Related papers: Overcoming Visual Clutter in Vision Language Actio…

Prevailing Dataset Distillation (DD) methods leveraging generative models confront two fundamental limitations. First, despite pioneering the use of diffusion models in DD and delivering impressive performance, the vast majority of…

Vision-Language-Action (VLA) models have shown great potential for embodied AI by integrating visual perception, language understanding, and action execution. In real-time deployment, these models must process continuous visual streams,…

Vision-Language-Action (VLA) models have significant potential to enable general-purpose robotic systems for a range of vision-language tasks. However, the performance of VLA-based robots is highly sensitive to the precise wording of…

Visual target navigation is a critical capability for autonomous robots operating in unknown environments, particularly in human-robot interaction scenarios. While classical and learning-based methods have shown promise, most existing…

Vision-language models (VLMs) struggle in open-world applications, where out-of-distribution (OOD) concepts often trigger cross-modal alignment collapse and severely degrade zero-shot performance. We identify the root cause as modal…

Self-supervised and language-supervised image models contain rich knowledge of the world that is important for generalization. Many robotic tasks, however, require a detailed understanding of 3D geometry, which is often lacking in 2D image…

We propose general visual inspection model using Vision-Language Model~(VLM) with few-shot images of non-defective or defective products, along with explanatory texts that serve as inspection criteria. Although existing VLM exhibit high…

Vision-Language-Action (VLA) models leverage powerful perceptual priors from web-scale Vision-Language Model (VLM) pre-training, yet they remain surprisingly brittle in practice, frequently failing at simple robotic tasks. To mitigate this,…

LiDAR semantic segmentation essential for advanced autonomous driving is required to be accurate, fast, and easy-deployed on mobile platforms. Previous point-based or sparse voxel-based methods are far away from real-time applications since…

Understanding visual degradations is a critical yet challenging problem in computer vision. While recent Vision-Language Models (VLMs) excel at qualitative description, they often fall short in understanding the parametric physics…

Vision-language-action (VLA) models show potential for general robotic tasks, but remain challenging in spatiotemporally coherent manipulation, which requires fine-grained representations. Typically, existing methods embed 3D positions into…

Large Vision Language Models (VLMs) effectively bridge the modality gap through extensive pretraining, acquiring sophisticated visual representations aligned with language. However, it remains underexplored whether these representations,…

Distracted driving is a major cause of traffic collisions, calling for robust and scalable detection methods. Vision-language models (VLMs) enable strong zero-shot image classification, but existing VLM-based distracted driver detectors…

While fine-tuning based methods for few-shot object detection have achieved remarkable progress, a crucial challenge that has not been addressed well is the potential class-specific overfitting on base classes and sample-specific…

Vision-Language Models (VLMs) have shown solid ability for multimodal understanding of both visual and language contexts. However, existing VLMs often face severe challenges of hallucinations, meaning that VLMs tend to generate responses…

Existing multi-object tracking algorithms typically fail to adequately address the issues in low-quality videos, resulting in a significant decline in tracking performance when image quality deteriorates in real-world scenarios. This…

Most existing vision-language-action (VLA) models for robotic manipulation lack progress awareness, typically relying on hand-crafted heuristics for task termination. This limitation is particularly severe in long-horizon tasks involving…

Visual Question and Answering (VQA) problems are attracting increasing interest from multiple research disciplines. Solving VQA problems requires techniques from both computer vision for understanding the visual contents of a presented…

Large-scale 3D vision-language models (VLMs) like LLaVA-3D offer strong spatial reasoning but are difficult to deploy due to high computational costs. We propose a knowledge distillation framework that transfers spatial reasoning from a 7B…

Current Vision-Language-Action (VLA) models predominantly rely on end-to-end fine-tuning. While effective, this paradigm compromises the inherent generalization capabilities of Vision-Language Models (VLMs) and incurs catastrophic…