This paper presents a physics-constrained neural differential equation framework for parameterization, and employs it to model the time evolution of seasonal snow depth given hydrometeorological forcings. When trained on data from multiple SNOTEL sites, the parameterization predicts daily snow depth with under 9% median error and Nash Sutcliffe Efficiencies over 0.94 across a wide variety of snow climates. The parameterization also generalizes to new sites not seen during training, which is not often true for calibrated snow models. Requiring the parameterization to predict snow water equivalent in addition to snow depth only increases error to ~12%. The structure of the approach guarantees the satisfaction of physical constraints, enables these constraints during model training, and allows modeling at different temporal resolutions without additional retraining of the parameterization. These benefits hold potential in climate modeling, and could extend to other dynamical systems with physical constraints.

High-quality machine learning (ML)-ready datasets play a foundational role in developing new artificial intelligence (AI) models or fine-tuning existing models for scientific applications such as weather and climate analysis. Unfortunately, despite the growing development of new deep learning models for weather and climate, there is a scarcity of curated, pre-processed machine learning (ML)-ready datasets. Curating such high-quality datasets for developing new models is challenging particularly because the modality of the input data varies significantly for different downstream tasks addressing different atmospheric scales (spatial and temporal). Here we introduce WxC-Bench (Weather and Climate Bench), a multi-modal dataset designed to support the development of generalizable AI models for downstream use-cases in weather and climate research. WxC-Bench is designed as a dataset of datasets for developing ML-models for a complex weather and climate system, addressing selected downstream tasks as machine learning phenomenon. WxC-Bench encompasses several atmospheric processes from meso-$\beta$ (20 - 200 km) scale to synoptic scales (2500 km), such as aviation turbulence, hurricane intensity and track monitoring, weather analog search, gravity wave parameterization, and natural language report generation. We provide a comprehensive description of the dataset and also present a technical validation for baseline analysis. The dataset and code to prepare the ML-ready data have been made publicly available on Hugging Face -- https://huggingface.co/datasets/nasa-impact/WxC-Bench

Existing vector quantization (VQ) methods struggle with scalability, largely attributed to the instability of the codebook that undergoes partial updates during training. The codebook is prone to collapse as utilization decreases, due to the progressively widening distribution gap between non-activated codes and visual features. To solve the problem, we propose Index Backpropagation Quantization (IBQ), a new VQ method for the joint optimization of all codebook embeddings and the visual encoder. Applying a straight-through estimator on the one-hot categorical distribution between the encoded feature and codebook, all codes are differentiable and maintain a consistent latent space with the visual encoder. IBQ enables scalable training of visual tokenizers and, for the first time, achieves a large-scale codebook ($2^{18}$) with high dimension ($256$) and high utilization. Experiments on the standard ImageNet benchmark demonstrate the scalability and superiority of IBQ, achieving competitive results on both reconstruction ($1.00$ rFID) and autoregressive visual generation ($2.05$ gFID). The code and models are available at https://github.com/TencentARC/SEED-Voken.

Most birds can navigate seamlessly between aerial and terrestrial environments. Whereas the forelimbs evolved into wings primarily for flight, the hindlimbs serve diverse functions such as walking, hopping, and leaping, and jumping take-off for transitions into flight. These capabilities have inspired engineers to aim for similar multi-modality in aerial robots, expanding their range of applications across diverse environments. However, challenges remain in reproducing multi-modal locomotion, across gaits with distinct kinematics and propulsive characteristics, such as walking and jumping, while preserving lightweight mass for flight. This tradeoff between mechanical complexity and versatility limits most existing aerial robots to only one additional locomotor mode. Here, we overcome the complexity-versatility tradeoff with RAVEN (Robotic Avian-inspired Vehicle for multiple ENvironments), which uses its bird-inspired multi-functional legs to jump rapidly into flight, walk on ground and hop over obstacles and gaps similar to the multi-modal locomotion of birds. We show that jumping for take-off contributes substantially to initial flight take-off speed and, remarkably, that it is more energy-efficient than solely propeller-based take-off. Our analysis suggests an important tradeoff in mass distribution between legs and body among birds adapted for different locomotor strategies, with greater investment in leg mass among terrestrial birds with multi-modal gait demands. Multi-functional robot legs expand opportunities to deploy traditional fixed-wing aircraft in complex terrains through autonomous take-offs and multi-modal gaits.

Transformers are now ubiquitous for sequence modeling tasks, but their extension to multi-dimensional data remains a challenge due to the quadratic cost of the attention mechanism. In this paper, we propose Higher-Order Transformers (HOT), a novel architecture designed to efficiently process data with more than two axes, i.e. higher-order tensors. To address the computational challenges associated with high-order tensor attention, we introduce a novel Kronecker factorized attention mechanism that reduces the attention cost to quadratic in each axis' dimension, rather than quadratic in the total size of the input tensor. To further enhance efficiency, HOT leverages kernelized attention, reducing the complexity to linear. This strategy maintains the model's expressiveness while enabling scalable attention computation. We validate the effectiveness of HOT on two high-dimensional tasks, including multivariate time series forecasting, and 3D medical image classification. Experimental results demonstrate that HOT achieves competitive performance while significantly improving computational efficiency, showcasing its potential for tackling a wide range of complex, multi-dimensional data.

