arXiv:2606. 15344v1 Announce Type: cross Abstract: Generative modelling requires efficient stochastic nonlinear transformations and physical platforms that can naturally realise them.
arXiv:2602. 21565v3 Announce Type: replace Abstract: Generative Flow Networks (GFlowNets) learn to sample diverse candidates in proportion to a reward function, making them well-suited for scientific discovery, where exploring multiple promising solutions is crucial.
The review examines how Large Language Models (LLMs) enhance nanophotonics design by providing semantic interfaces, code generation, and tool orchestration. It traces the evolution from classical neural networks to transformer-based models and categorizes LLM applications into surrogate models that map structure to spectrum and agentic systems that generate code and orchestrate simulations for closed-loop optimization. The article also highlights potential cross-disciplinary uses of LLMs in materials science and wireless communications, and envisions future multimodal foundation models that actively collaborate in autonomous scientific discovery.
Metasurfaces have revolutionized the development of photonic devices by enabling unprecedented precision in light manipulation. However, their design processes are often constrained by computationally...
WildRelight is the first in-the-wild dataset designed to evaluate single-image relighting models, featuring high-resolution outdoor scenes captured under strictly aligned, temporally varying natural illuminations paired with high-dynamic-range environment maps. The benchmark demonstrates that state-of-the-art models trained on synthetic data suffer severe domain shifts when applied to real-world imagery. Leveraging the dataset’s temporal structure, the authors introduce a physics-guided inference framework combining Diffusion Posterior Sampling with Temporal Sampling-Aware Test-Time Adaptation, enabling synthetic models to self-supervise and align with real-world statistics on-the-fly.
arXiv:2602. 04119v2 Announce Type: replace Abstract: The application of generative models for experimental drug discovery campaigns is severely limited by the difficulty of designing molecules de novo that can be synthesized in practice.
arXiv:2506. 23546v2 Announce Type: replace-cross Abstract: Fixed points of recurrent neural networks can be leveraged to store and generate information.
arXiv:2607. 27372v1 Announce Type: new Abstract: The deep learning revolution, kicked off by AlexNet, taught us that end-to-end training beats decomposing a problem into hand-designed stages.
arXiv:2608. 08101v1 Announce Type: new Abstract: Generative AI has emerged as one of the most transformative forces in modern artificial intelligence, reshaping how we create, imagine, and interact with digital content.
The paper presents a probabilistic deep learning emulator—a ResNet‑inspired Conditional Variational Autoencoder—for the stochastic Holton–Mass model of stratospheric variability, which exhibits rare transitions between strong and weak polar vortex regimes. The emulator accurately reproduces short‑term dynamics, steady‑state distributions, regime persistence, rare transition rates, the committor function, and expected lead times. Analysis of the 32‑dimensional latent space via PCA reveals an unsupervised separation into four physically interpretable clusters that correspond to the two vortex regimes and their stable or transition‑prone states.
Energy-Based Models (EBMs) provide an interpretable framework for generative modeling of scientific data, but poor Markov Chain Monte Carlo mixing often limits their reliability. We introduce a training algorithm based on Parallel Trajectory Tempering (PTT), which exploits the continuity of the optimization path to maintain equilibrium sampling throughout learning.
The paper introduces StyleGANCA, a lightweight neural cellular automata (NCA) based generative adversarial network designed for medical image synthesis. By combining a StyleGAN-inspired mapping network with adaptive style modulation in a multi-scale NCA framework, the model achieves high-quality image generation with far fewer parameters than existing adversarial, variational, diffusion, and NCA baselines. Experiments on BloodMNIST and PathMNIST show competitive FID and KID scores, and the synthetic images preserve class-specific information, effectively supporting downstream multi-class classifier training.
arXiv:2403. 18026v3 Announce Type: replace-cross Abstract: High-throughput imaging is often constrained by a trade-off between acquisition speed and image quality.