Related papers: LLaVA-c: Continual Improved Visual Instruction Tun…

Continual learning aims to learn knowledge of tasks observed in sequential time steps while mitigating the forgetting of previously learned knowledge. Existing methods were designed to learn a single modality (e.g., image) over time, which…

Recent advances in vision-language models have shown notable generalization in broad tasks through visual instruction tuning. However, bridging the gap between the pre-trained vision encoder and the large language models (LLMs) becomes the…

Large language models (LLMs) demonstrate strong task-specific capabilities through fine-tuning, but merging multiple fine-tuned models often leads to degraded performance due to overlapping instruction-following components. Task Arithmetic…

Foundational Vision-Language Models (VLMs) excel across diverse tasks, but adapting them to new domains without forgetting prior knowledge remains a critical challenge. Continual Learning (CL) addresses this challenge by enabling models to…

When deployed in open-ended robotic environments, Vision--Language--Action (VLA) models need to continually acquire new skills, yet suffer from severe catastrophic forgetting. We observe that this degradation is related to the deterioration…

Parameter-efficient continual learning aims to adapt pre-trained models to sequential tasks without forgetting previously acquired knowledge. Most existing approaches treat continual learning as avoiding interference with past updates,…

Intelligent agents should have the ability to leverage knowledge from previously learned tasks in order to learn new ones quickly and efficiently. Meta-learning approaches have emerged as a popular solution to achieve this. However,…

In this work, we introduce LLaDA-V, a purely diffusion-based Multimodal Large Language Model (MLLM) that integrates visual instruction tuning with masked diffusion models, representing a departure from the autoregressive paradigms dominant…

Continual learning (CL) studies how models acquire tasks sequentially while retaining previously learned knowledge. Despite substantial progress in benchmarking CL methods, comparative evaluations typically keep the fine-tuning regime…

Diverse instruction data is vital for effective instruction tuning of large language models, as it enables the model to generalize across different types of inputs . Building such diversified instruction dataset is an essential step in this…

The size and the computational load of fine-tuning large-scale pre-trained neural network are becoming two major obstacles in adopting machine learning in many applications. Continual learning (CL) can serve as a remedy through enabling…

We introduce SlowFast-LLaVA-1.5 (abbreviated as SF-LLaVA-1.5), a family of video large language models (LLMs) offering a token-efficient solution for long-form video understanding. We incorporate the two-stream SlowFast mechanism into a…

Recent advances in Multi-modal Large Language Models (MLLMs), such as LLaVA-series models, are driven by massive machine-generated instruction-following data tuning. Such automatic instruction collection pipelines, however, inadvertently…

Vision-Language (VL) pre-trained models have shown their superiority on many multimodal tasks. However, the adversarial robustness of such models has not been fully explored. Existing approaches mainly focus on exploring the adversarial…

Visual encoding constitutes the basis of large multimodal models (LMMs) in understanding the visual world. Conventional LMMs process images in fixed sizes and limited resolutions, while recent explorations in this direction are limited in…

Continual (sequential) training and multitask (simultaneous) training are often attempting to solve the same overall objective: to find a solution that performs well on all considered tasks. The main difference is in the training regimes,…

Humans can continuously learn new knowledge as their experience grows. In contrast, previous learning in deep neural networks can quickly fade out when they are trained on a new task. In this paper, we hypothesize this problem can be…

Vision-language pre-training has significantly elevated performance across a wide range of image-language applications. Yet, the pre-training process for video-related tasks demands exceptionally large computational and data resources,…

Instruction tuning of language models has demonstrated the ability to enhance model generalization to unseen tasks via in-context learning using a few examples. However, typical supervised learning still requires a plethora of downstream…

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…