Recent work in Offline Reinforcement Learning (RL) has shown that a unified Transformer trained under a masked auto-encoding objective can effectively capture the relationships between different modalities (e.g., states, actions, rewards) within given trajectory datasets. However, this information has not been fully exploited during the inference phase, where the agent needs to generate an optimal policy instead of just reconstructing masked components from unmasked ones. Given that a pretrained trajectory model can act as both a Policy Model and a World Model with appropriate mask patterns, we propose using Model Predictive Control (MPC) at test time to leverage the model's own predictive capability to guide its action selection. Empirical results on D4RL and RoboMimic show that our inference-phase MPC significantly improves the decision-making performance of a pretrained trajectory model without any additional parameter training. Furthermore, our framework can be adapted to Offline to Online (O2O) RL and Goal Reaching RL, resulting in more substantial performance gains when an additional online interaction budget is provided, and better generalization capabilities when different task targets are specified. The Masked Modeling paradigm has a simple, self-supervised training objective: predicting a randomly masked subset of the original sequence. It has become a powerful technique for generation or representation learning for sequential data, e.g., language tokens (Devlin et al., 2018) or image patches (He et al., 2022). Unlike autoregressive models like GPT (Brown et al., 2020), which condition only on the past context in the "left", bidirectional models trained with this objective learn to model the context from both sides, leading to richer representations and deeper understandings of the data's underlying dependencies. Given that a sequential decision-making trajectory inherently involves a sequence of states s and actions a, and other optional augmented properties like return-to-go (RTG) g (Chen et al., 2021) or approximate state-action value v (Yamagata et al., 2023) across T timesteps, the mask modeling paradigm can be adapted easily for sequential decision-making tasks. For example, in the case of Reinforcement Learning, the policy output P(a|s) at each time step can be regarded as predicting a masked action a conditioned on given states s.

The rise in energy demand highlights the importance of suitable subsurface storage, requiring detailed and accurate subsurface characterization often reliant on high-quality borehole well log data. However, obtaining complete well-log data is costly and time-consuming, with missing data being common due to borehole conditions or tool errors. While machine learning and deep learning algorithms have been implemented to address these issues, they often fail to capture the intricate, nonlinear relationships and long-term dependencies in complex well log sequences. Additionally, prior AI-driven models typically require retraining when introduced to new datasets and are constrained to deployment in the same basin. In this study, we explored and evaluated the potential of a time-series foundation model leveraging transformer architecture and a generative pre-trained approach for predicting and detecting anomalies in borehole well log data. Specifically, we fine-tuned and adopted the TimeGPT architecture to forecast key log responses and detect anomalies with high accuracy. Our proposed model demonstrated excellent performance, achieving R2 of up to 87% and a mean absolute percentage error (MAPE) as low as 1.95%. Additionally, the model's zero-shot capability successfully identified subtle yet critical anomalies, such as drilling hazards or unexpected geological formations, with an overall accuracy of 93%. The model represents a significant advancement in predictive accuracy and computational efficiency, enabling zero-shot inference through fine-tuning. Its application in well-log prediction enhances operational decision-making while reducing risks associated with subsurface exploration. These findings demonstrate the model's potential to transform well-log data analysis, particularly in complex geological settings.

Traditional locomotion strategies become ineffective at low Reynolds numbers, where viscous forces predominate over inertial forces. To adapt, microorganisms have evolved specialized structures like cilia and flagella for efficient maneuvering in viscous environments. Among these organisms, Phytophthora zoospores demonstrate unique locomotion mechanisms that allow them to rapidly spread and attack new hosts while expending minimal energy. In this study, we present the design, fabrication, and testing of a zoospore-inspired robot, which leverages dual flexible flagella and oscillatory propulsion mechanisms to emulate the natural swimming behavior of zoospores. Our experiments and theoretical model reveal that both flagellar length and oscillation frequency strongly influence the robot's propulsion speed, with longer flagella and higher frequencies yielding enhanced performance. Additionally, the anterior flagellum, which generates a pulling force on the body, plays a dominant role in enhancing propulsion efficiency compared to the posterior flagellum's pushing force. This is a significant experimental finding, as it would be challenging to observe directly in biological zoospores, which spontaneously release the posterior flagellum when the anterior flagellum detaches. This work contributes to the development of advanced microscale robotic systems with potential applications in medical, environmental, and industrial fields. It also provides a valuable platform for studying biological zoospores and their unique locomotion strategies.

