Related papers: Language as an Anchor: Preserving Relative Visual …

Visual question answering (VQA) is crucial for promoting surgical education. In practice, the needs of trainees are constantly evolving, such as learning more surgical types, adapting to different robots, and learning new surgical…

Gaze estimation methods encounter significant performance deterioration when being evaluated across different domains, because of the domain gap between the testing and training data. Existing methods try to solve this issue by reducing the…

We propose LCLA (Language-Conditioned Latent Alignment), a framework for vision-language navigation that learns modular perception-action interfaces by aligning sensory observations to a latent representation of an expert policy. The expert…

The wider application of end-to-end learning methods to embodied decision-making domains remains bottlenecked by their reliance on a superabundance of training data representative of the target domain. Meta-reinforcement learning (meta-RL)…

Vision-Language-Action (VLA) models achieve over 95% success on standard benchmarks. However, through systematic experiments, we find that current state-of-the-art VLA models largely ignore language instructions. Prior work lacks: (1)…

Visual and linguistic pre-training aims to learn vision and language representations together, which can be transferred to visual-linguistic downstream tasks. However, there exists semantic confusion between language and vision during the…

Graph Contrastive Learning frameworks have demonstrated success in generating high-quality node representations. The existing research on efficient data augmentation methods and ideal pretext tasks for graph contrastive learning remains…

Recent advances in generic large models, such as GPT and DeepSeek, have motivated the introduction of universality to graph pre-training, aiming to learn rich and generalizable knowledge across diverse domains using graph representations to…

Endeavors have been recently made to transfer knowledge from the labeled pinhole image domain to the unlabeled panoramic image domain via Unsupervised Domain Adaptation (UDA). The aim is to tackle the domain gaps caused by the style…

While current diffusion-based models, typically built on U-Net architectures, have shown promising results on the text-to-motion generation task, they still suffer from semantic misalignment and kinematic artifacts. Through analysis, we…

Visual data driven dictionaries have been successfully employed for various object recognition and classification tasks. However, the task becomes more challenging if the training and test data are from contrasting domains. In this paper,…

The parameter-efficient adaptation of the image-text pretraining model CLIP for video-text retrieval is a prominent area of research. While CLIP is focused on image-level vision-language matching, video-text retrieval demands comprehensive…

LLMs typically linearize 2D tables into 1D sequences to fit their autoregressive architecture, which weakens row-column adjacency and other layout cues. In contrast, purely visual encoders can capture spatial cues, yet often struggle to…

Vision-Language-Action (VLA) models have emerged as a promising paradigm for end-to-end autonomous driving, yet their reliance on implicit parametric knowledge limits generalization in long-tail scenarios. While Retrieval-Augmented…

Vision-Language Models (VLMs) such as CLIP are trained on large amounts of image-text pairs, resulting in remarkable generalization across several data distributions. However, in several cases, their expensive training and data…

Vision-Language-Action (VLA) models aim to control robots for manipulation from visual observations and natural-language instructions. However, existing hierarchical and autoregressive paradigms often introduce architectural overhead,…

Vision Language Navigation (VLN) typically requires agents to navigate to specified objects or remote regions in unknown scenes by obeying linguistic commands. Such tasks require organizing historical visual observations for linguistic…

Visual grounding (VG) is a challenging task to localize an object in an image based on a textual description. Recent surge in the scale of VG models has substantially improved performance, but also introduced a significant burden on…

Vision-language models (VLMs) have advanced rapidly, yet they still struggle with basic spatial reasoning. Despite strong performance on general benchmarks, modern VLMs remain brittle at understanding 2D spatial relationships such as…

Audio-visual joint representation learning under Cross-Modal Generalization (CMG) aims to transfer knowledge from a labeled source modality to an unlabeled target modality through a unified discrete representation space. Existing symmetric…