted content from across Meta apps including Facebook Groups, Reels, Instagram, and Thre…
Dirac, an AI email agent for founders, connects to Gmail or Outlook, learns the user's writing voice from sent mail, and delivers a morning brief with summaries, priorities, and ready-to-send drafts before the user opens…
A developer built a search engine over 50k saved tweets using hybrid retrieval and reranking, then added a single endpoint to turn it into an answer engine. By wiring Gemma 4 MoE to the retrieval pipeline, the system pro…
A three-step pipeline using pdfplumber, regex, and fuzzy matching converts unstructured invoices into structured data for RAG systems. The approach addresses common failures in extracting information from PDFs.
A writer reflects on a year in which they read more text generated by large language models than written by humans, and wrote more words for LLMs than for humans, leading to a shift in their perception of reading as an e…
Google unveiled Gemini 3.5 Live Translate, a new audio model that performs continuous streaming translation with only a few seconds of delay, enabling more natural multilingual conversations. The model supports over 70 l…
Organizations are adopting AI-powered redaction tools to automate the detection and removal of personally identifiable information (PII) in large document sets, addressing the limitations of manual redaction such as inco…
MiniMax launched Hub, an all-in-one AI video generator platform, at the Shanghai International Film Festival. The tool consolidates image, video, voiceover, music, and editing into a single interface with a human-in-the-…
GitHub released the GitHub Multilingual Repositories Dataset, a metadata dataset covering over 40 million repositories to help researchers and developers find public repositories with non-English natural-language content…
A developer explains how headless CMS teams can optimize content for AI answer engines like ChatGPT, Perplexity, and Google AI Overviews through Answer Engine Optimization (AEO). The key advantage of headless CMS is its …
A developer's guide to budget prompt engineering reveals that maximizing information density while minimizing token count can achieve premium-tier productivity from budget models like GPT-4.1-mini, DeepSeek-V3, and Phi-4…
Researchers have developed an anti-slop framework that reduces repetitive and robotic text outputs from large language models by 90%. The framework combines a backtracking sampler, an automated pipeline to identify overu…
The Seattle Fire Department has been using Corti AI to listen to all 911 medical calls since December 2023 without public disclosure or city council approval, routing callers to a nurse line in Texas. The department did …