21 accepted papers
Reinforcement learning for program repair is hindered by sparse execution feedback and coarse sequence-level rewards that obscure which edits actually fix bugs. We present BoostAPR, a three-stage framework: (1) supervised fine-tuning on execution-verified demonstrations with reasoning traces, (2) tr…
Score Distillation Sampling has driven recent advances in text-to-3D generation. However, current approaches often fail to produce 3D assets that are both rich in detail and consistent across viewpoints. These limitations primarily arise from imbalanced guidance on fine-grained details and an overde
Generative priors in Image Super-Resolution (SR) often compromise faithful restoration, we attribute this limitation to a fundamental spectral misalignment between isotropic objectives and the intrinsic natural image manifold. While Direct Preference Optimization offers a path to alignment, its reli…
Large Language Models (LLMs) have shown impressive capabilities in multi-step reasoning and problem-solving. Recent works introduce multi-agent reflection frameworks where multiple LLM agents critique and refine each other’s outputs using reinforcement learning (RL). However, these approaches often
Diffusion Policy (DP) is effective for imitation learning in robotic manipulation, yet likelihood-based replanning methods lack self-correction and often fail once execution deviates. Vision-Language Models (VLMs) offer strong spatial reasoning for failure handling but incur prohibitive latency for
Multimodal Recommendation (MMR) systems are crucial for modern platforms but are often hampered by inherent noise and uncertainty in modal features, such as blurry images, diverse visual appearances, or ambiguous text. Existing methods often overlook this modality-specific uncertainty, leading to in…
Recently, generating 3D assets using visual priors from pretrained diffusion models has shown remarkable results. However, due to the inherent lack of 3D geometric priors in 2D diffusion, the synthesized results often suffer from spatial hallucination and multi-view inconsistency. To address this li
Direct Preference Optimization has achieved remarkable success in aligning diffusion models with human feedback. However, existing methods heavily rely on image-level preferences, which suffer from sparse rewards in the spatial dimension. This creates a fundamental misalignment: while an image may b
The growing demand for non-wearable, long-term health monitoring solutions, especially for elderly, has driven the development of bed-based physiological monitoring systems. This letter introduces a novel non-contact, bed-based micro-movement sensing system designed for accurate heart rate variabili
Accurate identification of key anatomy structures in airway intubation, the primary step in general anesthesia, is crucial for surgical success and patient safety. Achieving both object detection and segmentation in this context using deep learning technologies is challenging due to limited labeled…
Soft pneumatic actuators and robotic systems offer significant advantages in biomedical applications and enable tasks beyond the capabilities of rigid systems, benefitting from their inherent deformability, compliance, and adaptability. However, their low stiffness often leads to severe vibrations d
Patronizing and Condescending Language (PCL) is a form of discriminatory toxic speech targeting vulnerable groups, threatening both online and offline safety. While toxic speech research has mainly focused on overt toxicity, such as hate speech, microaggressions in the form of PCL remain underexplor…
In the last decades, soft robotics has been growing rapidly as an emerging research topic, bringing new paradigms for robotic manipulation, locomotion, and human‒machine interactions. Pneumatic artificial muscle is a powerful, lightweight, rapid response with great design flexibility, making it prom…
Recent advancements in 3D content generation have been significant, primarily due to the visual priors provided by pretrained diffusion models. However, large 2D visual models exhibit spatial perception hallucinations, leading to multi-view inconsistency in 3D content generated through Score Distill…
Disclaimer: Samples in this paper may be harmful and cause discomfort! Patronizing and condescending language (PCL) is a form of speech directed at vulnerable groups. As an essential branch of toxic language, this type of language exacerbates conflicts and confrontations among Internet communities a…
Aiming at solving the problems of low compliance and unsatisfactory therapeutic effect in most existing waist rehabilitation robots, this letter presents a compact waist rehabilitation robot (CWRR) for patients with low back pain (LBP). First, the CWRR with a rigid pose adjustment mechanism and a so
Joint entity and relation extraction (JERE) is one of the most important tasks in information extraction. However, most existing works focus on sentence-level coarse-grained JERE, which have limitations in real-world scenarios. In this paper, we construct a large-scale document-level fine-grained JE…
Due to the advantages of high flexibility, large workspace, and good human-body compatibility, flexible tendon-driven surgical continuum robots have attracted a lot of attention in robot-assisted minimally invasive surgery. However, due to the coupling of the position and angle of the continuum robo…
Aiming at solving the problems of low flexibility, poor internal extension, and chopstick effect in most laparoscopic surgical robots, this letter presents a flexible tendon-driven continuum surgical manipulator with eight degrees of freedom, called FIORA. The manipulator is composed of three indepe
Objective: This work presents a method for the use of a soft multi-axis force sensor to determine tissue trauma in Minimally Invasive Surgery. Despite recent developments, there is a lack of effective haptic sensing technology employed in instruments for Minimally Invasive Surgery (MIS). There is th…
A model predictive controller is developed for following the position of a human dancer in robot ballroom dancing. The control design uses a dynamic model of a dancer, based on a variant of the so-called 3D Linear Inverted Pendulum Mode that includes also the swing foot. This model serves as a basis…