Natural Language Processing

On April 16, 2026, NAVI-Orbital became the first system to demonstrate a zero-shot vision-language model performing autonomous multi-modal inference entirely onboard a Low Earth Orbit spacecraft. The system uses Gemma 3 …

Researchers introduced RTSGameBench, a benchmark built on the real-time strategy game Beyond All Reason, to evaluate strategic reasoning in Vision-Language Models. The benchmark includes diverse matchups, mini-games for …

Researchers propose a fully local AI cascade for de-identifying educational dialogue that achieves 0.958 macro F1 on math tutoring transcripts, outperforming a commercial API (0.706) and LLM-only baselines (0.767), while…

Researchers introduced SproutRAG, a hierarchical retrieval-augmented generation framework that uses learned inter-sentence attention to organize sentence-level chunks into a binary tree for multi-granularity retrieval wi…

Researchers propose activation steering as an alternative to few-shot prompting for generating synthetic data in low-resource languages. The method improves data diversity and downstream model performance by steering lan…

A new study from arXiv reveals that large language models use partially shared parameters for mathematical reasoning across languages, with the strongest overlap in intermediate layers. English yields the largest set of …

The Montreal Forced Aligner (MFA) 3.0 achieves state-of-the-art speech-to-text alignment with mean boundary errors below 15 ms across English, Japanese, and Korean. Released in 2016, MFA has become the most widely used f…

Researchers at an undisclosed institution have found that large language models (LLMs) poorly preserve diagnostic uncertainty in clinical text, altering phrases like "possible pneumonia" more than half the time, which co…

Researchers introduced MCompassRAG, a metadata-guided retrieval framework that uses topic-level signals to improve paragraph-level retrieval in RAG systems. The method achieves 8.24% higher information efficiency with ov…

Researchers have developed a speech-driven end-to-end model for discriminating among Chinese dialects, combining MFCC features with word-level embeddings via a CNN. The approach outperforms state-of-the-art methods on tw…

Researchers developed a Chinese dialects discrimination framework using transfer learning and data augmentation to address low-resource challenges. The model outperformed state-of-the-art methods on two benchmark corpora…

Researchers introduced PragReST, a self-supervised framework that uses counterfactual reasoning to improve large language models' pragmatic language understanding. Across four benchmarks, PragReST boosted accuracy by up …

Researchers introduced Consensus Frame GRPO (CF-GRPO), a process-level reward framework for video multimodal large language models that uses consensus frame alignment to improve evidence-aware reasoning without temporal …

Dolfyn, an AI-powered call answering service for contractors, claims to recover an average of $3,400 in the first month by capturing missed calls. The service handles calls, captures leads, and automates follow-ups, inte…

A developer building a Persian-language tutor using small Qwen-based agents shares five dataset design lessons learned from production failures, including avoiding tool-calling data where decoding can enforce structure, …

AEOLyft, an AI search optimization vendor, published a framework for AI Search Optimization (AEO) via European Business Review, positioning it as distinct from traditional SEO by focusing on knowledge graph engineering, …

A developer built Lexicon, an AI-powered Python CLI dictionary that provides instant word definitions, examples, synonyms, and AI explanations directly from the terminal. The tool aims to eliminate context switching by o…

A developer built NEXUS, a production-grade review intelligence engine that brings Amazon-style AI-generated review summaries to any dataset. The system uses a custom deep bidirectional LSTM baseline trained on Sentiment…

A developer compares prompt engineering to writing a clear how-to, noting that models need explicit context—like a knife for a sandwich—to succeed. The developer describes a three-phase journey from one-liner prompts to …

A developer automated content workflows by building a custom Python script that integrates natural language processing and machine learning to reduce manual intervention. The script, part of the CLAUDE documentation upda…