About
Research & Development
iLearnRobot: Empowering Robots to Learn and Improve Through Everyday Conversations
TLDR: iLearnRobot is an innovative system that enables multi-modal robots to continuously improve their performance by learning from natural dialogues with non-expert users. It...
Research & Development
Advanced AI Framework Pinpoints Illicit Online Markets Across Digital Platforms
TLDR: A new AI framework utilizes a fine-tuned ModernBERT language model, combined with structural and metadata features, and a two-stage semi-supervised ensemble learning approach...
Research & Development
Bridging the Gap: How Discrete Tokens Power Multimodal Large Language Models
TLDR: This survey explores discrete tokenization, particularly Vector Quantization (VQ), as a crucial method for converting continuous data (like images, audio, video) into a...
Research & Development
Dynamic Context Compression for Faster, Smarter RAG
TLDR: ACC-RAG is a new framework that makes Retrieval-Augmented Generation (RAG) more efficient by dynamically adjusting context compression based on query complexity. It uses...
Research & Development
Unlocking Information in Telecom Flowcharts for Better Question Answering
TLDR: This research introduces a new method to improve Question-Answering (QA) from technical telecom documents, especially when answers are hidden in flowcharts. Traditional text-based...
Research & Development
The PARROT Dataset: A New Resource for Multilingual Radiology AI
TLDR: PARROT is the largest open-access, multilingual dataset of 2658 fictional radiology reports from 76 radiologists across 21 countries and 13 languages. It aims...