Machine learning interatomic potentials (MLIPs) have become increasingly effective at approximating quantum mechanical calculations at a fraction of the computational cost. However, lower errors on held out test sets do not always translate to improved results on downstream physical property prediction tasks. In this paper, we propose testing MLIPs on their practical ability to conserve energy during molecular dynamic simulations. If passed, improved correlations are found between test errors and their performance on physical property prediction tasks. We identify choices which may lead to models failing this test, and use these observations to improve upon highly-expressive models. The resulting model, eSEN, provides state-of-the-art results on a range of physical property prediction tasks, including materials stability prediction, thermal conductivity prediction, and phonon calculations.

Language Models (LLMs) are often quantized to lower precision to reduce the memory cost and latency in inference. However, quantization often degrades model performance, thus fine-tuning is required for various down-stream tasks. Traditional fine-tuning methods such as stochastic gradient descent and Adam optimization require backpropagation, which are error-prone in the low-precision settings. To overcome these limitations, we propose the Quantized Zeroth-Order (QuZO) framework, specifically designed for fine-tuning LLMs through low-precision (e.g., 4- or 8-bit) forward passes. Our method can avoid the error-prone low-precision straight-through estimator, and utilizes optimized stochastic rounding to mitigate the increased bias. QuZO simplifies the training process, while achieving results comparable to first-order methods in ${\rm FP}8$ and superior accuracy in ${\rm INT}8$ and ${\rm INT}4$ training. Experiments demonstrate that low-bit training QuZO achieves performance comparable to MeZO optimization on GLUE, Multi-Choice, and Generation tasks, while reducing memory cost by $2.94 \times$ in LLaMA2-7B fine-tuning compared to quantized first-order methods.

Physics-informed neural networks (PINNs) have shown promise in solving partial differential equations (PDEs), with growing interest in their energy-efficient, real-time training on edge devices. Photonic computing offers a potential solution to achieve this goal because of its ultra-high operation speed. However, the lack of photonic memory and the large device sizes prevent training real-size PINNs on photonic chips. This paper proposes a completely back-propagation-free (BP-free) and highly salable framework for training real-size PINNs on silicon photonic platforms. Our approach involves three key innovations: (1) a sparse-grid Stein derivative estimator to avoid the BP in the loss evaluation of a PINN, (2) a dimension-reduced zeroth-order optimization via tensor-train decomposition to achieve better scalability and convergence in BP-free training, and (3) a scalable on-chip photonic PINN training accelerator design using photonic tensor cores. We validate our numerical methods on both low- and high-dimensional PDE benchmarks. Through circuit simulation based on real device parameters, we further demonstrate the significant performance benefit (e.g., real-time training, huge chip area reduction) of our photonic accelerator.

Shallow water equations (SWEs) are the backbone of most hydrodynamics models for flood prediction, river engineering, and many other water resources applications. The estimation of flow resistance, i.e., the Manning's roughness coefficient $n$, is crucial for ensuring model accuracy, and has been previously determined using empirical formulas or tables. To better account for temporal and spatial variability in channel roughness, inverse modeling of $n$ using observed flow data is more reliable and adaptable; however, it is challenging when using traditional SWE solvers. Based on the concept of universal differential equation (UDE), which combines physics-based differential equations with neural networks (NNs), we developed a universal SWEs (USWEs) solver, Hydrograd, for hybrid hydrodynamics modeling. It can do accurate forward simulations, support automatic differentiation (AD) for gradient-based sensitivity analysis and parameter inversion, and perform scientific machine learning for physics discovery. In this work, we first validated the accuracy of its forward modeling, then applied a real-world case to demonstrate the ability of USWEs to capture model sensitivity (gradients) and perform inverse modeling of Manning's $n$. Furthermore, we used a NN to learn a universal relationship between $n$, hydraulic parameters, and flow in a real river channel. Unlike inverse modeling using surrogate models, Hydrograd uses a two-dimensional SWEs solver as its physics backbone, which eliminates the need for data-intensive pretraining and resolves the generalization problem when applied to out-of-sample scenarios. This differentiable modeling approach, with seamless integration with NNs, provides a new pathway for solving complex inverse problems and discovering new physics in hydrodynamics.

In tropical countries with high humidity, air conditioning can account for up to 60% of a building's energy use. For commercial buildings with centralized systems, the efficiency of the chiller plant is vital, and model predictive control provides an effective strategy for optimizing operations through dynamic adjustments based on accurate load predictions. Artificial neural networks are effective for modelling nonlinear systems but are prone to overfitting due to their complexity. Effective feature engineering can mitigate this issue. While weather data are crucial for load prediction, they are often used as raw numerical inputs without advanced processing. Clustering features is a technique that can reduce model complexity and enhance prediction accuracy. Although previous studies have explored clustering algorithms for load prediction, none have applied them to multidimensional weather data, revealing a research gap. This study presents a cooling load prediction model that combines a neural network with Kalman filtering and K-means clustering. Applied to real world data from a commercial skyscraper in Singapore's central business district, the model achieved a 46.5% improvement in prediction accuracy. An optimal chiller sequencing strategy was also developed through genetic algorithm optimization of the predictive load, potentially saving 13.8% in energy. Finally, the study evaluated the integration of thermal energy storage into the chiller plant design, demonstrating potential reductions in capital and operational costs of 26% and 13%, respectively.

