Natural Language Processing news and analysis on Web Pulse: 5576 curated articles tracking the latest Natural Language Processing developments, tools, and research, updated continuously from vetted sources.
Researchers introduced SAMPA, a Whisper-based model for prosodic segmentation in Brazilian Portuguese, achieving F1 scores of 0.731 on held-out test data and 0.796 on the MuPe-Diversidades dataset. The model outperforms …
A July 10, 2026 Python guide from How To Profit AI details building an asynchronous agent that aggregates updates from Slack, Jira, and email into daily project summaries, offering a blueprint for teams to automate cross…
A developer uses the analogy of galaxies in the night sky to explain how large language models (LLMs) work, mapping semantic space onto celestial structures. The analogy illustrates how prompts set entry points into sema…
Mistral released Robostral Navigate, an 8B-parameter AI model that uses a single RGB camera and natural-language instructions to navigate robots through indoor spaces. The model achieved a 76.6% success rate on the R2R-C…
Researchers found that the Gemma 4 2B vision-language model achieved 93.65% accuracy in detecting fast radio bursts, nearly matching the specialized SwinYNet detector's 92.90%, while producing far fewer false positives o…
Automated content moderation systems continue to disproportionately censor Arabic, LGBTQ+, and other marginalized content due to biased datasets and lack of cultural competence, according to reports from the Center for D…
New research reveals that transformer-based vision-language models are vulnerable to adversarial attacks through their spectral structure, introducing the spectral-subspace-guided attack (SSGRA) that exploits these weakn…
Artificial intelligence is transforming academic conferences by using deep learning and knowledge graph technology to analyze vast amounts of data, helping researchers find relevant information and predict trends. This t…
Researchers have developed a reference-free evaluation framework for Vision-Language Models that converts flowchart images into code, using OCR and visual entailment to assess output quality without ground-truth data. Va…
A new AI method using prefix control tokens and BART fine-tuning for ad headline generation claims a 25.82% increase in Rouge-L and a 5.82% boost in estimated click-through rates over previous baselines. The technique of…
A new study reveals that multilingual AI models in healthcare exhibit significant language bias, with responses aligning more closely with English Wikipedia regardless of the prompt language. Researchers created the Mult…
Text-to-Speech (TTS) technology converts written text into spoken audio through stages including text normalization, phonetic transcription, prosody generation, and waveform synthesis. Machine learning, particularly deep…
AI Humanizer claims to have developed an algorithm that mimics human conversational nuances to make AI interactions more relatable, but the company has yet to release data proving its technology improves customer satisfa…
Voice-to-Md.dev released Speech-to-Markdown, a 100% local app for macOS and iOS that converts voice into structured markdown documents using whisper.cpp and a local LLM, with no cloud dependency. The app offers global di…
A developer argues that schema-aware query generation outperforms generic AI templates for production databases, as it integrates the database's specific structure to produce correct queries. The approach, exemplified by…
Reuben launched Vuci, a platform that makes spoken conversations from podcasts searchable, savable, and shareable. The tool aims to connect topics across audio content and allow deeper reading of interesting segments. Bu…
Turing Award winner and Postgres creator Mike Stonebraker revealed that large language models score 0% accuracy on real-world data warehouse queries, contradicting the 80-85% reported on popular benchmarks like Spider an…
Stilta, a Stockholm-based legal AI startup founded by former McKinsey and QuantumBlack engineers, raised $10.5 million in seed funding led by Andreessen Horowitz to deploy AI agents for patent litigation, focusing on evi…
A new AI method using prefix control tokens with BART fine-tuning boosts ad headline click-through rates by 5.82% and Rouge-L scores by 25.82%, giving advertisers customizable control over headline generation.
Researchers developed a new method for out-of-scope intent detection using MiniLM embeddings, treating it as a one-class classification task with multi-cluster boundary learning. The approach outperformed existing baseli…