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 new arXiv paper (2609.13481v1) presents a Hybrid Hierarchical CNN-LSTM Summarizer that frames biomedical and clinical summarization as extractive sentence selection rather than generation, eliminating hallucination ris…
Researchers released CVSS-X, a synthetic speech-to-speech translation corpus that translates English into 28 target languages across 12 language families, comprising roughly 240,000 parallel speech pairs per language and…
A maxillofacial cone beam CT report generation system scored 0.4122 against a composite objective that weights 80% on large language model factual entailment and 20% on lexical overlap, versus 0.2909 for a report selecte…
A new arXiv paper, RFCLLM, evaluates how well large language models reason about network protocol state machines, testing 16 protocols across 4 tasks and 1482 task queries. The study compares each LLM's implicit finite-s…
Researchers introduced TestHallVQA, a multi-image visual question answering benchmark built from scientific exams that combines document-level scale with human-examination difficulty, according to the arXiv paper 2609.13…
Token merging speeds up multilingual speech recognition in the Whisper model family with almost no loss in transcription accuracy across sixteen languages and three model sizes, according to an arXiv paper (arXiv:2609.13…
A training-free, CPU-only lexical prompt-compression pipeline reduced prompt tokens by a mean of 40.3% (sigma = 9.2) while holding BERTScore-F1 at 0.876 against original-prompt output, according to an arXiv paper (2609.1…
A first-move retrieval module called Question's Gambit raised downstream agent answer accuracy from 83.1% to 90.5% with gpt-5.5 over the Pi-Serini agentic baseline on the BrowseComp-Plus benchmark, according to the arXiv…
Researchers introduced ClinAgent, a conversational agentic Retrieval-Augmented Generation (RAG) system built on a Large Language Model agent following the ReAct paradigm, which lets clinicians and researchers query clini…
Researchers developed GAVEL, an LLM judge protocol that compares clinical timelines against their source case reports, returning a discrepancy type, verdict, and report passage for each difference. Evaluating 2,738 findi…
Researchers introduced OrchSLM, a routing framework that unifies existing non-interactive small language model (SLM) orchestration methods and exposes their design choices as controllable parameters, according to the arX…
A new arXiv survey (arXiv:2609.13255v1) reviews multimodal facial state analysis, covering core tasks, representative methods, and datasets for facial expression recognition, action unit (AU) detection, and face-based so…
Researchers introduced Counterfactual Search for Grounding Regions (CSGR), a scalable pipeline that labels answer-critical image regions in visual question answering (VQA) data by perturbing candidate regions and measuri…
Researchers introduced MACE, a Multi-Agent Candidate Event acquisition method that uses evidence-specialized LLM agents to refine event structure before linking, according to a new arXiv paper (arXiv:2609.13670v1). MACE …
Tencent researchers introduced T-Mem, a long-term memory system for LLM agents that pre-saves contextual triggers at memory write time rather than relying on semantic similarity at retrieval. The approach sets new state-…
An interactive site, One Million Tokens, visualizes what a 1 million-token context window represents, converting it to roughly 750,000 words, 3,000 printed pages, 83 hours of conversation, or 75,000 lines of code. The si…
Researchers introduced ReMoMask-2, a latent retrieval-augmented masked motion generation model for text-to-motion (T2M) generation, which maps natural language to human joint movements for gaming, VR, and robotics. The w…
Google's Gemini 3.8 Live and Gemini 3.8 Live Extended Thinking models are now available on Vercel's AI Gateway, supporting real-time spoken interactions for voice assistants and audio-based applications. The google/gemin…
Google released two live voice models on September 15, 2026: Gemini 3.8 Live, which answers without a reasoning pause and is pitched for scale and cost efficiency, and Gemini 3.8 Live Extended Thinking, which reasons and…
Manticore Search added a `chunk_strategy` option to model-backed vector columns in `CREATE TABLE`, letting the database split long documents into chunks, embed each chunk, and search all of them without an external inges…