相关论文: Towards All-in-one Pre-training via Maximizing Mul…

In this paper, we propose a maximum mutual information (MMI) framework for multi-agent reinforcement learning (MARL) to enable multiple agents to learn coordinated behaviors by regularizing the accumulated return with the mutual information…

Unsupervised visible infrared person re-identification (USVI-ReID) is a challenging retrieval task that aims to retrieve cross-modality pedestrian images without using any label information. In this task, the large cross-modality variance…

Medical artificial general intelligence (MAGI) enables one foundation model to solve different medical tasks, which is very practical in the medical domain. It can significantly reduce the requirement of large amounts of task-specific data…

Multimodal embedding models, built upon causal Vision Language Models (VLMs), have shown promise in various tasks. However, current approaches face three key limitations: the use of causal attention in VLM backbones is suboptimal for…

Multimodal learning is expected to boost model performance by integrating information from different modalities. However, its potential is not fully exploited because the widely-used joint training strategy, which has a uniform objective…

Large behavior models have shown strong dexterous manipulation capabilities by extending imitation learning to large-scale training on multi-task robot data, yet their generalization remains limited by the insufficient robot data coverage.…

Multimodal retrieval models are becoming increasingly important in scenarios such as food delivery, where rich multimodal features can meet diverse user needs and enable precise retrieval. Mainstream approaches typically employ a dual-tower…

Fine-grained text-to-image retrieval aims to retrieve a fine-grained target image with a given text query. Existing methods typically assume that each training image is accurately depicted by its textual descriptions. However, textual…

Multimodal semantic understanding often has to deal with uncertainty, which means the obtained messages tend to refer to multiple targets. Such uncertainty is problematic for our interpretation, including inter- and intra-modal uncertainty.…

Multimodality Representation Learning, as a technique of learning to embed information from different modalities and their correlations, has achieved remarkable success on a variety of applications, such as Visual Question Answering (VQA),…

We introduce a vision-language foundation model called VL-BEiT, which is a bidirectional multimodal Transformer learned by generative pretraining. Our minimalist solution conducts masked prediction on both monomodal and multimodal data with…

We present JointMotion, a self-supervised pre-training method for joint motion prediction in self-driving vehicles. Our method jointly optimizes a scene-level objective connecting motion and environments, and an instance-level objective to…

Vision-language alignment learning for video-text retrieval arouses a lot of attention in recent years. Most of the existing methods either transfer the knowledge of image-text pretraining model to video-text retrieval task without fully…

Prompt tuning, like CoOp, has recently shown promising vision recognizing and transfer learning ability on various downstream tasks with the emergence of large pre-trained vision-language models like CLIP. However, we identify that existing…

Existing top-performance autonomous driving systems typically rely on the multi-modal fusion strategy for reliable scene understanding. This design is however fundamentally restricted due to overlooking the modality-specific strengths and…

Current research on trajectory prediction primarily relies on data collected by onboard sensors of an ego vehicle. With the rapid advancement in connected technologies, such as vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I)…

Although both self-supervised single-frame and multi-frame depth estimation methods only require unlabeled monocular videos for training, the information they leverage varies because single-frame methods mainly rely on appearance-based…

Many healthcare applications are inherently multimodal, involving several physiological signals. As sensors for these signals become more common, improving machine learning methods for multimodal healthcare data is crucial. Pretraining…

Multimodal VAEs seek to model the joint distribution over heterogeneous data (e.g.\ vision, language), whilst also capturing a shared representation across such modalities. Prior work has typically combined information from the modalities…

Model merging (e.g., via interpolation or task arithmetic) fuses multiple models trained on different tasks to generate a multi-task solution. The technique has been proven successful in previous studies, where the models are trained on…