arXiv:2510.13865v3 Announce Type: replace Abstract: We introduce the Deep Edge Filter, a novel approach that applies high-pass filtering to deep neural network features to improve model generalizability. Our method is motivated by our hypothesis that neural networks encode task-relevant semantic…
arXiv:2510.17991v1 Announce Type: new Abstract: Flow Matching (FM) underpins many state-of-the-art generative models, yet recent results indicate that Transition Matching (TM) can achieve higher quality with fewer sampling steps. This work answers the question of when and why TM outperforms…
arXiv:2402.07127v3 Announce Type: replace-cross Abstract: Robot learning of manipulation skills is hindered by the scarcity of diverse, unbiased datasets. While curated datasets can help, challenges remain in generalizability and real-world transfer. Meanwhile, large-scale “in-the-wild” video datasets have driven progress in…
arXiv:2510.18004v1 Announce Type: new Abstract: Deep subspace clustering models are vital for applications such as snowmelt detection, sea ice tracking, crop health monitoring, infectious disease modeling, network load prediction, and land-use planning, where multivariate spatiotemporal data exhibit complex temporal dependencies…
arXiv:2504.03772v2 Announce Type: replace-cross Abstract: Respiratory diseases account for a significant portion of global mortality. Affordable and early detection is an effective way of addressing these ailments. To this end, a low-cost commercial off-the-shelf (COTS), IEEE 802.15.4z standard compliant impulse-radio…
arXiv:2510.18037v1 Announce Type: new Abstract: Neural activity forecasting is central to understanding neural systems and enabling closed-loop control. While deep learning has recently advanced the state-of-the-art in the time series forecasting literature, its application to neural activity forecasting remains limited.…
arXiv:2506.06387v2 Announce Type: replace-cross Abstract: The increasing deployment of large antenna arrays at base stations has significantly improved the spatial resolution and localization accuracy of radio-localization methods. However, traditional signal processing techniques struggle in complex radio environments, particularly in scenarios…
arXiv:2510.18041v1 Announce Type: new Abstract: Forecasting unobservable physical quantities from sparse, cross-domain sensor data is a central unsolved problem in scientific machine learning. Existing neural operators and large-scale forecasters rely on dense, co-located input-output fields and short temporal contexts, assumptions…
arXiv:2510.18052v1 Announce Type: new Abstract: Causal representation learning in the anti-causal setting (labels cause features rather than the reverse) presents unique challenges requiring specialized approaches. We propose Anti-Causal Invariant Abstractions (ACIA), a novel measure-theoretic framework for anti-causal representation learning. ACIA…
arXiv:2510.17843v1 Announce Type: new Abstract: Despite remarkable advances in Large Language Model capabilities, tool retrieval for agent-based systems remains fundamentally limited by reliance on semantic similarity, which fails to capture functional viability. Current methods often retrieve textually relevant but functionally…
