About
Research & Development
Securing Sensitive Data: A New Defense Against Model Prediction Exploitation
TLDR: A new research paper introduces 'test-time privacy,' a threat where machine learning models confidently predict on unlearned sensitive data, enabling adversaries to cause...
Research & Development
Exploring Multi-Agent LLM Debates: The MALLM Framework for Systematic Analysis
TLDR: MALLM (Multi-Agent Large Language Models) is an open-source framework designed for the systematic analysis of Multi-Agent Debate (MAD) components. It offers over 144...
Research & Development
AI Agents Unveil Code’s Hidden Structures: Automating Visual Documentation for Developers
TLDR: A new research paper introduces VisDocSketcher, an AI-powered system that uses Large Language Model (LLM) agents to automatically generate high-level visual documentation (like...
Research & Development
Improving Text Accessibility: Vicomtech’s Iterative Approach to Plain Language and Easy Read
TLDR: Vicomtech developed an Automatic Post-Editing Cycles (APEC) method for adapting Spanish texts to Plain Language and Easy Read. This iterative approach uses Large...
Research & Development
Mimicking More Than Just Averages: New Algorithms for Risk-Sensitive Imitation Learning
TLDR: This research introduces Return Distribution Matching (RDM), a novel approach to imitation learning that trains agents to match an expert's entire return distribution,...
Research & Development
Advancing Open-Vocabulary Segmentation for Remote Sensing Images
TLDR: The paper introduces RSKT-Seg, a novel framework for Open-Vocabulary Remote Sensing Image Segmentation (OVRSIS). It addresses challenges like the lack of a unified...