Research Publications
Explore our latest research papers and publications in artificial intelligence, focusing on knowledge graphs, private AI deployment, and AI safety evaluation.
One Goal, Many Challenges: Robust Preference Optimization Amid Content-Aware and Multi-Source Noise
AktusAI Research Team
Large Language Models (LLMs) have made significant strides in generating human-like responses, largely due to preference alignment techniques. However, these methods often assume unbiased human feedback, which is rarely the case in real-world scenarios.
Cooperative Multi-Agent Constrained Stochastic Linear Bandits
AktusAI Research Team
We explore a collaborative multi-agent stochastic linear bandit setting involving a network of N agents that communicate locally to minimize their collective regret while keeping their expected cost under a specified threshold
Generalizable Spacecraft Trajectory Generation via Multimodal Learning with Transformers
AktusAI Research Team
Effective trajectory generation is essential for reliable on-board spacecraft autonomy. Among other approaches, learning-based warm-starting represents an appealing paradigm for solving the trajectory generation problem, effectively combining the benefits of optimization- and data-driven methods.
Ready to Transform Your Enterprise AI?
Join the growing number of enterprises leveraging AktusAI to build, deploy, and manage their AI solutions securely and efficiently.
Get Started Today