Beyond Filtering: Adaptive Image-Text Quality Enhancement for MLLM Pretraining

Multimodal large language models (MLLMs) have made significant strides by integrating visual and textual modalities. A critical factor in training MLLMs is the quality of image-text pairs within multimodal pretraining datasets. However, $\textit {de facto}$ filter-based data quality enhancement paradigms often discard a substantial portion of high-quality image data due to inadequate semantic alignment between images and texts, leading to inefficiencies in data utilization and scalability. In this paper, we propose the Adaptive Image-Text Quality Enhancer (AITQE), a model that dynamically assesses and enhances the quality of image-text pairs. AITQE employs a text rewriting mechanism for low-quality pairs and incorporates a negative sample learning strategy to improve evaluative capabilities by integrating deliberately selected low-quality samples during training. Unlike prior approaches that significantly alter text distributions, our method minimally adjusts text to preserve data volume while enhancing quality. Experimental results demonstrate that AITQE surpasses existing methods on various benchmark, effectively leveraging raw data and scaling efficiently with increasing data volumes. We hope our work will inspire future works. The code and model are available at: https://github.com/hanhuang22/AITQE.

Exploring the Design Space of Visual Context Representation in Video MLLMs

Video Multimodal Large Language Models (MLLMs) have shown remarkable capability of understanding the video semantics on various downstream tasks. Despite the advancements, there is still a lack of systematic research on visual context representation, which refers to the scheme to select frames from a video and further select the tokens from a frame. In this paper, we explore the design space for visual context representation, and aim to improve the performance of video MLLMs by finding more effective representation schemes. Firstly, we formulate the task of visual context representation as a constrained optimization problem, and model the language modeling loss as a function of the number of frames and the number of embeddings (or tokens) per frame, given the maximum visual context window size. Then, we explore the scaling effects in frame selection and token selection respectively, and fit the corresponding function curve by conducting extensive empirical experiments. We examine the effectiveness of typical selection strategies and present empirical findings to determine the two factors. Furthermore, we study the joint effect of frame selection and token selection, and derive the optimal formula for determining the two factors. We demonstrate that the derived optimal settings show alignment with the best-performed results of empirical experiments. Our code and model are available at: https://github.com/RUCAIBox/Opt-Visor.

Baichuan-Omni Technical Report

The salient multimodal capabilities and interactive experience of GPT-4o highlight its critical role in practical applications, yet it lacks a high-performing open-source counterpart. In this paper, we introduce Baichuan-Omni, the first open-source 7B Multimodal Large Language Model (MLLM) adept at concurrently processing and analyzing modalities of image, video, audio, and text, while delivering an advanced multimodal interactive experience and strong performance. We propose an effective multimodal training schema starting with 7B model and proceeding through two stages of multimodal alignment and multitask fine-tuning across audio, image, video, and text modal. This approach equips the language model with the ability to handle visual and audio data effectively. Demonstrating strong performance across various omni-modal and multimodal benchmarks, we aim for this contribution to serve as a competitive baseline for the open-source community in advancing multimodal understanding and real-time interaction.

Towards Event-oriented Long Video Understanding

With the rapid development of video Multimodal Large Language Models (MLLMs), numerous benchmarks have been proposed to assess their video understanding capability. However, due to the lack of rich events in the videos, these datasets may suffer from the short-cut bias that the answers can be deduced from a few frames, without the need to watch the entire video. To address this issue, we introduce Event-Bench, an event-oriented long video understanding benchmark built on existing datasets and human annotations. Event-Bench includes six event-related tasks and 2,190 test instances to comprehensively evaluate video event understanding ability. Additionally, we propose Video Instruction Merging~(VIM), a cost-effective method that enhances video MLLMs using merged, event-intensive video instructions, addressing the scarcity of human-annotated, event-intensive data. Extensive experiments show that the best-performing model, GPT-4o, achieves an overall accuracy of 53.33, significantly outperforming the best open-source model by 41.42%. Leveraging an effective instruction synthesis method and an adaptive model architecture, VIM surpasses both state-of-the-art open-source models and GPT-4V on the Event-Bench. All code, data, and models are publicly available at https://github.com/RUCAIBox/Event-Bench.

