Large language models (LLMs) demonstrate remarkable performance across diverse tasks, yet their effectiveness frequently depends on costly commercial APIs or cloud services.Model selection thus entails a critical trade-off between performance and cost: high-performing LLMs typically incur substantial expenses, whereas budget-friendly small language models (SLMs) are constrained by limited capabilities.Current research primarily proposes two routing strategies: pre-generation routing and cascade routing.Both approaches have distinct characteristics, with cascade routing typically offering superior cost-effectiveness and accuracy despite its higher latency.To further address the limitations of both approaches, we introduce SATER, a dual-mode compatible approach that finetunes models through shortest-response preference optimization and a confidence-aware rejection mechanism.SATER significantly reduces redundant outputs and response times, while improving both the performance of pregeneration routing and the efficiency of cascade routing.Experiments across three SLMs and six datasets, varying in type and complexity, demonstrate that SATER achieves comparable performance while consistently reducing computational costs by over 50% and cascade latency by over 80%.

Remote Sensing Image Super-Resolution (RSISR) aims to reconstruct high-resolution (HR) remote sensing (RS) images from low-resolution (LR) RS images inputs by overcoming the physical limitations of imaging systems. As a specialized task in the RS domain, RSISR provides critical support for downstream fine-grained ground object interpretation. Traditional RSISR methods face three major technical shortcomings: First, since wide-area RS images exhibit highly complex ground object characteristics, it is challenging to extract effective multi-scale features for SR reconstruction from their blurred representations. Second, the inherent imaging constraints of RS images lead to insufficient prior information, resulting in poor semantic consistency between SR reconstructions and real scenes. Third, existing SR methods struggle to balance the inherent trade-off between geometric accuracy and visual quality. To address these challenges, this paper proposes Texture Transfer Residual Denoising Dual Diffusion Model (TTRD3), a diffusion model (DM)-based reference-based super-resolution (RefSR) framework. Specifically, the Multi-scale Feature Aggregation Block (MFAB) is designed to extract spatially heterogeneous features with scale variations through parallel heterogeneous convolutional kernels. The Sparse Texture Transfer Guidance (STTG) is developed to mine multi-scale sparse texture features from high-resolution reference (Ref) images of similar scenes. The Residual Denoising Dual Diffusion Model (RDDM) framework is constructed to synergistically optimize geometric accuracy and visual quality by integrating the deterministic modeling of residual diffusion with the diverse generation of noise diffusion. Experiments on multi-source RS datasets demonstrate that TTRD3 significantly outperforms existing state-of-the-art (SOTA) methods in both geometric accuracy and visual quality. Our code and model are available at https://github.com/LED-666/TTRD3.

Designing insect-scale robots with high mobility is becoming an essential challenge in the field of robotics research. Among the methods for fabricating the transmission mechanism of the insect-scale robot, the smart composite microstructure (SCM) method is getting more and more attention. This method can construct compact and functional miniature origami mechanisms through planarized fabrication and folding assembly processes. Our previous work has proposed an untethered robot S$^{\text{2}}$worm equipped with a novel 2-DoF origami transmission mechanism. The S$^{\text{2}}$worm is fabricated through SCM and holds a top speed of 27.4 cm/s. In this work, we propose a novel strategy for designing the insect-scale robot with high mobility, that is, applying Grassmann–Cayley Algebra (GCA) to avoid the singularity of the transmission mechanism. The experimental results prove that the singularity of the previous work has been solved. The new robot prototype S$^{\text{2}}$worm-G weighs 4.71 g, scales 4.0 cm, achieves a top speed of 75.0 cm/s and a relative speed of 18.8 bodylength/s. To the best of our knowledge, the 2-DoF origami transmission mechanism is the first parallel mechanism designed for the insect-scale robot and the singularity of the mechanism is found and solved here. The experimental results prove that the refined S$^{\text{2}}$worm-G robot is one of the best insect-scale robots for its size, mass, and mobility.

Designing a swarm of robots to address different tasks and adapt to various environments through self-assembly is one of the most challenging topics in the field of robotics research. Here, we present an assembly robotic system with inchworm robots as modules. The system is called BioARS (Bionic Assembly Robotic System). It can either work as a swarm of individual untethered inchworm robots or be assembled into a quadruped robot. The inchworm robots are connected by magnets using a "shoulder-to-shoulder" connecting method, which helps strengthen the magnetic connection. Central pattern generators are used to control the trot gait of the quadruped robot. Our experiments demonstrate that the bionic assembly system is adaptive in that it can pass through confined spaces in the form of inchworms and walk on rough terrain in the form of a quadruped robot. The proposed BioARS, therefore, combines the flexibility of inchworms and the adaptability of quadruped animals, which is promising for application in planetary exploration, earthquake search and rescue operations. We also provide several examples of directions for future research regarding our system.