Recently, diffusion models have demonstrated impressive capabilities in text-guided and image-conditioned image generation. However, existing diffusion models cannot simultaneously generate a segmentation map of objects and a corresponding image from the prompt. Previous attempts either generate segmentation maps based on the images or provide maps as input conditions to control image generation, limiting their functionality to given inputs. Incorporating an inherent understanding of the scene layouts can improve the creativity and realism of diffusion models. To address this limitation, we present Panoptic Diffusion Model (PDM), the first model designed to generate both images and panoptic segmentation maps concurrently. PDM bridges the gap between image and text by constructing segmentation layouts that provide detailed, built-in guidance throughout the generation process. This ensures the inclusion of categories mentioned in text prompts and enriches the diversity of segments within the background. We demonstrate the effectiveness of PDM across two architectures: a unified diffusion transformer and a two-stream transformer with a pretrained backbone. To facilitate co-generation with fewer sampling steps, we incorporate a fast diffusion solver into PDM. Additionally, when ground-truth maps are available, PDM can function as a text-guided image-to-image generation model. Finally, we propose a novel metric for evaluating the quality of generated maps and show that PDM achieves state-of-the-art results in image generation with implicit scene control.

Modern time-series forecasting models often fail to make full use of rich unstructured information about the time series themselves. This lack of proper conditioning can lead to obvious model failures; for example, models may be unaware of the details of a particular product, and hence fail to anticipate seasonal surges in customer demand in the lead up to major exogenous events like holidays for clearly relevant products. To address this shortcoming, this paper introduces a novel forecast post-processor -- which we call LLMForecaster -- that fine-tunes large language models (LLMs) to incorporate unstructured semantic and contextual information and historical data to improve the forecasts from an existing demand forecasting pipeline. In an industry-scale retail application, we demonstrate that our technique yields statistically significantly forecast improvements across several sets of products subject to holiday-driven demand surges.

Accurate photovoltaic (PV) power forecasting is critical for integrating renewable energy sources into the grid, optimizing real-time energy management, and ensuring energy reliability amidst increasing demand. However, existing models often struggle with effectively capturing the complex relationships between target variables and covariates, as well as the interactions between temporal dynamics and multivariate data, leading to suboptimal forecasting accuracy. To address these challenges, we propose a novel model architecture that leverages the iTransformer for feature extraction from target variables and employs long short-term memory (LSTM) to extract features from covariates. A cross-attention mechanism is integrated to fuse the outputs of both models, followed by a Kolmogorov-Arnold network (KAN) mapping for enhanced representation. The effectiveness of the proposed model is validated using publicly available datasets from Australia, with experiments conducted across four seasons. Results demonstrate that the proposed model effectively capture seasonal variations in PV power generation and improve forecasting accuracy.

Federated Learning (FL) has emerged as a solution for distributed model training across decentralized, privacy-preserving devices, but the different energy capacities of participating devices (system heterogeneity) constrain real-world implementations. These energy limitations not only reduce model accuracy but also increase dropout rates, impacting on convergence in practical FL deployments. In this work, we propose LeanFed, an energy-aware FL framework designed to optimize client selection and training workloads on battery-constrained devices. LeanFed leverages adaptive data usage by dynamically adjusting the fraction of local data each device utilizes during training, thereby maximizing device participation across communication rounds while ensuring they do not run out of battery during the process. We rigorously evaluate LeanFed against traditional FedAvg on CIFAR-10 and CIFAR-100 datasets, simulating various levels of data heterogeneity and device participation rates. Results show that LeanFed consistently enhances model accuracy and stability, particularly in settings with high data heterogeneity and limited battery life, by mitigating client dropout and extending device availability. This approach demonstrates the potential of energy-efficient, privacy-preserving FL in real-world, large-scale applications, setting a foundation for robust and sustainable pervasive AI on resource-constrained networks.

LLMs exhibit advanced reasoning capabilities, offering the potential to transform natural language questions into mathematical models. However, existing open-source datasets in operations research domain lack detailed annotations of the modeling process, such as variable definitions, focusing solely on objective values, which hinders reinforcement learning applications. To address this, we release the StructuredOR dataset, annotated with comprehensive labels that capture the complete mathematical modeling process. We further propose BPP-Search, a algorithm that integrates reinforcement learning into a tree-of-thought structure using Beam search, a Process reward model, and a pairwise Preference algorithm. This approach enables efficient exploration of tree structures, avoiding exhaustive search while improving accuracy. Extensive experiments on StructuredOR, NL4OPT, and MAMO-ComplexLP datasets show that BPP-Search significantly outperforms state-of-the-art methods. In tree-based reasoning, BPP-Search excels in accuracy and efficiency, enabling faster retrieval of correct solutions.