Related papers: Demographic User Modeling for Social Robotics with…

Learning generalizable visual representations across different embodied environments is essential for effective robotic manipulation in real-world scenarios. However, the limited scale and diversity of robot demonstration data pose a…

Predicting human behavior in shared environments is crucial for safe and efficient human-robot interaction. Traditional data-driven methods to that end are pre-trained on domain-specific datasets, activity types, and prediction horizons. In…

Severe data imbalance naturally exists among web-scale vision-language datasets. Despite this, we find CLIP pre-trained thereupon exhibits notable robustness to the data imbalance compared to supervised learning, and demonstrates…

Significant progress has been made on visual captioning, largely relying on pre-trained features and later fixed object detectors that serve as rich inputs to auto-regressive models. A key limitation of such methods, however, is that the…

Large language models (LLMs) have emerged as powerful general-purpose interfaces for many machine learning problems. Recent work has adapted LLMs to generative visual tasks like image captioning, visual question answering, and visual chat,…

Recent multimodal models such as Contrastive Language-Image Pre-training (CLIP) have shown remarkable ability to align visual and linguistic representations. However, domains where small visual differences carry large semantic significance,…

Multimodal large language models (MLLMs) have shown remarkable performance in vision-language tasks. However, existing MLLMs are primarily trained on generic datasets, limiting their ability to reason on domain-specific visual cues such as…

Preference-conditioned image generation seeks to adapt generative models to individual users, producing outputs that reflect personal aesthetic choices beyond the given textual prompt. Despite recent progress, existing approaches either…

Pre-trained language models have been shown to improve performance in many natural language tasks substantially. Although the early focus of such models was single language pre-training, recent advances have resulted in cross-lingual and…

Social Media Popularity Prediction is a complex multimodal task that requires effective integration of images, text, and structured information. However, current approaches suffer from inadequate visual-textual alignment and fail to capture…

Few-shot classification requires deep neural networks to learn generalized representations only from limited training images, which is challenging but significant in low-data regimes. Recently, CLIP-based methods have shown promising…

Masked image modeling (MIM) as pre-training is shown to be effective for numerous vision downstream tasks, but how and where MIM works remain unclear. In this paper, we compare MIM with the long-dominant supervised pre-trained models from…

We present Fast Language-Image Pre-training (FLIP), a simple and more efficient method for training CLIP. Our method randomly masks out and removes a large portion of image patches during training. Masking allows us to learn from more…

Multi-modal learning has become increasingly popular due to its ability to leverage information from different data sources (e.g., text and images) to improve the model performance. Recently, CLIP has emerged as an effective approach that…

Vision-language models, like CLIP (Contrastive Language Image Pretraining), are becoming increasingly popular for a wide range of multimodal retrieval tasks. However, prior work has shown that large language and deep vision models can learn…

Recent advances in vision-language pre-training have enabled machines to perform better in multimodal object discrimination (e.g., image-text semantic alignment) and image synthesis (e.g., text-to-image generation). On the other hand,…

Existing contrastive language-image pre-training aims to learn a joint representation by matching abundant image-text pairs. However, the number of image-text pairs in medical datasets is usually orders of magnitude smaller than that in…

The availability of large language models and open-vocabulary object perception methods enables more flexibility for domestic service robots. The large variability of domestic tasks can be addressed without implementing each task…

Contrastive Language-Image Pretraining (CLIP) has emerged as a novel paradigm to learn visual models from language supervision. While researchers continue to push the frontier of CLIP, reproducing these works remains challenging. This is…

Multimodal contrastive pretraining has been used to train multimodal representation models, such as CLIP, on large amounts of paired image-text data. However, previous studies have revealed that such models are vulnerable to backdoor…