About
Research & Development
Navigating Crypto’s Swings: New Methods for Predicting Volatility Ranges
TLDR: A research paper introduces probabilistic forecasting methods (Quantile Estimation through Residual Simulation, Quantile Linear Regression, and Quantile Regression Forest) to predict cryptocurrency volatility,...
Research & Development
Evaluating LLM Behavior in Dynamic Economic Tasks
TLDR: A study introduces a process-oriented framework to assess how Large Language Models (LLMs) simulate human decision-making, focusing on variability and adaptability rather than...
Research & Development
Enhancing Stealthy Backdoor Attacks in Text AI Through Strategic Data Selection
TLDR: This research paper introduces three novel sample selection strategies (Minimum, Above50, and Below50) to significantly improve the effectiveness of clean-label backdoor attacks in...
Research & Development
Adaptive Superpixel Coding: Enhancing Vision Transformers with Dynamic Image Grouping
TLDR: Adaptive Superpixel Coding (ASC) is a self-supervised deep learning model that improves Vision Transformers by replacing their rigid, fixed-size image patches with adaptive...
Research & Development
Automated Program Repair: Bridging the Gap Between Benchmarks and Real-World Code
TLDR: A research paper from Oracle Labs explores their approach to automated program repair, combining LLMs with techniques like bug localization, context generation, and...
Research & Development
Unlocking LLM Potential: A Seed-Free Approach to Instruction Tuning
TLDR: CYCLE-INSTRUCT is a novel framework for instruction tuning large language models (LLMs) that operates entirely without human-annotated 'seed' data or external teacher models....