arXiv:2510.13060v1 Announce Type: new Abstract: Reverse Kullback-Leibler (KL) divergence-based regularization with respect to a fixed reference policy is widely used in modern reinforcement learning to preserve the desired traits of the reference policy and sometimes to promote exploration (using uniform…
arXiv:2403.16843v5 Announce Type: replace Abstract: Large language models (LLMs) have been increasingly employed for (interactive) decision-making, via the development of LLM-based autonomous agents. Despite their emerging successes, the performance of LLM agents in decision-making has not been fully investigated through…
arXiv:2510.13065v1 Announce Type: new Abstract: Finding “true” clusters in a data set is a challenging problem. Clustering solutions obtained using different models and algorithms do not necessarily provide compact and well-separated clusters or the optimal number of clusters. Cluster validity…
arXiv:2411.09642v3 Announce Type: replace Abstract: Specifying all desirable properties of a language model is challenging, but certain requirements seem essential. Given samples from an unknown language, the trained model should produce valid strings not seen in training and be expressive…
arXiv:2510.13068v1 Announce Type: new Abstract: Electroencephalography (EEG) captures neural activity across multiple temporal and spectral scales, yielding signals that are rich but complex for representation learning. Recently, EEG foundation models trained to predict masked signal-tokens have shown promise for learning…
arXiv:2502.17356v4 Announce Type: replace Abstract: Language models famously improve under a smooth scaling law, but some specific capabilities exhibit sudden breakthroughs in performance. While advocates of “emergence” view breakthroughs as unlocked capabilities, others attribute them to thresholding effects on noncontinuous…
arXiv:2510.13077v1 Announce Type: new Abstract: We develop an unsupervised deep learning framework for downlink beamforming in large-scale MU-MISO channels. The model is trained offline, allowing real-time inference through lightweight feedforward computations in dynamic communication environments. Following the learning-to-optimize (L2O) paradigm,…
arXiv:2505.12204v3 Announce Type: replace Abstract: Recent advances in reinforcement learning (RL) have demonstrated impressive capabilities in complex decision-making tasks. This progress raises a natural question: how do these artificial systems compare to biological agents, which have been shaped by millions…
arXiv:2510.13087v1 Announce Type: new Abstract: Marketing Mix Modeling (MMM) is a statistical technique used to estimate the impact of marketing activities on business outcomes such as sales, revenue, or customer visits. Traditional MMM approaches often rely on linear regression or…
After being trained with this technique, vision-language models can better identify a unique item in a new scene.
