About
Research & Development
Advancing 3D Scene Understanding with Feed-forward Reconstruction Models
TLDR: A comprehensive review of feed-forward 3D reconstruction models, highlighting their departure from traditional iterative methods towards unified deep networks for direct camera pose...
Research & Development
Balancing Speed, Loss, and Performance in LLM Training: An Optimizer Comparison
TLDR: A study compared AdamW, Lion, and Sophia optimizers for pre-training 2.7 billion parameter LLMs on a limited budget. Lion was fastest in training,...
Research & Development
Unlocking Emotions Across Languages: A New Framework for Multi-Emotion Detection in Short Texts
TLDR: This research introduces PromotionGo, a feature-centric framework for detecting multiple emotions in short texts across 28 languages. It evaluates various text representation methods...
Research & Development
Smart Search for Medical Images: How RadiomicsRetrieval Improves Diagnosis
TLDR: RadiomicsRetrieval is a new 3D medical image retrieval framework that combines traditional radiomics features with deep learning to allow flexible and precise searching...
Research & Development
Streamlining Proto-Persona Creation with Generative AI: A Case Study on Efficiency and User Acceptance
TLDR: This research explores using prompt engineering with Generative AI (GenAI) to create proto-personas, essential for early product discovery. A case study with 19...
Research & Development
WERSA: A New Attention Mechanism for Efficient Long Sequence Processing
TLDR: WERSA is a novel attention mechanism that processes very long sequences in linear time (O(n)) by combining wavelet transforms and random feature approximations....