Related papers: SEVO: Semantic-Enhanced Virtual Observation for Ro…
Vision-Language-Action (VLA) models are formulated to ground instructions in visual context and generate action sequences for robotic manipulation. Despite recent progress, VLA models still face challenges in learning related and reusable…
Fast and accurate object perception in low-light traffic scenes has attracted increasing attention. However, due to severe illumination degradation and the lack of reliable visual cues, existing perception models and methods struggle to…
Biological laboratory automation can reduce repetitive manual work and improve reproducibility, but reliable embodied execution in wet-lab environments remains challenging. Protocols are often unstructured, labware is frequently transparent…
Recent video semantic segmentation (VSS) methods have demonstrated promising results in well-lit environments. However, their performance significantly drops in low-light scenarios due to limited visibility and reduced contextual details.…
While end-to-end Vision-Language-Action (VLA) models offer a promising paradigm for robotic manipulation, fine-tuning them on narrow control data often compromises the profound reasoning capabilities inherited from their base…
Self-supervised VO methods have shown great success in jointly estimating camera pose and depth from videos. However, like most data-driven methods, existing VO networks suffer from a notable decrease in performance when confronted with…
Vision-Language-Action models (VLAs) are emerging as powerful tools for learning generalizable visuomotor control policies. However, current VLAs are mostly trained on large-scale image-text-action data and remain limited in two key ways:…
Existing state-of-the-art saliency detection methods heavily rely on CNN-based architectures. Alternatively, we rethink this task from a convolution-free sequence-to-sequence perspective and predict saliency by modeling long-range…
We introduce ZeroVO, a novel visual odometry (VO) algorithm that achieves zero-shot generalization across diverse cameras and environments, overcoming limitations in existing methods that depend on predefined or static camera calibration…
Can we see it all? Do we know it All? These are questions thrown to human beings in our contemporary society to evaluate our tendency to solve problems. Recent studies have explored several models in object detection; however, most have…
Stereo cameras closely mimic human binocular vision, providing rich spatial cues critical for precise robotic manipulation. Despite their advantage, the adoption of stereo vision in vision-language-action models (VLAs) remains…
Equivariant models have recently been shown to improve the data efficiency of diffusion policy by a significant margin. However, prior work that explored this direction focused primarily on point cloud inputs generated by multiple cameras…
Monocular visual odometry (VO) has attracted extensive research attention by providing real-time vehicle motion from cost-effective camera images. However, state-of-the-art optimization-based monocular VO methods suffer from the scale…
Gloss-free sign language translation (SLT) is hindered by two key challenges: **inadequate sign representation** that fails to capture nuanced visual cues, and **sentence-level semantic misalignment** in current LLM-based methods, which…
Vision-Language-Action (VLA) models have emerged as a powerful paradigm for robotic manipulation. However, existing post-training methods face a dilemma between stability and exploration: Supervised Fine-Tuning (SFT) is constrained by…
When using reinforcement learning (RL) for contact-rich robotic manipulation, vision can provide task-relevant information that accelerates learning beyond what proprioception alone can achieve. However, vision-enabled policies tend to…
The following three factors restrict the application of existing low-light image enhancement methods: unpredictable brightness degradation and noise, inherent gap between metric-favorable and visual-friendly versions, and the limited paired…
Navigating unseen environments from natural language instructions remains challenging for egocentric agents in Vision-and-Language Navigation (VLN). Humans naturally ground concrete semantic knowledge within spatial layouts during indoor…
Vision-Language-Action (VLA) models have emerged as a powerful paradigm in Embodied AI. However, the significant computational overhead of processing redundant visual tokens remains a critical bottleneck for real-time robotic deployment.…
Existing formal verification methods for image-based neural network controllers in autonomous vehicles often struggle with high-dimensional inputs, computational inefficiency, and a lack of explainability. These challenges make it difficult…