About
Research & Development
Unmasking Multimodal AI Vulnerabilities with Comic Narratives
TLDR: A new method called Sequential Comic Jailbreak (SCJ) uses comic-style visual stories to bypass safety features in multimodal AI models (MLLMs). It breaks...
Research & Development
FarsiMCQGen: Advancing Persian Multiple-Choice Question Generation
TLDR: FarsiMCQGen is a new framework for automatically generating high-quality multiple-choice questions (MCQs) in Persian. Developed by researchers at Amirkabir University of Technology, it...
Research & Development
Structure-R1: Enhancing LLM Reasoning with Dynamic Knowledge Structures
TLDR: Structure-R1 is a novel framework that significantly improves Large Language Models' (LLMs) reasoning capabilities by dynamically transforming retrieved information into optimized, structured representations....
Research & Development
A New Approach to Visual Generation: Latent Diffusion Models Without VAEs
TLDR: A new research paper introduces SVG, a latent diffusion model that eliminates the need for Variational Autoencoders (VAEs) by leveraging self-supervised DINO features...
Research & Development
Beyond the Surface: How New Metrics Are Redefining Readability Assessment
TLDR: A new research paper, "Readability Reconsidered: A Cross-Dataset Analysis of Reference-Free Metrics," investigates human perceptions of readability, finding that information content and topic...
Research & Development
GaussGym: High-Speed Photorealistic Simulation for Vision-Based Robot Learning
TLDR: GaussGym is a new open-source framework that enables photorealistic robot simulation at over 100,000 steps per second using 3D Gaussian Splatting. It allows...