Natural Language Processing

A new arXiv preprint proposes an end-to-end deep learning framework that directly learns portfolio weights by combining Long Short-Term Memory networks, Graph Attention Networks, and financial news sentiment analysis. Th…

Researchers from the National University of Singapore, MIT CSAIL, A*STAR, and SMART have developed MEMO, a framework that trains a separate, small language model to internalize new knowledge from documents without modify…

A developer built a full-stack sentiment analysis web app as their first machine learning project, using a Random Forest model with Scikit-Learn and TF-IDF vectorization on the backend and React on the frontend. The app …

A developer building a financial analysis tool discovered a prompt injection vulnerability when an LLM unexpectedly revealed system configuration details instead of processing a simple data query. The engineer outlines a…

A French SEO agency operating from Siem Reap, Cambodia, has shipped over 1,300 semantic content clusters for 650+ brands at a pace of 50 to 100 pages per week using a three-layer automation pipeline. The stack combines a…

A developer with over a decade of AI experience has published a learning roadmap for complete beginners, warning that starting with generative AI tools like ChatGPT is the biggest mistake newcomers can make. The roadmap …

A developer built Warung MiMo, an AI-powered assistant for Indonesian street shops that uses natural language processing to understand how shop owners actually speak. The project, which was abandoned after its initial de…

Researchers have developed RICE-PO, a policy optimization framework that converts retrieval interactions into localized learning signals for training reasoning-based retrieval agents. The framework addresses the credit-a…

A new study published on arXiv describes "The Daily Dose," an LLM-driven system that automates clinical summarization and clinical-trial identification for radiation oncology. After one month of deployment, a survey of 5…

Researchers introduced SPEAR (Sandboxed Prompt Engineer with Active Roll-back), a code-augmented agentic optimizer that autonomously rewrites prompts using a Python sandbox for structural error analysis, outperforming ex…

A new survey from arXiv researchers has unified the study of Pretraining Data Exposure (PDE) in large language models, revealing growing risks to evaluation integrity and data privacy as training datasets expand. The pap…

Researchers have developed Evi-Steer, a new framework for BiomedCLIP that enables uncertainty-aware fine-tuning of biomedical vision-language models by updating only 0.11% of total parameters. The method uses evidential …

Researchers have developed LexGuard, an adversarial multi-agent framework that improves legal AI reliability by ensuring large language models respond only to legally relevant changes in case facts. The system formalizes…

Researchers have developed Self-Verified Distillation, a method allowing large language models to improve themselves using only unlabeled prompts without external feedback. The approach, tested on Qwen3 models across mat…

MiniMax released the M2 series of Mixture-of-Experts language models, featuring 229.9 billion total parameters with only 9.8 billion activated per token, designed for agentic deployment. The models use agent-driven data …

Large language models (LLMs) show reduced accuracy on math problems when simple details like names or numbers are changed, and a new study finds that using code execution methods does not improve this robustness. Researc…

Researchers have developed DuoGesture, a neuro-inspired dual-stream system that separately generates semantic and beat gestures for co-speech animation. The model uses a stochastic gate to coordinate when semantic gestur…

A new study finds that vector representations exported from large language model summarization systems can leak sensitive information, even when source documents remain access-restricted. Researchers auditing clinical di…

Researchers have introduced FEPoID, a training-free method for automatically selecting intermediate layers in large language models to improve hallucination detection. The approach outperforms existing criteria and detec…

Researchers have developed Token-to-Mask (T2M) remasking, a training-free replacement for Token-to-Token (T2T) editing in discrete masked diffusion language models like LLaDA. The method resets suspected erroneous tokens…