Needle In A Video Haystack: A Scalable Synthetic Framework for Benchmarking Video MLLMs

Video understanding is a crucial next step for multimodal large language models (MLLMs). To probe specific aspects of video understanding ability, existing video benchmarks typically require careful video selection based on the target capability, along with laborious annotation of query-response pairs to match the specific video content. This process is both challenging and resource-intensive. In this paper, we propose VideoNIAH (Video Needle In A Haystack), a benchmark construction framework through synthetic video generation. VideoNIAH decouples test video content from their query-responses by inserting unrelated image/text 'needles' into original videos. It generates annotations solely from these needles, ensuring diversity in video sources and a variety of query-responses. Additionally, by inserting multiple needles, VideoNIAH rigorously evaluates the temporal understanding capabilities of models. We utilized VideoNIAH to compile a video benchmark VNBench, including tasks such as retrieval, ordering, and counting. VNBench can efficiently evaluate the fine-grained understanding ability and spatio-temporal modeling ability of a video model, while also supporting the long-context evaluation. Additionally, we evaluated recent video-centric multimodal large language models (MLLMs), both open-source and proprietary, providing a comprehensive analysis. We found that although proprietary models have significant advantages over open-source models, all existing video models still perform poorly on long-distance dependency tasks. VideoNIAH is a simple yet highly scalable benchmark construction framework, and we believe it will inspire future video benchmark works. The code and data are available at https://github.com/joez17/VideoNIAH.

VDT: An Empirical Study on Video Diffusion with Transformers

This work introduces Video Diffusion Transformer (VDT), which pioneers the use of transformers in diffusion-based video generation. It features transformer blocks with modularized temporal and spatial attention modules, allowing separate optimization of each component and leveraging the rich spatial-temporal representation inherited from transformers. VDT offers several appealing benefits. 1) It excels at capturing temporal dependencies to produce temporally consistent video frames and even simulate the dynamics of 3D objects over time. 2) It enables flexible conditioning information through simple concatenation in the token space, effectively unifying video generation and prediction tasks. 3) Its modularized design facilitates a spatial-temporal decoupled training strategy, leading to improved efficiency. Extensive experiments on video generation, prediction, and dynamics modeling (i.e., physics-based QA) tasks have been conducted to demonstrate the effectiveness of VDT in various scenarios, including autonomous driving, human action, and physics-based simulation. We hope our study on the capabilities of transformer-based video diffusion in capturing accurate temporal dependencies, handling conditioning information, and achieving efficient training will benefit future research and advance the field. Codes and models are available at https://github.com/RERV/VDT.

UniAdapter: Unified Parameter-Efficient Transfer Learning for Cross-modal Modeling

Large-scale vision-language pre-trained models have shown promising transferability to various downstream tasks. As the size of these foundation models and the number of downstream tasks grow, the standard full fine-tuning paradigm becomes unsustainable due to heavy computational and storage costs. This paper proposes UniAdapter, which unifies unimodal and multimodal adapters for parameter-efficient cross-modal adaptation on pre-trained vision-language models. Specifically, adapters are distributed to different modalities and their interactions, with the total number of tunable parameters reduced by partial weight sharing. The unified and knowledge-sharing design enables powerful cross-modal representations that can benefit various downstream tasks, requiring only 1.0%-2.0% tunable parameters of the pre-trained model. Extensive experiments on 6 cross-modal downstream benchmarks (including video-text retrieval, image-text retrieval, VideoQA, and VQA) show that in most cases, UniAdapter not only outperforms the state-of-the-arts, but even beats the full fine-tuning strategy. Particularly, on the MSRVTT retrieval task, UniAdapter achieves 49.7% recall@1 with 2.2% model parameters, outperforming the latest competitors by 2.0%. The code and models are available at https://github.com/RERV/UniAdapter.

