Natural Language Processing news and analysis on Web Pulse: 5440 curated articles tracking the latest Natural Language Processing developments, tools, and research, updated continuously from vetted sources.
Pakistan Telecommunication Company Limited (PTCL) will deploy SILA, an AI-powered sign language agent built by Pakistani accessibility technology company ConnectHear, across its customer care centers beginning in Karachi…
OpenAI released GPT-Live-1 through its API platform, a voice model that can listen and speak simultaneously, priced at $0.05 per minute. OpenAI reports GPT-Live-1 achieves 0.798-second turn-taking latency on its Full Dup…
A tutorial demonstrates treating prompt templates as tunable hyperparameters by wrapping a language model in a scikit-learn-compatible classifier and running GridSearchCV over candidate prompts for zero-shot text classif…
Orthrus, a hybrid autoregressive-diffusion architecture for accelerating autoregressive language-model inference, claims its intra-model consensus mechanism enables lossless speculative decoding, according to the source.…
A developer explains embeddings, the numerical vector representations that let AI systems compare meaning rather than exact text matches. The piece describes how an embedding model converts text into high-dimensional vec…
A Towards Data Science analysis measured how many labeled examples a text classifier actually needs, finding that a decades-old baseline can handle many classification problems before developers reach for an LLM API. The…
A developer proposes a "known-answer" testing method for spreadsheet AI copilots, arguing that assistants should first reproduce verified totals and explain their cell ranges before being trusted with unfamiliar business…
Contact centers adopting Voice AI must still route most voice traffic over the PSTN, making telephony integration central to customer experience deployments, according to an analysis of voice infrastructure for CX. The a…
Dynin-Robotics has implemented an omnimodal unified diffusion vision-language-action model that brings visual goal and dynamics prediction into action generation and selection through a shared trajectory model, according…
A developer released Back Me Up, a tool that performs semantic search across PMC, bioRxiv, medRxiv and arXiv to find published papers supporting a user-entered claim and returns a verdict. The developer states the projec…
A developer has documented the architecture for an AI voice sales agent that lets dealers place product orders through a phone conversation, combining Twilio telephony, the OpenAI Realtime API, and LangGraph for stateful…
A Medium post in the "AI in Plain English" series argues that BM25 keyword ranking remains essential to retrieval-augmented generation (RAG) systems even as embeddings draw widespread attention. The author walks through …
Bol.com launched Shophulp, an AI shopping assistant available in beta starting today in the bol app and on the website, letting customers describe what they need in natural language to get product recommendations with cu…
The FedV-KGQA poster paper reports that federated fusion across vertically partitioned knowledge graphs recovers most of the accuracy of a centralized system, while a single silo recovers little. The work, presented as a…
A new paper on arXiv (2609.13648v1) introduces Solar Intelligence, a hybrid retrieval-augmented framework that unifies structured solar analytics, evidence-grounded scientific question answering, and machine learning for…
Researchers proposed FLoKD, an adaptive knowledge-distillation framework for federated LoRA fine-tuning of large language models over wireless networks that transmits intermediate LoRA activations instead of logits or fu…
The University of Melbourne's submission to the WMT 2026 Creole Language Translation Shared Task reports that its machine translation models for Pacific creoles Tok Pisin, Bislama, and Solomon Pijin beat open model basel…
A new arXiv paper (2609.13581v1) presents an evidence-driven alignment framework for hospital discharge summarization that treats provenance as a first-class constraint, using semantic graphs and deep learning models to …
Researchers built pseudo-references for the WMT26 General MT task's 10 reference-free language pairs by translating 3,277 official documents with seven models across up to five prompt conditions, producing 26 system-prom…
Researchers proposed ModelLog, a declarative probabilistic framework for pre-training evaluation of large language models that specifies evaluation targets as symbolic constraints over token-level predictions, according …