Quality follows upgrading
All Articles
arXiv:2603.18396v1 Announce Type: new Abstract: Bus holding control is challenging due to stochastic traffic and passenger demand. While deep reinforcement learning (DRL) shows promise, standard …
arXiv:2603.18397v1 Announce Type: new Abstract: Mass spectrometry (MS) stands as a cornerstone analytical technique for molecular identification, yet de novo structure elucidation from spectra remains …
arXiv:2603.18417v1 Announce Type: new Abstract: Sparse attention mechanisms promise to break the quadratic bottleneck of long-context transformers, yet production adoption remains limited by a critical …
arXiv:2603.18431v1 Announce Type: new Abstract: Quantum multi-armed bandits (MAB) and stochastic linear bandits (SLB) have recently attracted significant attention, as their quantum counterparts can achieve …
arXiv:2603.18432v1 Announce Type: new Abstract: Separating multiple effects in time series is fundamental yet challenging for time-series forecasting (TSF). However, existing TSF models cannot effectively …
arXiv:2603.18444v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has emerged as an effective post-training paradigm for improving the reasoning capabilities of large …
arXiv:2603.18448v1 Announce Type: new Abstract: Shot language understanding (SLU) is crucial for cinematic analysis but remains challenging due to its diverse cinematographic dimensions and subjective …
arXiv:2603.18464v1 Announce Type: new Abstract: Reinforcement learning (RL) for large-scale Vision-Language-Action (VLA) models faces significant challenges in computational efficiency and data acquisition. We propose AcceRL, …
arXiv:2603.18492v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) language models increase parameter capacity without proportional per-token compute, but the deployment still requires storing all experts, making …
arXiv:2603.18533v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) have shown exceptional reasoning capabilities, but they also suffer from the issue of overthinking, often generating …
arXiv:2603.18534v1 Announce Type: new Abstract: Synthetic data augmentation has emerged as a promising solution when pre-training is constrained by data rather than compute. We study …
arXiv:2603.18538v1 Announce Type: new Abstract: Decentralized Federated Learning (DFL) remains highly vulnerable to adaptive backdoor attacks designed to bypass traditional passive defense metrics. To address …