DeepSeek may have found a new way to improve AI’s ability to remember

An AI model released by Chinese AI company DeepSeek uses new techniques that could significantly improve AI’s ability to “remember.” Released last week, the optical character recognition (OCR) model works by extracting text from an image and turning it into machine-readable words. This is the same technology that powers scanner apps, translation of text in […]

Evaluating the role of ChatGPT in rehabilitation medicine: a narrative review

Chat Generative Pretrained Transformer (ChatGPT) has emerged as a sophisticated artificial intelligence (AI) language model in healthcare. This narrative review examines ChatGPT’s current applications and limitations in rehabilitation medicine through analysing multiple studies. While demonstrating promising performance in structured tasks and basic medical guidance, significant challenges persist. These include inconsistent performance in complex clinical scenarios, […]

The health-promoting experiences of storytellers in group-based digital storytelling workshops: a meta-synthesis of qualitative studies

ObjectiveTo synthesize qualitative evidence, using the framework analysis method, on how participating in a digital storytelling workshop shapes the storytellers’ health attitudes, values, beliefs, or behaviors.MethodsWe conducted a meta-synthesis using the framework analysis method to generate analytic themes. We searched Medline, CINHAL, SocIndex, Embase, PsycINFO, SciELO, Academic Search Ultimate, Scopus, the Directory of Open Access […]

Uncovering the Potential Risks in Unlearning: Danger of English-only Unlearning in Multilingual LLMs

arXiv:2510.23949v1 Announce Type: cross Abstract: There have been a couple of studies showing that attempting to erase multilingual knowledge using only English data is insufficient for multilingual LLMs. However, their analyses remain highly performance-oriented. In this paper, we switch the point of view to evaluation, and address an additional blind spot which reveals itself when […]

A Neural Model for Contextual Biasing Score Learning and Filtering

arXiv:2510.23849v1 Announce Type: cross Abstract: Contextual biasing improves automatic speech recognition (ASR) by integrating external knowledge, such as user-specific phrases or entities, during decoding. In this work, we use an attention-based biasing decoder to produce scores for candidate phrases based on acoustic information extracted by an ASR encoder, which can be used to filter out […]

DynaStride: Dynamic Stride Windowing with MMCoT for Instructional Multi-Scene Captioning

arXiv:2510.23907v1 Announce Type: cross Abstract: Scene-level captioning in instructional videos can enhance learning by requiring an understanding of both visual cues and temporal structure. By aligning visual cues with textual guidance, this understanding supports procedural learning and multimodal reasoning, providing a richer context for skill acquisition. However, captions that fail to capture this structure may […]

Traffic flow forecasting, STL decomposition, Hybrid model, LSTM, ARIMA, XGBoost, Intelligent transportation systems

arXiv:2510.23668v1 Announce Type: cross Abstract: Accurate traffic flow forecasting is essential for intelligent transportation systems and urban traffic management. However, single model approaches often fail to capture the complex, nonlinear, and multi scale temporal patterns in traffic flow data. This study proposes a decomposition driven hybrid framework that integrates Seasonal Trend decomposition using Loess (STL) […]

Subscribe for Updates

Copyright 2025 dijee Intelligence Ltd.   dijee Intelligence Ltd. is a private limited company registered in England and Wales at Media House, Sopers Road, Cuffley, Hertfordshire, EN6 4RY, UK registeration number 16808844