MM1.5: Methods, Analysis & Insights from Multimodal LLM Fine-tuning

We present MM1.5, a new family of multimodal large language models (MLLMs) designed to enhance capabilities in text-rich image understanding, visual referring and grounding, and multi-image reasoning. Building upon the MM1 architecture, MM1.5 adopts a data-centric approach to model training, systematically exploring the impact of diverse data mixtures across the entire model training lifecycle. This includes high-quality OCR data and synthetic captions for continual pre-training, as well as an optimized visual instruction-tuning data mixture for supervised fine-tuning. Our models range from 1B to 30B parameters, encompassing both dense and mixture-of-experts (MoE) variants, and demonstrate that careful data curation and training strategies can yield strong performance even at small scales (1B and 3B). Additionally, we introduce two specialized variants: MM1.5-Video, designed for video understanding, and MM1.5-UI, tailored for mobile UI understanding. Through extensive empirical studies and ablations, we provide detailed insights into the training processes and decisions that inform our final designs, offering valuable guidance for future research in MLLM development.

SlowFast-LLaVA: A Strong Training-Free Baseline for Video Large Language Models

We propose SlowFast-LLaVA (or SF-LLaVA for short), a training-free video large language model (LLM) that can jointly capture the detailed spatial semantics and long-range temporal context without exceeding the token budget of commonly used LLMs. This is realized by using a two-stream SlowFast design of inputs for Video LLMs to aggregate features from sampled video frames in an effective way. Specifically, the Slow pathway extracts features at a low frame rate while keeping as many spatial details as possible (e.g., with 24x24 tokens), and the Fast pathway operates on a high frame rate but uses a larger spatial pooling stride (e.g., downsampling 6x) to focus on the motion cues. As a result, this design allows us to adequately capture both spatial and temporal features that are beneficial for understanding details along the video. Experimental results show that SF-LLaVA outperforms existing training-free methods on a wide range of video tasks. On some benchmarks, it achieves comparable or even better performance compared to state-of-the-art Video LLMs that are fine-tuned on video datasets.

4M-21: An Any-to-Any Vision Model for Tens of Tasks and Modalities

Current multimodal and multitask foundation models like 4M or UnifiedIO show promising results, but in practice their out-of-the-box abilities to accept diverse inputs and perform diverse tasks are limited by the (usually rather small) number of modalities and tasks they are trained on. In this paper, we expand upon the capabilities of them by training a single model on tens of highly diverse modalities and by performing co-training on large-scale multimodal datasets and text corpora. This includes training on several semantic and geometric modalities, feature maps from recent state of the art models like DINOv2 and ImageBind, pseudo labels of specialist models like SAM and 4DHumans, and a range of new modalities that allow for novel ways to interact with the model and steer the generation, for example image metadata or color palettes. A crucial step in this process is performing discrete tokenization on various modalities, whether they are image-like, neural network feature maps, vectors, structured data like instance segmentation or human poses, or data that can be represented as text. Through this, we expand on the out-of-the-box capabilities of multimodal models and specifically show the possibility of training one model to solve at least 3x more tasks/modalities than existing ones and doing so without a loss in performance. This enables more fine-grained and controllable multimodal generation capabilities and allows us to study the distillation of models trained on diverse data and objectives into a unified model. We successfully scale the training to a three billion parameter model using tens of modalities and different datasets. The resulting models and training code are open sourced at 4m.epfl.ch.

4M: Massively Multimodal Masked Modeling

Current machine learning models for vision are often highly specialized and limited to a single modality and task. In contrast, recent large language models exhibit a wide range of capabilities, hinting at a possibility for similarly versatile models in computer vision. In this paper, we take a step in this direction and propose a multimodal training scheme called 4M. It consists of training a single unified Transformer encoder-decoder using a masked modeling objective across a wide range of input/output modalities - including text, images, geometric, and semantic modalities, as well as neural network feature maps. 4M achieves scalability by unifying the representation space of all modalities through mapping them into discrete tokens and performing multimodal masked modeling on a small randomized subset of tokens. 4M leads to models that exhibit several key capabilities: (1) they can perform a diverse set of vision tasks out of the box, (2) they excel when fine-tuned for unseen downstream tasks or new input modalities, and (3) they can function as a generative model that can be conditioned on arbitrary modalities, enabling a wide variety of expressive multimodal editing capabilities with remarkable flexibility. Through experimental analyses, we demonstrate the potential of 4M for training versatile and scalable foundation models for vision tasks, setting the stage for further exploration in multimodal learning for vision and other domains.

Mask-free OVIS: Open-Vocabulary Instance Segmentation without Manual Mask Annotations

Existing instance segmentation models learn task-specific information using manual mask annotations from base (training) categories. These mask annotations require tremendous human effort, limiting the scalability to annotate novel (new) categories. To alleviate this problem, Open-Vocabulary (OV) methods leverage large-scale image-caption pairs and vision-language models to learn novel categories. In summary, an OV method learns task-specific information using strong supervision from base annotations and novel category information using weak supervision from image-captions pairs. This difference between strong and weak supervision leads to overfitting on base categories, resulting in poor generalization towards novel categories. In this work, we overcome this issue by learning both base and novel categories from pseudo-mask annotations generated by the vision-language model in a weakly supervised manner using our proposed Mask-free OVIS pipeline. Our method automatically generates pseudo-mask annotations by leveraging the localization ability of a pre-trained vision-language model for objects present in image-caption pairs. The generated pseudo-mask annotations are then used to supervise an instance segmentation model, freeing the entire pipeline from any labour-expensive instance-level annotations and overfitting. Our extensive experiments show that our method trained with just pseudo-masks significantly improves the mAP scores on the MS-COCO dataset and OpenImages dataset compared to the recent state-of-the-art methods trained with manual masks. Codes and models are provided in https://vibashan.github.io/ovis-web/.

