Related papers: Chart2Code-MoLA: Efficient Multi-Modal Code Genera…

Enabling large-scale generative models to continuously learn new visual concepts is essential for personalizing pre-trained models to meet individual user preferences. Existing approaches for continual visual concept learning are…

Continual learning (CL), which requires the model to learn multiple tasks sequentially, is crucial for large language models (LLMs). Recently, low-rank adaptation~(LoRA), one of the most representative parameter-efficient fine-tuning (PEFT)…

Generative AI has made rapid advancements in recent years, achieving unprecedented capabilities in multimodal understanding and code generation. This can enable a new paradigm of front-end development in which multimodal large language…

Solving complex chart Q&A tasks requires advanced visual reasoning abilities in multimodal large language models (MLLMs), including recognizing key information from visual inputs and conducting reasoning over it. While fine-tuning MLLMs for…

Training a unified model to take multiple targets into account is a trend towards artificial general intelligence. However, how to efficiently mitigate the training conflicts among heterogeneous data collected from different domains or…

Mixture of Experts (MoE) architectures increase large language model scalability, yet their performance depends on the router module that moves tokens to specialized experts. Bad routing can load imbalance and reduced accuracy. This project…

The scaling law of Large Language Models (LLMs) reveals a power-law relationship, showing diminishing return on performance as model scale increases. While training LLMs from scratch is resource-intensive, fine-tuning a pre-trained model…

Mixture-of-Experts (MoE) has emerged as a promising approach to scale up deep learning models due to its significant reduction in computational resources. However, the dynamic nature of MoE leads to load imbalance among experts, severely…

Domain-specific adaptation is critical to maximizing the performance of pre-trained language models (PLMs) on one or multiple targeted tasks, especially under resource-constrained use cases, such as edge devices. However, existing methods…

Due to the inherent difficulty in modeling phonetic similarities across different languages, code-switching speech recognition presents a formidable challenge. This study proposes a Collaborative-MoE, a Mixture of Experts (MoE) model that…

Chart question answering (ChartQA) is challenged by the heterogeneous composition of chart elements and the subtle data patterns they encode. This work introduces a novel joint multimodal scene graph framework that explicitly models the…

Large Language Models (LLMs) demonstrate exceptional performance across various tasks but demand substantial computational resources even for fine-tuning computation. Although Low-Rank Adaptation (LoRA) significantly alleviates memory…

Large Language Models (LLMs) have achieved impressive results across various tasks, yet their high computational demands pose deployment challenges, especially on consumer-grade hardware. Mixture of Experts (MoE) models provide an efficient…

Multi-Task Learning (MTL) for Vision Transformer aims at enhancing the model capability by tackling multiple tasks simultaneously. Most recent works have predominantly focused on designing Mixture-of-Experts (MoE) structures and in…

Robust multimodal visual analytics remains challenging when heterogeneous modalities provide complementary but input-dependent evidence for decision-making.Existing multimodal learning methods mainly rely on fixed fusion modules or…

We introduce MoMa, a novel modality-aware mixture-of-experts (MoE) architecture designed for pre-training mixed-modal, early-fusion language models. MoMa processes images and text in arbitrary sequences by dividing expert modules into…

In this work, we undertake the challenge of augmenting the existing generative capabilities of pre-trained text-only large language models (LLMs) with multi-modal generation capability while satisfying two core constraints: C1 preserving…

Low-Rank Adaptation (LoRA) has gained prominence as a computationally efficient method for fine-tuning generative models, enabling distinct visual concept synthesis with minimal overhead. However, current methods struggle to effectively…

Pre-trained language models (PLMs) demonstrate remarkable intelligence but struggle with emerging tasks unseen during training in real-world applications. Training separate models for each new task is usually impractical. Multi-task…

Multilingual speech recognition for both monolingual and code-switching speech is a challenging task. Recently, based on the Mixture of Experts (MoE), many works have made good progress in multilingual and code-switching ASR, but present…