Related papers: LG-CAV: Train Any Concept Activation Vector with L…
Considerable progress has recently been made in leveraging CLIP (Contrastive Language-Image Pre-Training) models for text-guided image manipulation. However, all existing works rely on additional generative models to ensure the quality of…
We study the task of extending the large language model (LLM) into a vision-language instruction-following model. This task is crucial but challenging since the LLM is trained on text modality only, making it hard to effectively digest the…
Automated audio captioning is a task that generates textual descriptions for audio content, and recent studies have explored using visual information to enhance captioning quality. However, current methods often fail to effectively fuse…
Our understanding of the visual world is centered around various concept axes, characterizing different aspects of visual entities. While different concept axes can be easily specified by language, e.g. color, the exact visual nuances along…
Visual question answering (VQA) is the task of answering questions about an image. The task assumes an understanding of both the image and the question to provide a natural language answer. VQA has gained popularity in recent years due to…
Multilingual vision-language models have made significant strides in image captioning, yet they still lag behind their English counterparts due to limited multilingual training data and costly large-scale model parameterization.…
Pre-trained contextual vision-and-language (V&L) models have achieved impressive performance on various benchmarks. However, existing models require a large amount of parallel image-caption data for pre-training. Such data are costly to…
Image-based visual-language (I-VL) pre-training has shown great success for learning joint visual-textual representations from large-scale web data, revealing remarkable ability for zero-shot generalisation. This paper presents a simple but…
With the maturity of visual detection techniques, we are more ambitious in describing visual content with open-vocabulary, fine-grained and free-form language, i.e., the task of image captioning. In particular, we are interested in…
The scaling of large language models to encode all the world's knowledge in model parameters is unsustainable and has exacerbated resource barriers. Retrieval-Augmented Generation (RAG) presents a potential solution, yet its application to…
The integration of visual encoders and large language models (LLMs) has driven recent progress in multimodal large language models (MLLMs). However, the scarcity of high-quality instruction-tuning data for vision-language tasks remains a…
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)…
Recent Vision-Language-Action (VLA) models built on pre-trained Vision-Language Models (VLMs) require extensive post-training, resulting in high computational overhead that limits scalability and deployment.We propose CogVLA, a…
Vision model have gained increasing attention due to their simplicity and efficiency in Scene Text Recognition (STR) task. However, due to lacking the perception of linguistic knowledge and information, recent vision models suffer from two…
As large vision language models (VLMs) advance, their capabilities in multilingual visual question answering (mVQA) have significantly improved. Chain-of-thought (CoT) reasoning has been proven to enhance interpretability and complex…
Recent advancements in Vision-Language (VL) research have sparked new benchmarks for complex visual reasoning, challenging models' advanced reasoning ability. Traditional Vision-Language Models (VLMs) perform well in visual perception tasks…
Vision-language (VL) pre-training has recently gained much attention for its transferability and flexibility in novel concepts (e.g., cross-modality transfer) across various visual tasks. However, VL-driven segmentation has been…
Concept Activation Vectors (CAVs) are widely used to model human-understandable concepts as directions within the latent space of neural networks. They are trained by identifying directions from the activations of concept samples to those…
Voice Activity Detection (VAD) is the process of automatically determining whether a person is speaking and identifying the timing of their speech in an audiovisual data. Traditionally, this task has been tackled by processing either audio…
Concept Activation Vectors (CAVs) are a fundamental tool for concept-based explainability in deep learning, yet their practical utility is limited by statistical instability. We analyze the stochastic nature of CAVs and the Testing with…