BID-LoRA: Efficient Framework for Continual Learning & Unlearning
Discover BID-LoRA, a parameter-efficient framework enabling precise continual learning and unlearning to enhance AI adaptability and data privacy.
PromptEcho: Annotation-Free Rewards for Text-to-Image RL
Discover PromptEcho, an annotation-free reward method using vision-language models to enhance text-to-image reinforcement learning efficiently and effectiv...
Chain-of-Thought Prompts for Knowledge Graph Prediction
Discover how chain-of-thought prompts improve entity, relation, and literal prediction on knowledge graphs with RALP and large language models.
TimeSAF: LLM-Guided Fusion for Accurate Time Series Forecasting
Discover TimeSAF, an innovative LLM-guided asynchronous fusion framework that improves time series forecasting accuracy and generalization.
Multi-Task Reinforcement Learning for Autonomous Reef Monitoring
Discover how multi-task reinforcement learning enhances autonomous reef monitoring with adaptable, robust control policies for diverse underwater tasks.