This paper develops a Time Shift Governor (TSG)-based control scheme to enforce constraints during rendezvous and docking (RD) missions in the setting of the Two-Body problem. As an add-on scheme to the nominal closed-loop system, the TSG generates a time-shifted Chief spacecraft trajectory as a target reference for the Deputy spacecraft. This modification of the commanded reference trajectory ensures that constraints are enforced while the time shift is reduced to zero to effect the rendezvous. Our approach to TSG implementation integrates an LSTM neural network which approximates the time shift parameter as a function of a sequence of past Deputy and Chief spacecraft states. This LSTM neural network is trained offline from simulation data. We report simulation results for RD missions in the Low Earth Orbit (LEO) and on the Molniya orbit to demonstrate the effectiveness of the proposed control scheme. The proposed scheme reduces the time to compute the time shift parameter in most of the scenarios and successfully completes rendezvous missions.

Physics-informed neural networks (PINNs) commonly address ill-posed inverse problems by uncovering unknown physics. This study presents a novel unsupervised learning framework that identifies spatial subdomains with specific governing physics. It uses the partition of unity networks (POUs) to divide the space into subdomains, assigning unique nonlinear model parameters to each, which are integrated into the physics model. A vital feature of this method is a physics residual-based loss function that detects variations in physical properties without requiring labeled data. This approach enables the discovery of spatial decompositions and nonlinear parameters in partial differential equations (PDEs), optimizing the solution space by dividing it into subdomains and improving accuracy. Its effectiveness is demonstrated through applications in porous media thermal ablation and ice-sheet modeling, showcasing its potential for tackling real-world physics challenges.

Visual servoing, the method of controlling robot motion through feedback from visual sensors, has seen significant advancements with the integration of optical flow-based methods. However, its application remains limited by inherent challenges, such as the necessity for a target image at test time, the requirement of substantial overlap between initial and target images, and the reliance on feedback from a single camera. This paper introduces Imagine2Servo, an innovative approach leveraging diffusion-based image editing techniques to enhance visual servoing algorithms by generating intermediate goal images. This methodology allows for the extension of visual servoing applications beyond traditional constraints, enabling tasks like long-range navigation and manipulation without predefined goal images. We propose a pipeline that synthesizes subgoal images grounded in the task at hand, facilitating servoing in scenarios with minimal initial and target image overlap and integrating multi-camera feedback for comprehensive task execution. Our contributions demonstrate a novel application of image generation to robotic control, significantly broadening the capabilities of visual servoing systems. Real-world experiments validate the effectiveness and versatility of the Imagine2Servo framework in accomplishing a variety of tasks, marking a notable advancement in the field of visual servoing.

Large Language Models (LLMs) are distinguished by their massive parameter counts, which typically result in significant redundancy. This work introduces MaskLLM, a learnable pruning method that establishes Semi-structured (or ``N:M'') Sparsity in LLMs, aimed at reducing computational overhead during inference. Instead of developing a new importance criterion, MaskLLM explicitly models N:M patterns as a learnable distribution through Gumbel Softmax sampling. This approach facilitates end-to-end training on large-scale datasets and offers two notable advantages: 1) High-quality Masks - our method effectively scales to large datasets and learns accurate masks; 2) Transferability - the probabilistic modeling of mask distribution enables the transfer learning of sparsity across domains or tasks. We assessed MaskLLM using 2:4 sparsity on various LLMs, including LLaMA-2, Nemotron-4, and GPT-3, with sizes ranging from 843M to 15B parameters, and our empirical results show substantial improvements over state-of-the-art methods. For instance, leading approaches achieve a perplexity (PPL) of 10 or greater on Wikitext compared to the dense model's 5.12 PPL, but MaskLLM achieves a significantly lower 6.72 PPL solely by learning the masks with frozen weights. Furthermore, MaskLLM's learnable nature allows customized masks for lossless application of 2:4 sparsity to downstream tasks or domains. Code is available at https://github.com/NVlabs/MaskLLM.

