arXiv:2604.15400v1 Announce Type: new Abstract: We present causal evidence that hallucination in autoregressive language models is an early trajectory commitment governed by asymmetric attractor dynamics. Using same-prompt bifurcation, in which we repeatedly sample identical inputs to observe spontaneous divergence, we…
arXiv:2504.06355v2 Announce Type: replace Abstract: Learning in environments with sparse rewards remains a fundamental challenge in reinforcement learning. Artificial curiosity addresses this limitation through intrinsic rewards to guide exploration, however, the precise formulation of these rewards has remained elusive. Ideally,…
arXiv:2604.15392v1 Announce Type: new Abstract: Physics-Informed Neural Networks (PINNs) often suffer from slow convergence, training instability, and reduced accuracy on challenging partial differential equations due to the anisotropic and rapidly varying geometry of their loss landscapes. We propose a lightweight…
arXiv:2604.15398v1 Announce Type: new Abstract: We explore the possibility of solving Partial Differential Equations (PDEs) using discrete weak formulations. We propose a programming environment for defining a discrete computational domain, introducing discrete functions defined over a set of points, constructing…
arXiv:2604.15377v1 Announce Type: new Abstract: Accurate and timely rainfall nowcasting is crucial for disaster mitigation and water resource management. Despite recent advances in deep learning, precipitation prediction remains challenging due to limitations in effectively leveraging diverse multimedia data sources. We…
arXiv:2604.15360v1 Announce Type: new Abstract: This study presents a triadic analysis of energy storage operation under multi-stage model predictive control, investigating the interplay between data characteristics, forecast uncertainty, planning horizon, and battery c-rate. Synthetic datasets are generated to systematically explore…
arXiv:2604.15356v1 Announce Type: new Abstract: Recent work on KV cache quantization, culminating in TurboQuant, has approached the Shannon entropy limit for per-vector compression of transformer key-value caches. We observe that this limit applies to a strictly weaker problem than the…
arXiv:2604.16061v1 Announce Type: cross Abstract: We study discrete k-clustering problems in general metric spaces that are constrained by a combination of two different fairness conditions within the demographic fairness model. Given a metric space (P,d), where every point in P…
arXiv:2604.15408v1 Announce Type: new Abstract: Token pruning methods for Vision Transformers (ViTs) promise quadratic reductions in attention FLOPs by dropping uninformative patches. Yet when pruned sequences are executed with state-of-the-art variable-length attention APIs — including FlashAttention-2’s varlen and PyTorch’s NestedTensor…
arXiv:2604.16278v1 Announce Type: cross Abstract: Although most of the automated theorem-proving approaches depend on formal proof systems, informal theorem proving can align better with large language models’ (LLMs) strength in natural language processing. In this work, we identify a primary…
