Interactive Groupwise Comparison for Reinforcement Learning from Human Feedback
The standard RLHF uses pairwise comparisons and therefore requires a large number of comparisons leading to a high workload. The comparison pairs are suggested by the system and cannot be chosen by the user. Our RLHF approach provides more agency to the user and demands less work: we leverage the user's visual abilities to effectively explore the ...
Jan Kompatscher +4 more
wiley +1 more source
Enhancing multi-component alloy composition prediction based on generative adversarial networks and proximal policy optimization. [PDF]
Zhang SL, Bai SB, Shang WJ, Liu Q, Yu P.
europepmc +1 more source
Robo‐Saber: Generating and Simulating Virtual Reality Players
Abstract We present the first motion generation system for playtesting virtual reality (VR) games. Our player model generates VR headset and handheld controller movements from in‐game object arrangements, guided by style reference gameplay examples. We train on the large BOXRR‐23 dataset and apply our framework on the popular VR game Beat Saber.
N. H. Kim +5 more
wiley +1 more source
An intelligent and adaptive security framework for UAV swarms: a cross-layer approach integrating highly reliable EPUF, DRL-based key management, and distributed ledger technology. [PDF]
Kim H, Kim S.
europepmc +1 more source
FaceMamba: Geometry‐Aware Mamba for Efficient Speech‐Driven 3D Facial Animation
Abstract Speech‐driven 3D facial animation plays a pivotal role in immersive digital human applications. Recent works have explored Mamba‐based sequence modeling as an efficient alternative to Transformer, but they often suffer from limited cross‐modal alignment and insufficient control over fine‐grained facial deformations.
Yifan Ge +5 more
wiley +1 more source
Deep Reinforcement Learning for Autonomous Underwater Navigation: A Comparative Study with DWA and Digital Twin Validation. [PDF]
Mari Z, Nawaf MM, Drap P.
europepmc +1 more source
Helicopter drops in an open economy when markets are incomplete
Abstract We characterize the spillover effects of helicopter drops and optimal monetary policy in a tractable two‐country overlapping generations model with incomplete markets. As helicopter drops can affect the distribution of income across countries, they create room for redistribution policies which are particularly relevant when agents are ...
Sara Eugeni
wiley +1 more source
Impact of Neuron Models on Spiking Neural Network Performance: A Complexity-based Classification Approach. [PDF]
Rudnicka Z, Szczepanski J, Pregowska A.
europepmc +1 more source
Paving the way for incumbents' digital transformation. A review and research agenda
Abstract Digital transformation is reshaping the competitive landscape by forcing incumbent firms to rethink their strategies, organizational structures, and business models. While a substantial body of literature has explored digital transformation in specific sectors, focusing on various factors and organizational mechanisms, there remains a lack of ...
Anna Bastone +3 more
wiley +1 more source
Structure-aware state space modeling with multi-scale feature fusion for railway scene segmentation. [PDF]
Fu H +5 more
europepmc +1 more source

