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.
A comparison of three Thai text-to-speech systems finds that ThonburianTTS, built by a Thai research team on the F5-TTS architecture with flow matching, delivers the most accurate Thai pronunciation and voice cloning, wh…
Three Thai open-weight LLM projects — SCB 10X's Typhoon, the Thai AI Entrepreneur Association's OpenThai, and VISTEC's Pathumma — offer locally runnable, commercially usable alternatives to foreign models, each different…
Researchers introduced Mosaic, a training-free framework that formulates GraphRAG retrieval as a per-query control problem, with an LLM analyzer converting query-specific evidence requirements into a bounded policy over …
A new arXiv paper (2609.11199v1) presents an AI-driven, culturally sensitive stress detection and wellness support system for Pakistani university students, built on a Random Forest model trained on 1,100 validated stude…
A study of 70,500 X messages tied to securities class actions from 2002 to 2025 found that benchmark agreement between financial sentiment tools and human labels establishes semantic validity but does not by itself deter…
A multi-agent framework that automatically generates Quadratic Unconstrained Binary Optimization (QUBO) formulations from natural-language problem descriptions achieved 68% accuracy on QUBOBench, a new benchmark of 100 c…
Researchers introduced the KuaiRP series of role-playing models in a technical report, using a multi-stage training pipeline to inject deep domain knowledge without losing general agent capabilities. The pipeline combine…
Researchers introduced RAMamba-Net, a reliability-aware Mamba-based multimodal fusion network for auditory attention decoding (AAD) that combines electroencephalography (EEG) and electrooculography (EOG) signals, accordi…
A new benchmark called NovGauge, built from 619 paper pairs and 50 multi-paper sets drawn from ICLR reviewer overlap claims and survey co-citations, finds that large language models remain unreliable at assessing scienti…
A developer's experiment testing a full hierarchical Pitman-Yor language model with Gibbs sampling and inferred hyperparameters found it fails to match the data-scaling slope of a small transformer, gaining only +0.008 t…
A developer built LinkDigest, a hosted reader and MCP server that converts links from Xiaohongshu, Douyin, TikTok, YouTube and X into LLM-usable text, including transcripts with timecodes, on-screen text, image descripti…
A developer released Next Notes, a native macOS dictation and meeting-notes app that runs fully on-device, supporting Apple and Parakeet transcription plus deterministic or on-device LLM cleanup. The app records calendar…
A data scientist's informal test found that six of seven major chatbots — ChatGPT, Gemini, Claude, DeepSeek, Llama and Qwen — all returned 27 when asked for a random number between 1 and 50, with only Grok answering 42. …
Gartner, Inc. (NYSE:IT) posted an on-site Lead Software Engineer role in Gurgaon for NLP and generative AI, requiring 7-9 years of experience in algorithms, statistics, data mining, machine learning, deep learning and na…
A developer reduced voice AI response latency from roughly nine seconds to about 1.5 seconds by replacing a VAPI-based integration with an in-house architecture that orchestrates Twilio for telephony, Deepgram for speech…
A Rust-based tool called Spanda computes LLM epistemic uncertainty in 652.1 nanoseconds (0.65 µs) per evaluation, roughly 90,000× faster than neural Semantic Entropy methods that add about 92.4 ms of GPU overhead per inf…
Semrush Traffic Analytics estimates that chatgpt.com received about 1.09 billion US visits in July 2026, a 48.38% year-over-year increase, while bing.com referrals fell roughly 50.43% and Google's direct figures rose 10.…
A developer tool called GPU-time parses plain-English date and time phrases into real dates and RFC 5545 recurrence rules using a small neural model with 24,761 parameters that runs locally in the browser. The tool accep…
A developer has published a TypeScript tutorial for building an atomic handoff coordinator for AI-assisted direct messages on Tencent RTC's Social Messaging platform. The coordinator enforces a single invariant — at most…
A proposed evaluation method for video captioning replaces BLEU and METEOR with Multiple-Choice Question Answering (MCQA), scoring captions by the percentage of video-grounded questions an LLM can answer correctly from t…