arXiv:2509.26301v2 Announce Type: replace Abstract: Large-scale foundation models for EEG signals offer a promising path to generalizable brain-computer interface (BCI) applications, but they often suffer from misalignment between pretraining objectives and downstream tasks, as well as significant cross-subject distribution shifts.…
arXiv:2510.01271v1 Announce Type: new Abstract: Understanding the internal dynamics of Recurrent Neural Networks (RNNs) is crucial for advancing their interpretability and improving their design. This study introduces an innovative information-theoretic method to identify and analyze information-transfer nodes within RNNs, which…
arXiv:2502.03323v2 Announce Type: replace-cross Abstract: Distinguishing in- and out-of-distribution (OOD) inputs is crucial for reliable deployment of classification systems. However, OOD data is typically unavailable or difficult to collect, posing a significant challenge for accurate OOD detection. In this work,…
arXiv:2510.01278v1 Announce Type: new Abstract: Positive-Unlabeled (PU) learning aims to train a binary classifier (positive vs. negative) where only limited positive data and abundant unlabeled data are available. While widely applicable, state-of-the-art PU learning methods substantially underperform their supervised counterparts…
arXiv:2508.03674v2 Announce Type: replace-cross Abstract: We develop Morphlux, a server-scale programmable photonic fabric to interconnect accelerators within servers. We show that augmenting state-of-the-art torus-based ML data-centers with Morphlux can improve the bandwidth of tenant compute allocations by up to 66%,…
arXiv:2510.01288v1 Announce Type: new Abstract: We draw inspiration from microsaccades, tiny involuntary eye movements that reveal hidden dynamics of human perception, to propose an analogous probing method for large language models (LLMs). Just as microsaccades expose subtle but informative shifts…
arXiv:2510.01850v1 Announce Type: cross Abstract: Capturing comprehensive statistics of nonperiodic asynchronous impulsive noise is a critical issue in enhancing impulse noise processing for narrowband powerline communication (NB-PLC) transceivers. However, existing mathematical noise generative models capture only some of the characteristics…
arXiv:2510.01290v1 Announce Type: new Abstract: The long-output context generation of large reasoning models enables extended chain of thought (CoT) but also drives rapid growth of the key-value (KV) cache, quickly overwhelming GPU memory. To address this challenge, we propose ThinKV,…
arXiv:2510.02060v1 Announce Type: cross Abstract: In tabular anomaly detection (AD), textual semantics often carry critical signals, as the definition of an anomaly is closely tied to domain-specific context. However, existing benchmarks provide only raw data points without semantic context, overlooking…
arXiv:2510.01292v1 Announce Type: new Abstract: Accurate vehicle delay estimation is essential for evaluating the performance of signalized intersections and informing traffic management strategies. Delay reflects congestion levels and affects travel time reliability, fuel use, and emissions. Machine learning (ML) offers…
