Inertial confinement fusion (ICF) is a leading pathway toward clean energy, but each shot at the National Ignition Facility costs on the order of one million dollars, making accurate AI surrogates a h...
arXiv:2607. 10366v1 Announce Type: new Abstract: Offline-trained surrogates for Inertial Confinement Fusion (ICF) suffer a well-known failure mode that iterative optimizers drive inputs into out-of-distribution (OOD) regions where predictions become unreliable.
arXiv:2509. 05510v3 Announce Type: replace-cross Abstract: Continued progress in inertial confinement fusion (ICF) requires solving inverse problems relating experimental observations to simulation input parameters, followed by design optimization.
arXiv:2604. 01313v2 Announce Type: replace Abstract: High-fidelity simulations and complex inverse problems, such as detector modeling and unfolding, are computationally intensive bottlenecks across subatomic physics, yet essential for accurate physical interpretation.
arXiv:2605. 29283v2 Announce Type: replace-cross Abstract: Recent physics foundation models claim general spatiotemporal forecasting ability, yet their evaluations often collapse performance into a single average score under a fixed training distribution.
Orthrus is a hybrid autoregressive‑diffusion model that claims to perform lossless speculative decoding by generating multiple tokens in parallel while maintaining a frozen autoregressive backbone. In our independent reproduction, we found that under BF16 precision the model matches the exact autoregressive trajectory only about 45% of the time, whereas with FP32 precision it achieves perfect matching on all evaluated prompts. Despite trajectory mismatches at lower precision, Orthrus does not exhibit systematic degradation on downstream lm‑eval‑harness benchmarks.
arXiv:2609. 04010v1 Announce Type: new Abstract: Large Language Models (LLMs) owe much of their success to next-token prediction (NTP), but their autoregressive (AR) structure requires slow, sequential token generation.
The paper investigates whether two particle physics foundation models, OmniLearned and ParticleViT, pretrained on high‑energy proton–proton and electron–proton collisions can transfer knowledge to a low‑energy neutrino experiment. Using MINERvA neutrino–nucleus scattering data, the authors evaluate the models on energy regression and charged‑current pion classification tasks, finding that the pretrained models outperform similarly sized models trained from scratch, with OmniLearned excelling in regression and ParticleViT in classification. When the same transformer architecture is initialized from unrelated text pretraining (BERT), the performance advantage is minimal for classification and absent for regression, indicating that particle‑level foundation models capture inductive biases that generalize across energy scales, detector technologies, and physics processes.
arXiv:2607. 04244v1 Announce Type: new Abstract: This report describes our approach to the Efficient Qwen Competition, where the goal is to enable low-latency serving of Qwen3.
The paper presents a method to enhance one‑dimensional rotating detonation engine (RDE) models by integrating data assimilation and machine learning. Continuous data assimilation (nudging) aligns the low‑order Koch‑Kutz solver with high‑fidelity temperature data, while a Jacobian‑regularized closure is trained on the recorded correction forces. The resulting corrected model, once the observation term is removed, autonomously reproduces the temperature spectrum and key statistical properties of the full high‑fidelity simulation.
arXiv:2608. 06107v1 Announce Type: new Abstract: Machine learning offers a promising avenue to accelerate physical simulations by replacing computationally expensive traditional Partial Differential Equation (PDE) solvers with fast, differentiable surrogate models.
arXiv:2606. 27474v1 Announce Type: cross Abstract: How should we evaluate generation systems that combine autoregressive (AR) and diffusion decoding?