Related papers: Video Relationship Detection Using Mixture of Expe…

Building scalable vision-language models to learn from diverse, multimodal data remains an open challenge. In this paper, we introduce an Efficient Vision-languagE foundation model, namely EVE, which is one unified multimodal Transformer…

Soft prompt learning methods are effective for adapting vision-language models (VLMs) to downstream tasks. Nevertheless, empirical evidence reveals a tendency of existing methods that they overfit seen classes and exhibit degraded…

While Dense Retrieval Models (DRMs) have advanced Information Retrieval (IR), one limitation of these neural models is their narrow generalizability and robustness. To cope with this issue, one can leverage the Mixture-of-Experts (MoE)…

Audio-visual speech recognition (AVSR) has become critical for enhancing speech recognition in noisy environments by integrating both auditory and visual modalities. However, existing AVSR systems struggle to scale up without compromising…

We present a unified Vision-Language pretrained Model (VLMo) that jointly learns a dual encoder and a fusion encoder with a modular Transformer network. Specifically, we introduce Mixture-of-Modality-Experts (MoME) Transformer, where each…

Product search is the most common way for people to satisfy their shopping needs on e-commerce websites. Products are typically annotated with one of several broad categorical tags, such as "Clothing" or "Electronics", as well as…

Visual relationship detection is fundamental for holistic image understanding. However, the localization and classification of (subject, predicate, object) triplets remain challenging tasks, due to the combinatorial explosion of possible…

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…

Mixture-of-Experts (MoE) has become a prevalent backbone for large vision-language models (VLMs), yet how modality-specific signals should guide expert routing remains under-explored. Existing routing strategies are either hand-crafted or…

Visual 2.5D perception involves understanding the semantics and geometry of a scene through reasoning about object relationships with respect to the viewer in an environment. However, existing works in visual recognition primarily focus on…

In this paper, a deep mixture of diverse experts algorithm is developed for seamlessly combining a set of base deep CNNs (convolutional neural networks) with diverse outputs (task spaces), e.g., such base deep CNNs are trained to recognize…

A thorough comprehension of image content demands a complex grasp of the interactions that may occur in the natural world. One of the key issues is to describe the visual relationships between objects. When dealing with real world data,…

Reference-guided video editing takes a source video, a text instruction, and a reference image as inputs, requiring the model to faithfully apply the instructed edits while preserving original motion and unedited content. Existing methods…

Single-view reference-to-video methods often struggle to preserve identity consistency under large facial-angle variations. This limitation naturally motivates the incorporation of multi-view facial references. However, simply introducing…

The sparsely activated mixture of experts (MoE) model presents a promising alternative to traditional densely activated (dense) models, enhancing both quality and computational efficiency. However, training MoE models from scratch demands…

Dense Retrieval Models (DRMs) are a prominent development in Information Retrieval (IR). A key challenge with these neural Transformer-based models is that they often struggle to generalize beyond the specific tasks and domains they were…

Reinforcement learning (RL) has equipped LLM agents with a strong ability to solve complex tasks. However, existing RL methods normally use a \emph{single} policy network, causing \emph{simplicity bias} where simple tasks occupy most…

Recent advancements in Multimodal Large Language Models (MLLMs) underscore the significance of scalable models and data to boost performance, yet this often incurs substantial computational costs. Although the Mixture of Experts (MoE)…

Mixture-of-Experts (MoE) large language models (LLM) have memory requirements that often exceed the GPU memory capacity, requiring costly parameter movement from secondary memories to the GPU for expert computation. In this work, we present…

People can easily imagine the potential sound while seeing an event. This natural synchronization between audio and visual signals reveals their intrinsic correlations. To this end, we propose to learn the audio-visual correlations from the…