IEEE

P-BERT: Toward Long Sequence Modeling by Enabling Language Representation With Prefix Sequence Compression, Soft Position Embedding, and Data Augmentation for Patent Relevance ...

Abstract: Recent works have increasingly adopted pre-trained language models, such as BERT, to model technical semantics for patent relevance assessment. However, existing truncation and divide-merge ...
Nature

AI models were given four weeks of therapy: the results worried researchers

Chatbots put through psychotherapy report trauma and abuse. Authors say models are doing more than role play, but researchers ...

AI’s Memorization Crisis

O n Tuesday, researchers at Stanford and Yale revealed something that AI companies would prefer to keep hidden. Four popular ...
IEEE

DeCoAgent: Large Language Model Empowered Decentralized Autonomous Collaboration Agents Based on Smart Contracts

Abstract: Large Language Models (LLMs) empowered agents are effective across various tasks and demonstrate outstanding performance, which can be further enhanced through collaboration with multiple ...

Meta’s Vision-Language Shift VL-JEPA Beats Bulky LLMs

VL-JEPA predicts meaning in embeddings, not words, combining visual inputs with eight Llama 3.2 layers to give faster answers ...