RBF kernel to increase pretraining data diversity. Architectural details In all experiments, we use the same ExPT architecture. This section details how we constructed new objectives from the original D'Kitty and Ant that we In Ant-Energy, the reward at each time step is: R =1+ Survival reward Control cost Contact cost, (6) which means we incentivize the robot to conserve energy instead of running fast. D'Kitty tasks In D'Kitty, the goal is to design a morphology that allows the D'Kitty robot to reach We found the approximate oracle provided by Design-Bench not accurate enough to provide a reliable comparison of optimization methods on this task. C.1 Effects of GP hyperparameters We empirically examine the impact of two GP hyperparameters, the variance and the length scale ` Specifically, we evaluate the performance of ExPT on D'Kitty We average the performance across 3 seeds.

In the embedding phase, NIERT uniformly embeds both observed and target points. A learnable mask vector is introduced for target points lacking value data. The NIERT interpolator's core is a Transformer encoder with a masked self-attention mechanism, uniformly encoding observed and The NIERT, a Transformer encoder-only architecture that uniformly encodes observed points and models their correlations, exhibits superior interpolation accuracy. Our proposed architecture, specifically adapted to HINT's overall framework, introduces HINT employs residuals on observed points to estimate residuals on target points. Table 1: Statistics of the interpolation tasks used for training in each dataset.Dataset d Theoretical dataset II: Perlin is another synthetic assembly of interpolation tasks, specifically designed for the numerical interpolation of two-dimensional rough functions.

HINT consists of several sequentially arranged lightweight interpolation blocks.

Drag-based image editing aims to modify visual content followed by user-specified drag operations. Despite existing methods having made notable progress, they still fail to fully exploit the contextual information in the reference image, including fine-grained texture details, leading to edits with limited coherence and fidelity. To address this challenge, we introduce ContextDrag, a new paradigm for drag-based editing that leverages the strong contextual modeling capability of editing models, such as FLUX-Kontext. By incorporating VAE-encoded features from the reference image, ContextDrag can leverage rich contextual cues and preserve fine-grained details, without the need for finetuning or inversion. Specifically, ContextDrag introduced a novel Context-preserving Token Injection (CTI) that injects noise-free reference features into their correct destination locations via a Latent-space Reverse Mapping (LRM) algorithm. This strategy enables precise drag control while preserving consistency in both semantics and texture details. Second, ContextDrag adopts a novel Position-Consistent Attention (PCA), which positional re-encodes the reference tokens and applies overlap-aware masking to eliminate interference from irrelevant reference features. Extensive experiments on DragBench-SR and DragBench-DR demonstrate that our approach surpasses all existing SOTA methods. Code will be publicly available.

Transition control poses a critical challenge in Vertical Take-Off and Landing Unmanned Aerial Vehicle (VTOL UAV) development due to the tilting rotor mechanism, which shifts the center of gravity and thrust direction during transitions. Current control methods' decoupled control of altitude and position leads to significant vibration, and limits interaction consideration and adaptability. In this study, we propose a novel coupled transition control methodology based on reinforcement learning (RL) driven controller. Besides, contrasting to the conventional phase-transition approach, the ST3M method demonstrates a new perspective by treating cruise mode as a special case of hover. We validate the feasibility of applying our method in simulation and real-world environments, demonstrating efficient controller development and migration while accurately controlling UAV position and attitude, exhibiting outstanding trajectory tracking and reduced vibrations during the transition process.

In the 1990s, the modern scientific and technological revolution marked by computer technology, microelectronics technology, information technology, network technology, etc., entered a rapid development stage, which became the intrinsic driving force to promote the development of robotics technology, and robotics technology has developed rapidly. Among them, autonomous mobile robots(AMRs) can rely on the sensors they carry to perceive and understand the external environment, make real-time decisions according to the needs of the task, carry out closed-loop control, and operate in an autonomous or semi-autonomous manner. It is a new type of robot with certain self-learning and adaptive ability in known or unknown environment. Navigation is an important problem that needs to be solved for AMRs to realize autonomous control, which refers to the process of mobile robot sensing the environment and its own state through sensors and learning, and realizing the process of pointing to the target autonomous movement in an obstructed environment. Since the first mobile robot, Shakey, was introduced in the 1960s, mobile robot navigation has been receiving a lot of attention due to its comprehensiveness and practicality [1].