arXiv:2607.02967v1 Announce Type: cross Abstract: Large language models remain limited as continual learning systems, motivating renewed interest in Sparse Distributed Memory (SDM) as an explicit online…
arXiv:2607.02608v1 Announce Type: cross Abstract: Lightweight neuromorphic computing offers a promising route to efficient AI, with particular benefits for resource-constrained edge deployments. However, its scalable deployment…
arXiv:2607.05205v1 Announce Type: cross Abstract: Fast and reliable motion detection is essential for machine vision and autonomous systems operating in dynamic environments. This work integrates emerging…
arXiv:2607.04562v1 Announce Type: cross Abstract: Large language models (LLMs) generate fluent outputs that can be wrong. Unlike humans, who often exhibit cues when providing false information,…
arXiv:2606.04468v2 Announce Type: replace-cross Abstract: Offline multi-objective optimization (Offline MOO) seeks Pareto-optimal designs from static datasets without additional environment interactions. Existing generative methods typically guide sampling…
arXiv:2507.23033v2 Announce Type: replace-cross Abstract: Spiking Neural Networks (SNNs) provide an energy-efficient computing paradigm for neural rendering, but existing spike-based Neural Radiance Field (NeRF) models usually…
arXiv:2607.02753v1 Announce Type: new Abstract: Neuromorphic controllers for size, weight, and power-constrained systems require neural architectures that are both energy-efficient and interpretable at the level of…
arXiv:2607.02829v1 Announce Type: new Abstract: Existing ViT-based weather forecasting models apply uniform computation across all spatial tokens, even though nearby atmospheric grid points often contain similar…
arXiv:2607.05001v1 Announce Type: cross Abstract: Cyber Threat Intelligence (CTI) reports are predominantly unstructured, heterogeneous, and noisy, which limits their direct usability for automated analysis and reasoning.…
arXiv:2607.02805v1 Announce Type: new Abstract: High-throughput long-context generation is one of the central challenges for large language models. Generation is typically memory-bandwidth-bound rather than compute-bound: each…
arXiv:2607.02800v1 Announce Type: new Abstract: Induction heads are attention circuits believed to underlie in-context learning in transformers, yet a precise characterization of the estimators they implement…
arXiv:2607.02781v1 Announce Type: new Abstract: Inference-time alignment steers a frozen language model during decoding using auxiliary reward signals, avoiding the cost of repeated weight updates. However,…
arXiv:2404.06294v2 Announce Type: replace-cross Abstract: Super-Resolution (SR) is a time-hallowed image processing problem that aims to improve the quality of a Low-Resolution (LR) sample up to…
arXiv:2607.02755v1 Announce Type: new Abstract: Training AIs to be risk-averse in resources could offer a failsafe in the event that AIs turn out misaligned. Misaligned but…
arXiv:2604.16084v2 Announce Type: replace Abstract: Traffic forecasting is a challenging spatio-temporal modeling task and a critical component of urban transportation management. Current studies mainly focus on…
arXiv:2607.02722v1 Announce Type: new Abstract: Predicting thermal volatility in high-performance EV powertrains is difficult as internal temperatures are rarely observable outside the lab, and models calibrated…
arXiv:2602.07832v3 Announce Type: replace Abstract: Process rewards have been widely used in deep reinforcement learning to improve training efficiency, reduce variance, and prevent reward hacking. In…
arXiv:2607.02632v1 Announce Type: new Abstract: Time-series forecasting supports decisions in finance, en-ergy, transportation, public health, and industrial monitoring. Recent foundation models improve transfer across forecast-ing tasks,…
arXiv:2607.02633v1 Announce Type: new Abstract: We present GRAFT, a per-word pronunciation conditioning mechanism for text-to-speech neural codec language modeling. Existing systems reach high intelligibility and naturalness…
arXiv:2607.02636v1 Announce Type: new Abstract: Object detection is a fundamental capability for AI-driven perception in safety-critical drone and edge-vision systems, including disaster response, operational security environments,…
arXiv:2607.02670v1 Announce Type: new Abstract: Electroencephalography (EEG) offers a noninvasive approach for examining neurophysiological correlates of dimensional psychopathology, yet systematic evidence across EEG paradigms and feature…
arXiv:2607.02637v1 Announce Type: new Abstract: Recent generative models can produce high-quality synthetic images, offering scalable training training data for data-hungry models. Existing approaches to exploiting this…
arXiv:2606.12913v2 Announce Type: replace Abstract: The rapid growth of modern training datasets has significantly increased computational cost, motivating dataset pruning~(DP) methods which retain only a subset…
arXiv:2607.02715v1 Announce Type: new Abstract: Recently, neural operators have shown promising outcomes for learning solution operators of differential equations directly from data. This framework learns a…