About
Research & Development
New Framework Addresses Data Forgetting in Federated Learning with Information Theory
TLDR: Researchers introduce a novel Federated Unlearning (FU) framework that tackles data erasure as a parameter estimation problem. By using second-order Hessian information, the...
Research & Development
HIPLAN: Enhancing LLM Agents with Adaptive Hierarchical Planning for Complex Tasks
TLDR: HIPLAN is a hierarchical planning framework that improves LLM-based agents' ability to handle complex, long-horizon tasks. It provides adaptive global-local guidance by decomposing...
Research & Development
Zero-Shot Navigation: How ZeST Helps Robots Map Unknown Environments
TLDR: ZeST is a novel robotics navigation system that uses Large Language Models (LLMs) to predict terrain traversability in real-time for unknown environments, eliminating...
Research & Development
Unlocking Image Detail: A New Approach to Photo Restoration from Raw Sensor Data
TLDR: RDDM is a novel diffusion model that directly restores high-quality images from unprocessed camera RAW data, bypassing traditional sRGB processing. It addresses challenges...
Research & Development
Real-Time Planning for Autonomous Robots: Model Checking Enhances Obstacle Avoidance
TLDR: Researchers developed a novel real-time model checking algorithm for autonomous robots that enables multi-step planning and obstacle avoidance without pre-computed data, even on...
Research & Development
Expanding Speaker Datasets with Synthetic Voices for Enhanced AI Training
TLDR: INSIDE (Interpolating Speaker Identities in Embedding Space) is a novel data expansion method that synthesizes new speaker identities by blending existing speaker embeddings...