Multi-Criteria Decision Making~(MCDM) is widely applied in various fields, using quantitative and qualitative analyses of multiple levels and attributes to support decision makers in making scientific and rational decisions in complex scenarios. However, traditional MCDM methods face bottlenecks in high-dimensional problems. Given the fact that Large Language Models~(LLMs) achieve impressive performance in various complex tasks, but limited work evaluates LLMs in specific MCDM problems with the help of human domain experts, we further explore the capability of LLMs by proposing an LLM-based evaluation framework to automatically deal with general complex MCDM problems. Within the framework, we assess the performance of various typical open-source models, as well as commercial models such as Claude and ChatGPT, on 3 important applications, these models can only achieve around 60\% accuracy rate compared to the evaluation ground truth. Upon incorporation of Chain-of-Thought or few-shot prompting, the accuracy rates rise to around 70\%, and highly depend on the model. In order to further improve the performance, a LoRA-based fine-tuning technique is employed. The experimental results show that the accuracy rates for different applications improve significantly to around 95\%, and the performance difference is trivial between different models, indicating that LoRA-based fine-tuned LLMs exhibit significant and stable advantages in addressing MCDM tasks and can provide human-expert-level solutions to a wide range of MCDM challenges.

Large language models (LLMs) generally utilize a consistent data distribution throughout the pretraining process. However, as the model's capability improves, it is intuitive that its data preferences dynamically change, indicating the need for pretraining with different data at various training stages. To achieve it, we propose the Perplexity Difference (PD) based Preference Curriculum learning (PDPC) framework, which always perceives and uses the data preferred by LLMs to train and boost them. First, we introduce the PD metric to quantify the difference in how challenging a sample is for weak versus strong models. Samples with high PD are more challenging for weak models to learn and are more suitable to be arranged in the later stage of pretraining. Second, we propose the preference function to approximate and predict the data preference of the LLM at any training step, so as to complete the arrangement of the dataset offline and ensure continuous training without interruption. Experimental results on 1.3B and 3B models demonstrate that PDPC significantly surpasses baselines. Notably, the 3B model trained on 1T tokens achieves an increased average accuracy of over 8.1% across MMLU and CMMLU.

We study a novel language model architecture that is capable of scaling test-time computation by implicitly reasoning in latent space. Our model works by iterating a recurrent block, thereby unrolling to arbitrary depth at test-time. This stands in contrast to mainstream reasoning models that scale up compute by producing more tokens. Unlike approaches based on chain-of-thought, our approach does not require any specialized training data, can work with small context windows, and can capture types of reasoning that are not easily represented in words. We scale a proof-of-concept model to 3.5 billion parameters and 800 billion tokens. We show that the resulting model can improve its performance on reasoning benchmarks, sometimes dramatically, up to a computation load equivalent to 50 billion parameters.

As a powerful all-weather Earth observation tool, synthetic aperture radar (SAR) remote sensing enables critical military reconnaissance, maritime surveillance, and infrastructure monitoring. Although Vision language models (VLMs) have made remarkable progress in natural language processing and image understanding, their applications remain limited in professional domains due to insufficient domain expertise. This paper innovatively proposes the first large-scale multimodal dialogue dataset for SAR images, named SARChat-2M, which contains approximately 2 million high-quality image-text pairs, encompasses diverse scenarios with detailed target annotations. This dataset not only supports several key tasks such as visual understanding and object detection tasks, but also has unique innovative aspects: this study develop a visual-language dataset and benchmark for the SAR domain, enabling and evaluating VLMs' capabilities in SAR image interpretation, which provides a paradigmatic framework for constructing multimodal datasets across various remote sensing vertical domains. Through experiments on 16 mainstream VLMs, the effectiveness of the dataset has been fully verified. The project will be released at https://github.com/JimmyMa99/SARChat.

Quantum computing, a prominent non-Von Neumann paradigm beyond Moore's law, can offer superpolynomial speedups for certain problems. Yet its advantages in efficiency for tasks like machine learning remain under investigation, and quantum noise complicates resource estimations and classical comparisons. We provide a detailed estimation of space, time, and energy resources for fault-tolerant superconducting devices running the Harrow-Hassidim-Lloyd (HHL) algorithm, a quantum linear system solver relevant to linear algebra and machine learning. Excluding memory and data transfer, possible quantum advantages over the classical conjugate gradient method could emerge at $N \approx 2^{33} \sim 2^{48}$ or even lower, requiring ${O}(10^5)$ physical qubits, ${O}(10^{12}\sim10^{13})$ Joules, and ${O}(10^6)$ seconds under surface code fault-tolerance with three types of magic state distillation (15-1, 116-12, 225-1). Key parameters include condition number, sparsity, and precision $\kappa, s\approx{O}(10\sim100)$, $\epsilon\sim0.01$, and physical error $10^{-5}$. Our resource estimator adjusts $N, \kappa, s, \epsilon$, providing a map of quantum-classical boundaries and revealing where a practical quantum advantage may arise. Our work quantitatively determine how advanced a fault-tolerant quantum computer should be to achieve possible, significant benefits on problems related to real-world.