LeLaR: AI-Based Satellite Attitude Control In-Orbit Demo
Discover LeLaR, the first AI-based satellite attitude controller tested in orbit, improving satellite orientation with deep reinforcement learning.
Machine Unlearning in Quantum Machine Learning: Key Insights
Explore empirical findings on machine unlearning in hybrid quantum-classical models, highlighting new techniques and performance factors.
PyFi: Enhancing Financial Image Understanding for VLMs
Discover PyFi, a pyramid-structured framework boosting vision language models' financial image understanding with adversarial agents.
Adaptive Replay Buffer Boosts Offline-to-Online RL Performance
Discover how the Adaptive Replay Buffer improves Offline-to-Online Reinforcement Learning by dynamically balancing offline and online data for optimal resu...
Optimizing LLM Reasoning with RePro Method
Discover how the RePro method enhances large language model reasoning by optimizing chain-of-thought processes for better AI performance.