arXiv:2606.04063v1 Announce Type: new Abstract: Deploying large language models (LLMs) is challenging due to their significant memory and computational requirements. While some methods address this by developing small or tiny language models from scratch, these approaches demand extensive GPU training.…
arXiv:2606.04750v1 Announce Type: cross Abstract: Instilling virtuous behavior in artificial intelligence has seen increasing interest. One of the techniques proposed is known as affinity-based reinforcement learning, which uses policy regularization on the objective function to incentivize virtuous actions without being…
arXiv:2606.04073v1 Announce Type: new Abstract: This paper proposes a two-stage pseudo anomaly-guided anomaly detection method (textbf{T}wo-stage textbf{P}seudo textbf{A}nomaly-guided textbf{A}nomaly textbf{D}etection, textbf{TPA-AD}) for axle-box bearing time-series anomaly detection (time series anomaly detection, TSAD) under the setting where only normal samples are…
arXiv:2606.05101v1 Announce Type: cross Abstract: Audio deepfake detection (ADD) models are critical for countering the malicious use of text-to-speech (TTS) models. Evaluating and strengthening ADD models requires developing datasets that span the space of generated audio and highlight high-error regions.…
arXiv:2606.04074v1 Announce Type: new Abstract: Adaptive patching is a recent and compelling proposal for time-series Transformers: allocate finer patches where the sequence looks locally informative. This paper asks under what conditions a content-adaptive patching operator should outperform a tuned uniform…
arXiv:2506.05233v2 Announce Type: replace Abstract: Sequence modeling is currently dominated by causal transformer architectures that use softmax self-attention. Although widely adopted, transformers require scaling memory and compute linearly during inference. A recent stream of work linearized the softmax operation, resulting…
arXiv:2606.04075v1 Announce Type: new Abstract: Reinforcement learning (RL) has become a dominant post-training paradigm, enabling large language models (LLMs) to learn from rewards. We observe that societal regulations are structurally similar to reward functions. They define measurable outcomes, thresholds, and…
arXiv:2512.17678v2 Announce Type: replace Abstract: Selecting compact and informative gene subsets from single-cell transcriptomic data is essential for biomarker discovery, improving interpretability, and cost-effective profiling. However, most existing feature selection approaches either operate as multi-stage pipelines or rely on post…
arXiv:2606.04100v1 Announce Type: new Abstract: Machine learning interatomic potentials (MLIPs) enable efficient and accurate atomistic simulations but depend critically on the quality and diversity of the training data. We introduce Stein kernelized molecular dynamics (SKMD), an enhanced sampling method that…
arXiv:2602.02405v2 Announce Type: replace Abstract: Improving the reasoning capabilities of large language models (LLMs) typically relies either on the model’s ability to sample a correct solution to be reinforced or the existence of a stronger model able to solve the…
