Related papers: CodeBind: Decoupled Representation Learning for Mu…
We present UniBind, a flexible and efficient approach that learns a unified representation space for seven diverse modalities -- images, text, audio, point cloud, thermal, video, and event data. Existing works, eg., ImageBind, treat the…
Research on multi-modal learning dominantly aligns the modalities in a unified space at training, and only a single one is taken for prediction at inference. However, for a real machine, e.g., a robot, sensors could be added or removed at…
Recent advancements in biology and chemistry have leveraged multi-modal learning, integrating molecules and their natural language descriptions to enhance drug discovery. However, current pre-training frameworks are limited to two…
Recently, human-computer interaction with various modalities has shown promising applications, like GPT-4o and Gemini. Given the foundational role of multimodal joint representation in understanding and generation pipelines, high-quality…
Solo piano music, despite being a single-instrument medium, possesses significant expressive capabilities, conveying rich semantic information across genres, moods, and styles. However, current general-purpose music representation models,…
A unified representation space in multi-modal learning is essential for effectively integrating diverse data sources, such as text, images, and audio, to enhance efficiency and performance across various downstream tasks. Recent binding…
Multimodal representation learning aims to capture both shared and complementary semantic information across multiple modalities. However, the intrinsic heterogeneity of diverse modalities presents substantial challenges to achieve…
In this paper, we propose EventBind, a novel and effective framework that unleashes the potential of vision-language models (VLMs) for event-based recognition to compensate for the lack of large-scale event-based datasets. In particular,…
Recent advances in representation learning have demonstrated an ability to represent information from different modalities such as video, text, and audio in a single high-level embedding vector. In this work we present a self-supervised…
To enhance the interpretability of multimodal unified representations, many studies have focused on discrete unified representations. These efforts typically start with contrastive learning and gradually extend to the disentanglement of…
Large language models with instruction-following abilities have revolutionized the field of artificial intelligence. These models show exceptional generalizability to tackle various real-world tasks through their natural language…
We present ImageBind, an approach to learn a joint embedding across six different modalities - images, text, audio, depth, thermal, and IMU data. We show that all combinations of paired data are not necessary to train such a joint…
We present TaxaBind, a unified embedding space for characterizing any species of interest. TaxaBind is a multimodal embedding space across six modalities: ground-level images of species, geographic location, satellite image, text, audio,…
Multimodal representation learning produces high-dimensional embeddings that align diverse modalities in a shared latent space. While this enables strong generalization, it also introduces scalability challenges, both in terms of storage…
Collaborative perception leverages data exchange among multiple agents to enhance overall perception capabilities. However, heterogeneity across agents introduces domain gaps that hinder collaboration, and this is further exacerbated by an…
Cross-modal alignment is a crucial task in multimodal learning aimed at achieving semantic consistency between vision and language. This requires that image-text pairs exhibit similar semantics. Traditional algorithms pursue embedding…
Understanding neural activity and information representation is crucial for advancing knowledge of brain function and cognition. Neural activity, measured through techniques like electrophysiology and neuroimaging, reflects various aspects…
Unified multi-model representation spaces are the foundation of multimodal understanding and generation. However, the billions of model parameters and catastrophic forgetting problems make it challenging to further enhance pre-trained…
Multimodal representation learning has demonstrated remarkable potential in enabling models to process and integrate diverse data modalities, such as text and images, for improved understanding and performance. While the medical domain can…
Multimodal regression aims to predict a continuous target from heterogeneous input sources and typically relies on fusion strategies such as early or late fusion. However, existing methods lack principled tools to disentangle and quantify…