Every story across every category, newest first. Each card links to the original publisher; daily-brief posts open as editorial pages.
arXiv:2509.23052v2 Announce Type: replace Abstract: We present a new meta-learning method to determine the optimal learning rate schedule for gradient descent. It leverages training runs from…
arXiv:2608.06503v1 Announce Type: new Abstract: Recurrent context compression controls context growth in long-horizon agents, but its behavioral effects remain poorly understood. In this preliminary empirical study,…
arXiv:2608.07401v1 Announce Type: cross Abstract: The search for new crystalline materials spans an enormous compositional and structural space. Generating candidates in this space requires jointly modeling…
arXiv:2608.06486v1 Announce Type: new Abstract: In a feature-tokenized transformer (arXiv:2106.11959) such as BiomeGPT (doi:10.64898/2026.01.05.697599), each input token is built by fusing a fixed identity with a…
arXiv:2608.07226v1 Announce Type: cross Abstract: Compact AI systems make local language-model experimentation increasingly accessible, yet practical evidence for multi-node training on desktop-class accelerators remains limited. This…
arXiv:2608.06422v1 Announce Type: new Abstract: Giving an LLM judge more compute does not necessarily make it check more requirements. When one call must return many verdicts,…
arXiv:2608.06427v1 Announce Type: new Abstract: Generative models can reproduce an observational distribution while encoding an incorrect causal structure. We study a sequential game in which a…
arXiv:2608.06428v1 Announce Type: new Abstract: Deep Operator Networks (DeepONets; arXiv:1910.03193) typically encode an input function through point values on a fixed discretization. Building on the Topological…
arXiv:2608.06441v1 Announce Type: new Abstract: Full-graph GNN training delivers high accuracy but scales poorly on multi-server clusters due to heavy, irregular inter-node embedding exchanges. We present…
arXiv:2608.06430v1 Announce Type: new Abstract: Learning from Electronic Health Records (EHRs) has gained significant attention due to its potential to improve clinical prediction. However, effective learning…
arXiv:2608.07463v1 Announce Type: cross Abstract: Recent advances in video diffusion models (VDMs) have enabled high-fidelity video synthesis. However, generating mirror reflections remains challenging because the content…
arXiv:2608.06448v1 Announce Type: new Abstract: Recovering a periodic 3D crystal structure from sparse, unindexed electron diffraction (ED) observations is a challenging generative inverse problem. Existing ED-based…
arXiv:2606.03121v2 Announce Type: replace Abstract: Multivariate time series forecasting plays a critical role in real-world applications, including weather prediction, stock analysis, and health monitoring. Due to…
arXiv:2601.19897v2 Announce Type: replace Abstract: Continual learning, enabling models to acquire new skills and knowledge without degrading existing capabilities, remains a fundamental challenge for foundation models.…
arXiv:2509.05208v2 Announce Type: replace-cross Abstract: Large language models (LLMs) excel at program synthesis, yet their ability to produce symbolic graphics programs (SGPs) that render into precise…
arXiv:2608.07042v1 Announce Type: cross Abstract: Rectified flows, also called flow matching or stochastic interpolants, are generative models that learn a time-dependent vector field steering a probability…
arXiv:2608.07361v1 Announce Type: cross Abstract: Vision-language-action (VLA) models route driving decisions through a deep language model, but it is unclear how much of that depth the…
arXiv:2608.06717v1 Announce Type: new Abstract: Diffusion-based face restoration that adjusts the sampling trajectory of pre-trained diffusion models has achieved remarkable progress. However, existing approaches provide insufficient…
arXiv:2608.07018v1 Announce Type: cross Abstract: Horizon detection in images of ice-covered waters is a challenging problem for maritime navigation due to low contrast between water and…
arXiv:2608.06712v1 Announce Type: new Abstract: Model robustness against natural image corruptions is essential for safety-critical applications. While existing methods primarily focus on implicit representation learning, we…
arXiv:2608.06799v1 Announce Type: cross Abstract: Learning structured and control-relevant latent representations remains a key challenge for world models. Recent JEPA-based world models learn action-conditioned predictive latent…
arXiv:2608.06691v1 Announce Type: new Abstract: Real-time human action recognition on Internet-of-Things (IoT) edge devices requires models that capture rich spatio-temporal cues within strict latency, memory, and…
arXiv:2512.22539v4 Announce Type: replace-cross Abstract: While Vision-Language-Action models (VLAs) are rapidly advancing toward generalist robot policies, quantitatively characterizing their capability boundaries and failure modes remains challenging.…
arXiv:2608.06674v1 Announce Type: new Abstract: Adversarial vulnerabilities remain a major concern for the safe deployment of neural networks, particularly in object detection, a core task embedded…