arXiv:2511.08579v2 Announce Type: replace-cross Abstract: Can language models (LMs) learn to faithfully describe their internal computations? Are they better able to describe themselves than other models? We study the extent to which LMs’ privileged access to their own internals can…
arXiv:2512.23753v1 Announce Type: new Abstract: Evidential deep learning (EDL) models, based on Subjective Logic, introduce a principled and computationally efficient way to make deterministic neural networks uncertainty-aware. The resulting evidential models can quantify fine-grained uncertainty using learned evidence. However, the…
arXiv:2512.23755v1 Announce Type: new Abstract: Human decision-making, emotions, and collective psychology are complex factors that shape the temporal dynamics observed in financial and economic systems. Many recent time series forecasting models leverage external sources (e.g., news and social media) to…
arXiv:2512.23752v1 Announce Type: new Abstract: Recent work has shown that small transformers trained in controlled “wind-tunnel” settings can implement exact Bayesian inference, and that their training dynamics produce a geometric substrate — low-dimensional value manifolds and progressively orthogonal keys —…
arXiv:2512.23749v1 Announce Type: new Abstract: Human-level concept learning argues that humans typically learn new concepts from a single example, whereas machine learning algorithms typically require hundreds of samples to learn a single concept. Our brain subconsciously identifies important features and…
arXiv:2512.23748v1 Announce Type: new Abstract: For complex simulation problems, inferring parameters of scientific interest often precludes the use of classical likelihood-based techniques due to intractable likelihood functions. Simulation-based inference (SBI) methods forego the need for explicit likelihoods by directly utilizing…
arXiv:2501.02994v2 Announce Type: replace-cross Abstract: We propose a novel deep neural network methodology for density estimation on product Riemannian manifold domains. In our approach, the network directly parameterizes the unknown density function and is trained using a penalized maximum likelihood…
arXiv:2512.23762v1 Announce Type: new Abstract: Machine learning (ML) represents an efficient and popular approach for network traffic classification. However, network traffic classification is a challenging domain, and trained models may degrade soon after deployment due to the obsolete datasets and…
arXiv:2507.06415v2 Announce Type: replace-cross Abstract: Long-context reasoning requires accurately identifying relevant information in extensive, noisy input contexts. Previous research shows that using test-time learning to encode context directly into model parameters can effectively enable reasoning over noisy information. However, meta-learning…
arXiv:2512.23763v1 Announce Type: new Abstract: We introduce Neural Optimal Design of Experiments, a learning-based framework for optimal experimental design in inverse problems that avoids classical bilevel optimization and indirect sparsity regularization. NODE jointly trains a neural reconstruction model and a…
