arXiv:2509.16924v1 Announce Type: new Abstract: In audio-visual navigation (AVN) tasks, an embodied agent must autonomously localize a sound source in unknown and complex 3D environments based on audio-visual signals. Existing methods often rely on static modality fusion strategies and neglect…
arXiv:2505.11750v3 Announce Type: replace-cross Abstract: Improving the skill of medium-range (3-8 day) severe weather prediction is crucial for mitigating societal impacts. This study introduces a novel approach leveraging decoder-only transformer networks to post-process AI-based weather forecasts, specifically from the Pangu-Weather…
arXiv:2509.16958v1 Announce Type: new Abstract: Abductive reasoning – the search for plausible explanations – has long been central to human inquiry, from forensics to medicine and scientific discovery. Yet formal approaches in AI have largely reduced abduction to eliminative search:…
arXiv:2509.16627v1 Announce Type: new Abstract: Conditional multidimensional scaling seeks for a low-dimensional configuration from pairwise dissimilarities, in the presence of other known features. By taking advantage of available data of the known features, conditional multidimensional scaling improves the estimation quality…
arXiv:2411.17180v4 Announce Type: replace Abstract: The growing environmental footprint of artificial intelligence (AI), especially in terms of storage and computation, calls for more frugal and interpretable models. Sparse models (e.g., linear, neural networks) offer a promising solution by selecting only…
arXiv:2503.21639v4 Announce Type: replace-cross Abstract: This paper tackles a fundamental inference problem: given $n$ observations from a distribution $P$ over $mathbb{R}^d$ with unknown mean $boldsymbol{mu}$, we must form a confidence set for the index (or indices) corresponding to the smallest…
arXiv:2505.19741v2 Announce Type: replace-cross Abstract: We study online adversarial regression with convex losses against a rich class of continuous yet highly irregular prediction rules, modeled by Besov spaces $B_{pq}^s$ with general parameters $1 leq p,q leq infty$ and smoothness $s…
arXiv:2409.10096v3 Announce Type: replace-cross Abstract: In a reinforcement learning (RL) setting, the agent’s optimal strategy heavily depends on her risk preferences and the underlying model dynamics of the training environment. These two aspects influence the agent’s ability to make well-informed…
arXiv:2502.02216v2 Announce Type: replace-cross Abstract: We introduce AutoGraph, a scalable autoregressive model for attributed graph generation using decoder-only transformers. By flattening graphs into random sequences of tokens through a reversible process, AutoGraph enables modeling graphs as sequences without relying on…
arXiv:2509.17543v1 Announce Type: new Abstract: Existing distribution compression methods reduce dataset size by minimising the Maximum Mean Discrepancy (MMD) between original and compressed sets, but modern datasets are often large in both sample size and dimensionality. We propose Bilateral Distribution…
