arXiv:2411.16719v4 Announce Type: replace-cross
Abstract: Domain randomization through synthesis is a powerful strategy to train networks that are unbiased with respect to the domain of the input images. Randomization allows networks to see a virtuall…
arXiv:2604.09429v3 Announce Type: replace-cross
Abstract: Recovering camera parameters from images and rendering scenes from novel viewpoints have been treated as separate tasks in computer vision and graphics. This separation breaks down when image c…
arXiv:2508.01575v2 Announce Type: replace
Abstract: Long-term time series forecasting (LTSF) underpins critical applications from energy management to weather prediction, yet achieving reliable multi-step-ahead accuracy remains challenging. Existing L…
arXiv:2604.20595v1 Announce Type: cross
Abstract: We establish a mathematical correspondence between state space models, a state-of-the-art architecture for capturing long-range dependencies in data, and an exactly solvable nonlinear oscillator networ…
arXiv:2604.09563v2 Announce Type: replace-cross
Abstract: AI systems produce large volumes of logs as they interact with tools and users. Analysing these logs can help understand model capabilities, propensities, and behaviours, or assess whether an e…
arXiv:2604.19859v1 Announce Type: new
Abstract: Edge-scale deep research agents based on small language models are attractive for real-world deployment due to their advantages in cost, latency, and privacy. In this work, we study how to train a strong…
arXiv:2604.20659v1 Announce Type: new
Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has advanced the reasoning capabilities of Large Language Models (LLMs) by leveraging direct outcome verification instead of learned reward models. B…
arXiv:2604.19877v1 Announce Type: new
Abstract: We release Super Apriel, a 15B-parameter supernet in which every decoder layer provides four trained mixer choices — Full Attention (FA), Sliding Window Attention (SWA), Kimi Delta Attention (KDA), and …
arXiv:2604.19903v1 Announce Type: new
Abstract: Cement production is among the largest contributors to industrial air pollution, emitting ~3 Mt NOx/year. The industry-standard mitigation approach, selective non-catalytic reduction (SNCR), exhibits low…
arXiv:2604.20688v1 Announce Type: new
Abstract: Storm surge forecasting remains a critical challenge in mitigating the impacts of tropical cyclones on coastal regions, particularly given recent trends of rapid intensification and increasing nearshore …