arXiv:2406.02613v3 Announce Type: replace Abstract: Training LLMs relies on distributed implementations using multiple GPUs to compute gradients in parallel with sharded optimizers. However, synchronizing gradients in data parallel setups introduces communication overhead that grows with the number of workers, limiting…
arXiv:2510.11899v1 Announce Type: new Abstract: Robust reinforcement learning (Robust RL) seeks to handle epistemic uncertainty in environment dynamics, but existing approaches often rely on nested min–max optimization, which is computationally expensive and yields overly conservative policies. We propose textbf{Adaptive Rank…
arXiv:2504.08621v2 Announce Type: replace Abstract: The Finite Element Method (FEM) is widely used in engineering and scientific computing, but its pre-processing, solver configuration, and post-processing stages are often time-consuming and require specialized knowledge. This paper proposes an automated solution framework,…
arXiv:2510.11903v1 Announce Type: new Abstract: User event modeling plays a central role in many machine learning applications, with use cases spanning e-commerce, social media, finance, cybersecurity, and other domains. User events can be broadly categorized into personal events, which involve…
arXiv:2506.15065v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly being adopted as the cognitive core of embodied agents. However, inherited hallucinations, which stem from failures to ground user instructions in the observed physical environment, can lead to navigation…
arXiv:2510.11917v1 Announce Type: new Abstract: Dementia disorders such as Alzheimer’s disease (AD) and frontotemporal dementia (FTD) exhibit overlapping electrophysiological signatures in EEG that challenge accurate diagnosis. Existing EEG-based methods are limited by full-band frequency analysis that hinders precise differentiation of…
arXiv:2509.04154v3 Announce Type: replace Abstract: We introduce Adaptive Filter Attention (AFA), a novel attention mechanism that incorporates a learnable dynamics model directly into the computation of attention weights. Rather than comparing queries and keys directly, we model the input sequence…
arXiv:2510.11926v1 Announce Type: new Abstract: Indoor Wi-Fi positioning remains a challenging problem due to the high sensitivity of radio signals to environmental dynamics, channel propagation characteristics, and hardware heterogeneity. Conventional fingerprinting and model-based approaches typically require labor-intensive calibration and suffer…
arXiv:2510.09719v2 Announce Type: replace Abstract: Large language models (LLMs) often exhibit complementary strengths. Model routing harnesses these strengths by dynamically directing each query to the most suitable model, given a candidate model pool. However, routing performance relies on accurate model…
arXiv:2510.11933v1 Announce Type: new Abstract: In this work, we propose three efficient restart paradigms for model-free non-stationary reinforcement learning (RL). We identify two core issues with the restart design of Mao et al. (2022)’s RestartQ-UCB algorithm: (1) complete forgetting, where…
