arXiv:2505.16950v3 Announce Type: replace Abstract: Transformer LLMs have been shown to exhibit strong reasoning ability that scales with inference-time compute, most prominently through token-space “thinking” chains of thought. A growing line of work pushes extra computation into the model’s latent…
arXiv:2509.21470v1 Announce Type: new Abstract: Idempotent generative networks (IGNs) are a new line of generative models based on idempotent mapping to a target manifold. IGNs support both single-and multi-step generation, allowing for a flexible trade-off between computational cost and sample…
arXiv:2509.22598v1 Announce Type: cross Abstract: We prove that all standard subregular language classes are linearly separable when represented by their deciding predicates. This establishes finite observability and guarantees learnability with simple linear models. Synthetic experiments confirm perfect separability under noise-free…
arXiv:2509.21446v1 Announce Type: new Abstract: We introduce textit{SeismoGPT}, a transformer-based model for forecasting three-component seismic waveforms in the context of future gravitational wave detectors like the Einstein Telescope. The model is trained in an autoregressive setting and can operate on…
arXiv:2509.21465v1 Announce Type: new Abstract: Tabular foundation models are becoming increasingly popular for low-resource tabular problems. These models make up for small training datasets by pretraining on large volumes of synthetic data. The prior knowledge obtained via pretraining provides the…
arXiv:2509.21413v1 Announce Type: new Abstract: Data-free continual model merging (DFCMM) aims to fuse independently fine-tuned models into a single backbone that evolves with incoming tasks without accessing task data. This paper formulate two fundamental desiderata for DFCMM: transparency, avoiding interference…
arXiv:2509.21405v1 Announce Type: new Abstract: This work addresses object identification under known dynamics in unmanned aerial vehicle applications, where learning and classification are combined through a physics-informed residual neural network. The proposed framework leverages physics-informed learning for state mapping and…
arXiv:2509.21403v1 Announce Type: new Abstract: Large language models (LLMs) have recently been proposed as general-purpose agents for experimental design, with claims that they can perform in-context experimental design. We evaluate this hypothesis using both open- and closed-source instruction-tuned LLMs applied…
arXiv:2509.22049v1 Announce Type: cross Abstract: Computed tomography (CT) is essential for treatment and diagnostics; In case CT are missing or otherwise difficult to obtain, methods for generating synthetic CT (sCT) images from magnetic resonance imaging (MRI) images are sought after.…
arXiv:2509.21473v1 Announce Type: new Abstract: We formalize hallucinations in generative models as failures to link an estimate to any plausible cause. Under this interpretation, we show that even loss-minimizing optimal estimators still hallucinate. We confirm this with a general high…
