Quality follows upgrading
Academic
arXiv:2603.06727v1 Announce Type: new Abstract: Current safety alignment methods encode safe behavior implicitly within model parameters, creating a fundamental opacity: we cannot easily inspect why …
arXiv:2603.06728v1 Announce Type: new Abstract: Over two billion Apple devices ship with a Neural Processing Unit (NPU) - the Apple Neural Engine (ANE) - yet …
arXiv:2603.06729v1 Announce Type: new Abstract: Navigating safely through dense crowds requires collision avoidance that generalizes beyond the densities seen during training. Learning-based crowd navigation can …
arXiv:2603.06738v1 Announce Type: new Abstract: Recent Super-Resolution~(SR) methods mainly adopt Transformers for their strong long-range modeling capability and exceptional representational capacity. However, most SR Transformers …
arXiv:2603.06741v1 Announce Type: new Abstract: Training frontier-scale diffusion models often requires substantial computational resources concentrated in tightly coupled clusters, limiting participation to well-resourced institutions. While …
arXiv:2603.06742v1 Announce Type: new Abstract: Constrained generative modeling is fundamental to applications such as robotic control and autonomous driving, where models must respect physical laws …
arXiv:2603.06743v1 Announce Type: new Abstract: Group Relative Policy Optimization (GRPO) is highly effective for post-training autoregressive (AR) language models, yet its direct application to diffusion …
arXiv:2603.06745v1 Announce Type: new Abstract: Large Language Models (LLMs), despite advances in instruction tuning, often fail to follow complex user instructions. Activation steering techniques aim …
arXiv:2603.06748v1 Announce Type: new Abstract: Protein sequence design must balance designability, defined as the ability to recover a target backbone, with multiple, often competing, developability …
arXiv:2603.06752v1 Announce Type: new Abstract: The ensemble Kalman filter (EnKF) is widely used for data assimilation in high-dimensional systems, but its performance often deteriorates for …
arXiv:2603.05598v1 Announce Type: cross Abstract: We investigate the impact of tokeniser pretraining on the accuracy and efficiency of physics emulation. Modern high-resolution simulations produce vast …
arXiv:2603.05538v1 Announce Type: cross Abstract: Data-driven surrogate models improve the efficiency of simulating continuous dynamical systems, yet their autoregressive rollouts are often limited by instability …