Natural Language Processing news and analysis on Web Pulse: 5432 curated articles tracking the latest Natural Language Processing developments, tools, and research, updated continuously from vetted sources.
DiffFind launched a semantic search and diff tool that compares text and documents by character, word, sentence, line, or paragraph and tracks additions, removals, and moved text. The tool supports JSON, YAML, XML, CSV, …
A developer has built SignBridge, a prototype that generates videos of individual words being signed in American Sign Language from text prompts. The developer, who has years of ASL experience in the Deaf community, repo…
Sarvam AI released Saaras V4, a speech-to-text model covering all 22 scheduled Indian languages plus global English accents, available today through Sarvam's API as model="saaras:v4". Sarvam reports state-of-the-art accu…
A developer built an order risk detector on Laya, an open-source non-autoregressive decision model based on ModernBERT, to test whether a small specialized model can replace large generative LLMs for e-commerce fraud det…
Supersonic Labs, a small AI lab from Brazil, released Julia 1, a 144.3M-parameter open decision model that runs on a plain CPU and is published on Hugging Face under Apache 2.0. Julia 1 starts from JHU CLSP's 140M-parame…
A developer published a Python tutorial building an "utterance commit gate" for Tencent RTC Conversational AI voice applications, a state-machine controller that waits for a configurable quiet window before committing a …
Developer "&." released an early-prototype webpage at ampdot.mesh.host that generates a token-space font by combining a base font with a user-selected tokenizer, giving every token equal width so AI outputs can be read a…
Dhruva Karkada's paper on arXiv (2602.15029) showed that LLM embeddings of the 12 months project onto a circle with an approximately circulant Gram matrix, a result the author of the post bet a beer he could reproduce wi…
TypeSafe AI's Jev is a typed, probabilistic decision API that maps unstructured text to finite labels and code branches, positioning itself as a System One alternative to GPT-class LLMs for high-volume classification tas…
A first systematic study of epistemic diversity in large language models, testing 27 LLMs on 155 topics across 12 countries and generating 1.7M responses and 70M individual claims, found that epistemic diversity has incr…
A developer proposes a "claim-to-source contract" for healthcare retrieval-augmented generation systems, arguing that a working citation link does not prove an answer's claims are supported by the cited passage. The desi…
A tutorial demonstrates an end-to-end multimodal data augmentation and adversarial robustness workflow using Meta's AugLy library for images, text, and audio, connected directly to PyTorch datasets and DataLoaders. The w…
A developer found that setting Deepgram's endpointing parameter to 300ms caused 22% of long user answers to be cut off mid-thought in their voice interview practice tool, Preterview. Analysis of 1,140 long answers showed…
A new token-space font compiler generates TTF fonts in which every LLM token renders at the same width, built from a font plus a tokenizer such as DeepSeek V4.1 Flash's byte-level BPE pre-tokenizer. The tool ships with s…
Edge0 released Audio8 ASR Infinite, an open-weight streaming speech recognition model under the Apache 2.0 license, available on Hugging Face as Edge0/Audio8-ASR-Infinite and on GitHub as Edge0-AI/Audio8-ASR-Infinite. Th…
Munder Difflin released version 0.5.3, adding a local transcription feature called Stapler that dictates into any app and records meetings with both sides of a call labeled "You" and "Them," running entirely on the user'…
A developer released Scripta v3.4.7, a macOS meeting transcription app that adds local scheduled recordings so sessions can auto-start without sending anything to the cloud. The update introduces a ScheduleCoordinator th…
A September 24, 2026 arXiv paper proposes an agentic framework that uses social-context tools to detect conspiracy discourse in online posts by inferring a speaker's intent rather than relying on explicit claims or lexic…
Amazon SageMaker JumpStart now offers the publicly available Qwen3-TTS-12Hz-1.7B-Base text-to-speech model from Alibaba Cloud's Qwen team for deployment to fully managed, real-time inference endpoints, enabling voice clo…
A developer built cbjev, an open decision model that packs multiple typed questions about a document into a single encoder pass, making inference 6.7x faster than the Laya model it is fine-tuned from. On one RTX 4090, cb…