arXiv:2602.16052v1 Announce Type: new Abstract: Speculative decoding accelerates Large Language Model (LLM) inference by verifying multiple drafted tokens in parallel. However, for Mixture-of-Experts (MoE) models, this parallelism introduces a severe bottleneck: large draft trees activate many unique experts, significantly increasing…
By minimizing the need to drive around looking for a parking spot, this technique can save drivers up to 35 minutes — and give them a realistic estimate of total travel time.
arXiv:2602.09238v3 Announce Type: replace Abstract: Explainable AI (XAI) promises to provide insight into machine learning models’ decision processes, where one goal is to identify failures such as shortcut learning. This promise relies on the field’s assumption that input features marked…
arXiv:2503.16191v2 Announce Type: replace-cross Abstract: The integration of Large Language Models (LLMs) into engineering workflows presents new opportunities for making computational tools more accessible. Especially where such tools remain underutilized due to technical or expertise barriers, such as water distribution…
arXiv:2508.10480v2 Announce Type: replace Abstract: We introduce an output layer for neural networks that ensures satisfaction of convex constraints. Our approach, $Pi$net, leverages operator splitting for rapid and reliable projections in the forward pass, and the implicit function theorem for…
arXiv:2511.12158v2 Announce Type: replace Abstract: Many bioacoustics, neuroscience, and linguistics research utilize birdsongs as proxy models to acquire knowledge in diverse areas. Developing models generally requires precisely annotated data at the level of syllables. Hence, automated and data-efficient methods that…
arXiv:2602.16601v1 Announce Type: cross Abstract: Machine learning models are increasingly trained or fine-tuned on synthetic data. Recursively training on such data has been observed to significantly degrade performance in a wide range of tasks, often characterized by a progressive drift…
arXiv:2502.17356v5 Announce Type: replace Abstract: Language models famously improve under a smooth scaling law, but some specific capabilities exhibit sudden breakthroughs in performance. Advocates of “emergence” view these capabilities as unlocked at a specific scale, but others attribute breakthroughs to…
arXiv:2602.15955v1 Announce Type: new Abstract: A P300 ERP-based Brain-Computer Interface (BCI) speller is an assistive communication tool. It searches for the P300 event-related potential (ERP) elicited by target stimuli, distinguishing it from the neural responses to non-target stimuli embedded in…
arXiv:2602.16337v1 Announce Type: cross Abstract: We propose the Subtractive Modulative Network (SMN), a novel, parameter-efficient Implicit Neural Representation (INR) architecture inspired by classical subtractive synthesis. The SMN is designed as a principled signal processing pipeline, featuring a learnable periodic activation…