ULIP: Learning Unified Representation of Language, Image and Point Cloud for 3D Understanding

The understanding capabilities of current state-of-the-art 3D models are limited by datasets with a small number of annotated data and a pre-defined set of categories. In its 2D counterpart, recent advances have shown that similar problems can be significantly alleviated by employing knowledge from other modalities, such as language. Inspired by this, leveraging multimodal information for 3D modality could be promising to improve 3D understanding under the restricted data regime, but this line of research is not well studied. Therefore, we introduce ULIP to learn a unified representation of image, text, and 3D point cloud by pre-training with object triplets from the three modalities. To overcome the shortage of training triplets, ULIP leverages a pre-trained vision-language model that has already learned a common visual and textual space by training with massive image-text pairs. Then, ULIP learns a 3D representation space aligned with the common image-text space, using a small number of automatically synthesized triplets. ULIP is agnostic to 3D backbone networks and can easily be integrated into any 3D architecture. Experiments show that ULIP effectively improves the performance of multiple recent 3D backbones by simply pre-training them on ShapeNet55 using our framework, achieving state-of-the-art performance in both standard 3D classification and zero-shot 3D classification on ModelNet40 and ScanObjectNN. ULIP also improves the performance of PointMLP by around 3% in 3D classification on ScanObjectNN, and outperforms PointCLIP by 28.8% on top-1 accuracy for zero-shot 3D classification on ModelNet40. Our code and pre-trained models will be released.

TAG: Boosting Text-VQA via Text-aware Visual Question-answer Generation

Text-VQA aims at answering questions that require understanding the textual cues in an image. Despite the great progress of existing Text-VQA methods, their performance suffers from insufficient human-labeled question-answer (QA) pairs. However, we observe that, in general, the scene text is not fully exploited in the existing datasets -- only a small portion of text in each image participates in the annotated QA activities. This results in a huge waste of useful information. To address this deficiency, we develop a new method to generate high-quality and diverse QA pairs by explicitly utilizing the existing rich text available in the scene context of each image. Specifically, we propose, TAG, a text-aware visual question-answer generation architecture that learns to produce meaningful, and accurate QA samples using a multimodal transformer. The architecture exploits underexplored scene text information and enhances scene understanding of Text-VQA models by combining the generated QA pairs with the initial training data. Extensive experimental results on two well-known Text-VQA benchmarks (TextVQA and ST-VQA) demonstrate that our proposed TAG effectively enlarges the training data that helps improve the Text-VQA performance without extra labeling effort. Moreover, our model outperforms state-of-the-art approaches that are pre-trained with extra large-scale data. Code is available at https://github.com/HenryJunW/TAG.

Value Retrieval with Arbitrary Queries for Form-like Documents

We propose value retrieval with arbitrary queries for form-like documents to reduce human effort of processing forms. Unlike previous methods that only address a fixed set of field items, our method predicts target value for an arbitrary query based on the understanding of layout and semantics of a form. To further boost model performance, we propose a simple document language modeling (simpleDLM) strategy to improve document understanding on large-scale model pre-training. Experimental results show that our method outperforms our baselines significantly and the simpleDLM further improves our performance on value retrieval by around 17\% F1 score compared with the state-of-the-art pre-training method. Code will be made publicly available.

Burn After Reading: Online Adaptation for Cross-domain Streaming Data

In the context of online privacy, many methods propose complex privacy and security preserving measures to protect sensitive data. In this paper, we argue that: not storing any sensitive data is the best form of security. Thus we propose an online framework that "burns after reading", i.e. each online sample is immediately deleted after it is processed. Meanwhile, we tackle the inevitable distribution shift between the labeled public data and unlabeled private data as a problem of unsupervised domain adaptation. Specifically, we propose a novel algorithm that aims at the most fundamental challenge of the online adaptation setting--the lack of diverse source-target data pairs. Therefore, we design a Cross-Domain Bootstrapping approach, called CroDoBo, to increase the combined diversity across domains. Further, to fully exploit the valuable discrepancies among the diverse combinations, we employ the training strategy of multiple learners with co-supervision. CroDoBo achieves state-of-the-art online performance on four domain adaptation benchmarks.

Towards Open Vocabulary Object Detection without Human-provided Bounding Boxes

Despite great progress in object detection, most existing methods are limited to a small set of object categories, due to the tremendous human effort needed for instance-level bounding-box annotation. To alleviate the problem, recent open vocabulary and zero-shot detection methods attempt to detect object categories not seen during training. However, these approaches still rely on manually provided bounding-box annotations on a set of base classes. We propose an open vocabulary detection framework that can be trained without manually provided bounding-box annotations. Our method achieves this by leveraging the localization ability of pre-trained vision-language models and generating pseudo bounding-box labels that can be used directly for training object detectors. Experimental results on COCO, PASCAL VOC, Objects365 and LVIS demonstrate the effectiveness of our method. Specifically, our method outperforms the state-of-the-arts (SOTA) that are trained using human annotated bounding-boxes by 3% AP on COCO novel categories even though our training source is not equipped with manual bounding-box labels. When utilizing the manual bounding-box labels as our baselines do, our method surpasses the SOTA largely by 8% AP.