arXiv:2603.04317v1 Announce Type: cross Abstract: Recent work interprets the linear recoverability of geographic and temporal variables from large language model (LLM) hidden states as evidence for world-like internal representations. We test a simpler possibility: that much of the relevant structure…
arXiv:2603.03530v1 Announce Type: new Abstract: Frozen self-supervised representations often transfer well with only a few labels across many semantic tasks. We argue that a single geometric quantity, emph{directional} CDNV (decision-axis variance), sits at the core of two favorable behaviors: strong…
arXiv:2603.04385v1 Announce Type: cross Abstract: Feed-forward transformer models have driven rapid progress in 3D vision, but state-of-the-art methods such as VGGT and $pi^3$ have a computational cost that scales quadratically with the number of input images, making them inefficient when…
arXiv:2603.03531v1 Announce Type: new Abstract: Accurate prediction of terrestrial ecosystem carbon fluxes (e.g., CO$_2$, GPP, and CH$_4$) is essential for understanding the global carbon cycle and managing its impacts. However, prediction remains challenging due to strong spatiotemporal heterogeneity: ecosystem flux…
arXiv:2511.22935v2 Announce Type: replace Abstract: Electrocardiogram (ECG) analysis plays a vital role in the early detection, monitoring, and management of various cardiovascular conditions. While existing models have achieved notable success in ECG interpretation, they fail to leverage the interrelated nature…
arXiv:2602.22227v3 Announce Type: replace Abstract: Despite their impressive capabilities, Multimodal Large Language Models (MLLMs) exhibit perceptual fragility when confronted with visually complex scenes. This weakness stems from a reliance on finite training datasets, which are prohibitively expensive to scale and…
arXiv:2505.20065v2 Announce Type: replace Abstract: As Large Language Models (LLMs) are increasingly deployed in real-world applications, balancing helpfulness and safety has become a central challenge. A natural approach is to incorporate safety constraints into Reinforcement Learning from Human Feedback (RLHF),…
arXiv:2603.04223v1 Announce Type: cross Abstract: We introduce Latent Space Distribution Matching (LSDM), a novel framework for semi-supervised generative modeling of conditional distributions. LSDM operates in two stages: (i) learning a low-dimensional latent space from both paired and unpaired data, and…
arXiv:2403.10889v2 Announce Type: replace Abstract: List learning is a variant of supervised classification where the learner outputs multiple plausible labels for each instance rather than just one. We investigate classical principles related to generalization within the context of list learning.…
arXiv:2603.03459v1 Announce Type: new Abstract: We investigate when transformer MLP nonlinearity is actually necessary. A gate with $d+1$ parameters decides when to replace the full MLP with a linear surrogate. Through systematic investigation across six models (162M-2.8B parameters), two architectures,…
