About
Research & Development
RICL: Enhancing Robot Learning with In-Context Adaptability
TLDR: The research paper introduces RICL (Retraining for In-Context Learning), a method to inject in-context learning (ICL) abilities into pre-trained Vision-Language-Action (VLA) models for...
Research & Development
Safeguarding AI: A New Approach to Preserving LLM Alignment During Fine-Tuning
TLDR: AlignGuard-LoRA is a novel framework that addresses 'alignment drift' in large language models (LLMs) during fine-tuning. It prevents LLMs from losing their safety...
Research & Development
CRINN: AI Framework Accelerates Approximate Nearest Neighbor Search Algorithms
TLDR: CRINN is a novel AI framework that uses contrastive reinforcement learning to automatically optimize Approximate Nearest Neighbor Search (ANNS) algorithms. By learning from...
Research & Development
Navigating User Experience in Conversational Recommender Systems: A Systematic Review
TLDR: A systematic review of 23 studies on Conversational Recommender Systems (CRSs) reveals that user experience (UX) evaluation is fragmented, often focusing on satisfaction...
Research & Development
Unmasking Malicious Clients in Federated Learning with Watermarks
TLDR: A new defense called Coward protects federated learning from backdoor attacks. Unlike previous methods, Coward proactively injects a "watermark" into the global model....
Research & Development
AuroBind: A Scalable AI Platform for Discovering Potent Drug Candidates
TLDR: AuroBind is a novel AI-driven virtual screening framework that significantly accelerates drug discovery by accurately predicting protein-ligand structures and binding fitness. It can...