Text-to-3D generation is a valuable technology in virtual reality and digital content creation. While recent works have pushed the boundaries of text-to-3D generation, producing high-fidelity 3D objects with inefficient prompts and simulating their physics-grounded motion accurately still remain unsolved challenges. To address these challenges, we present an innovative framework that utilizes the Large Language Model (LLM)-refined prompts and diffusion priors-guided Gaussian Splatting (GS) for generating 3D models with accurate appearances and geometric structures. We also incorporate a continuum mechanics-based deformation map and color regularization to synthesize vivid physics-grounded motion for the generated 3D Gaussians, adhering to the conservation of mass and momentum. By integrating text-to-3D generation with physics-grounded motion synthesis, our framework renders photo-realistic 3D objects that exhibit physics-aware motion, accurately reflecting the behaviors of the objects under various forces and constraints across different materials. Extensive experiments demonstrate that our approach achieves high-quality 3D generations with realistic physics-grounded motion.

Self-supervised learning has become a popular and effective approach for enhancing time series forecasting, enabling models to learn universal representations from unlabeled data. However, effectively capturing both the global sequence dependence and local detail features within time series data remains challenging. To address this, we propose a novel generative self-supervised method called TimeDART, denoting Diffusion Auto-regressive Transformer for Time series forecasting. In TimeDART, we treat time series patches as basic modeling units. Specifically, we employ an self-attention based Transformer encoder to model the dependencies of inter-patches. Additionally, we introduce diffusion and denoising mechanisms to capture the detail locality features of intra-patch. Notably, we design a cross-attention-based denoising decoder that allows for adjustable optimization difficulty in the self-supervised task, facilitating more effective self-supervised pre-training. Furthermore, the entire model is optimized in an auto-regressive manner to obtain transferable representations. Extensive experiments demonstrate that TimeDART achieves state-of-the-art fine-tuning performance compared to the most advanced competitive methods in forecasting tasks. Time series forecasting (Harvey, 1990; Hamilton, 2020; Box et al., 2015; Cheng et al., 2024b) is crucial in a wide array of domains, including finance (Black & Scholes, 1973), healthcare (Cheng et al., 2024c), energy management (Zhou et al., 2024). Accurate predictions of future data points could enable better decision-making, resource allocation, and risk management, ultimately leading to significant operational improvements and strategic advantages. Among the various methods developed for time series forecasting (Miller et al., 2024), deep neural networks (Ding et al., 2024; Jin et al., 2023; Cao et al., 2023; Cheng et al., 2024b) have emerged as a popular and effective solution paradigm. To further enhance the performance of time series forecasting, self-supervised learning has become an increasingly popular research paradigm (Nie et al., 2022).

Large language models (LLMs) have transformed natural language processing, yet face challenges in specialized tasks such as simulating opinions on environmental policies. This paper introduces a novel fine-tuning approach that integrates socio-demographic data from the UK Household Longitudinal Study, uniquely using profiling factors, such as age, gender, income, education, and region. This method enhances the accuracy and representation of generated views. By emulating diverse synthetic profiles, the fine-tuned models significantly outperform pre-trained counterparts, achieving measurable improvements in capturing demographic nuances. Evaluation metrics, including Chi-Squared, Cosine Similarity, Jaccard Index, and KL-divergence, reveal a strong alignment between synthetic and real-world opinions. This work demonstrates the potential of fine-tuned LLMs tailored to societal contexts to enable more ethical and precise policy simulations. Its broader implications include deploying LLMs in domains like healthcare and education, fostering inclusive and data-driven decision-making in both research and practice.