LGDN: Language-Guided Denoising Network for Video-Language Modeling

Video-language modeling has attracted much attention with the rapid growth of web videos. Most existing methods assume that the video frames and text description are semantically correlated, and focus on video-language modeling at video level. However, this hypothesis often fails for two reasons: (1) With the rich semantics of video contents, it is difficult to cover all frames with a single video-level description; (2) A raw video typically has noisy/meaningless information (e.g., scenery shot, transition or teaser). Although a number of recent works deploy attention mechanism to alleviate this problem, the irrelevant/noisy information still makes it very difficult to address. To overcome such challenge, we thus propose an efficient and effective model, termed Language-Guided Denoising Network (LGDN), for video-language modeling. Different from most existing methods that utilize all extracted video frames, LGDN dynamically filters out the misaligned or redundant frames under the language supervision and obtains only 2--4 salient frames per video for cross-modal token-level alignment. Extensive experiments on five public datasets show that our LGDN outperforms the state-of-the-arts by large margins. We also provide detailed ablation study to reveal the critical importance of solving the noise issue, in hope of inspiring future video-language work.

COTS: Collaborative Two-Stream Vision-Language Pre-Training Model for Cross-Modal Retrieval

Large-scale single-stream pre-training has shown dramatic performance in image-text retrieval. Regrettably, it faces low inference efficiency due to heavy attention layers. Recently, two-stream methods like CLIP and ALIGN with high inference efficiency have also shown promising performance, however, they only consider instance-level alignment between the two streams (thus there is still room for improvement). To overcome these limitations, we propose a novel COllaborative Two-Stream vision-language pretraining model termed COTS for image-text retrieval by enhancing cross-modal interaction. In addition to instance level alignment via momentum contrastive learning, we leverage two extra levels of cross-modal interactions in our COTS: (1) Token-level interaction - a masked visionlanguage modeling (MVLM) learning objective is devised without using a cross-stream network module, where variational autoencoder is imposed on the visual encoder to generate visual tokens for each image. (2) Task-level interaction - a KL-alignment learning objective is devised between text-to-image and image-to-text retrieval tasks, where the probability distribution per task is computed with the negative queues in momentum contrastive learning. Under a fair comparison setting, our COTS achieves the highest performance among all two-stream methods and comparable performance (but with 10,800X faster in inference) w.r.t. the latest single-stream methods. Importantly, our COTS is also applicable to text-to-video retrieval, yielding new state-ofthe-art on the widely-used MSR-VTT dataset.

WenLan 2.0: Make AI Imagine via a Multimodal Foundation Model

The fundamental goal of artificial intelligence (AI) is to mimic the core cognitive activities of human including perception, memory, and reasoning. Although tremendous success has been achieved in various AI research fields (e.g., computer vision and natural language processing), the majority of existing works only focus on acquiring single cognitive ability (e.g., image classification, reading comprehension, or visual commonsense reasoning). To overcome this limitation and take a solid step to artificial general intelligence (AGI), we develop a novel foundation model pre-trained with huge multimodal (visual and textual) data, which is able to be quickly adapted for a broad class of downstream cognitive tasks. Such a model is fundamentally different from the multimodal foundation models recently proposed in the literature that typically make strong semantic correlation assumption and expect exact alignment between image and text modalities in their pre-training data, which is often hard to satisfy in practice thus limiting their generalization abilities. To resolve this issue, we propose to pre-train our foundation model by self-supervised learning with weak semantic correlation data crawled from the Internet and show that state-of-the-art results can be obtained on a wide range of downstream tasks (both single-modal and cross-modal). Particularly, with novel model-interpretability tools developed in this work, we demonstrate that strong imagination ability (even with hints of commonsense) is now possessed by our foundation model. We believe our work makes a transformative stride towards AGI and will have broad impact on various AI+ fields (e.g., neuroscience and healthcare).