PaTaRM: Bridging Pairwise and Pointwise Signals via Preference-Aware Task-Adaptive Reward Modeling
arXiv:2510.24235v1 Announce Type: cross Abstract: Reward models (RMs) are central to reinforcement learning from human feedback (RLHF), providing the critical…
Closing Gaps: An Imputation Analysis of ICU Vital Signs
arXiv:2510.24217v1 Announce Type: cross Abstract: As more Intensive Care Unit (ICU) data becomes available, the interest in developing clinical prediction…
Eigen-Value: Efficient Domain-Robust Data Valuation via Eigenvalue-Based Approach
arXiv:2510.23409v2 Announce Type: replace-cross Abstract: Data valuation has become central in the era of data-centric AI. It drives efficient training…
A Multi-Component AI Framework for Computational Psychology: From Robust Predictive Modeling to Deployed Generative Dialogue
arXiv:2510.21720v1 Announce Type: new Abstract: The confluence of Artificial Intelligence and Computational Psychology presents an opportunity to model, understand, and…
WhaleVAD-BPN: Improving Baleen Whale Call Detection with Boundary Proposal Networks and Post-processing Optimisation
arXiv:2510.21280v2 Announce Type: replace-cross Abstract: While recent sound event detection (SED) systems can identify baleen whale calls in marine audio,…
Efficient and Encrypted Inference using Binarized Neural Networks within In-Memory Computing Architectures
arXiv:2510.23034v1 Announce Type: cross Abstract: Binarized Neural Networks (BNNs) are a class of deep neural networks designed to utilize minimal…
Nested AutoRegressive Models
arXiv:2510.23028v1 Announce Type: cross Abstract: AutoRegressive (AR) models have demonstrated competitive performance in image generation, achieving results comparable to those…
Towards General Modality Translation with Contrastive and Predictive Latent Diffusion Bridge
arXiv:2510.20819v2 Announce Type: replace-cross Abstract: Recent advances in generative modeling have positioned diffusion models as state-of-the-art tools for sampling from…
Sketch2BIM: A Multi-Agent Human-AI Collaborative Pipeline to Convert Hand-Drawn Floor Plans to 3D BIM
arXiv:2510.20838v1 Announce Type: new Abstract: This study introduces a human-in-the-loop pipeline that converts unscaled, hand-drawn floor plan sketches into semantically…
Real-Time Gait Adaptation for Quadrupeds using Model Predictive Control and Reinforcement Learning
arXiv:2510.20706v2 Announce Type: replace-cross Abstract: Model-free reinforcement learning (RL) has enabled adaptable and agile quadruped locomotion; however, policies often converge…