Humans possess the visual-spatial intelligence to remember spaces from sequential visual observations. However, can Multimodal Large Language Models (MLLMs) trained on million-scale video datasets also "think in space" from videos? We present a novel video-based visual-spatial intelligence benchmark (VSI-Bench) of over 5,000 question-answer pairs, and find that MLLMs exhibit competitive—though subhuman—visual-spatial intelligence. We probe models to express how they think in space both linguistically and visually and find that while spatial reasoning capabilities remain the primary bottleneck for MLLMs to reach higher benchmark performance, local world models and spatial awareness do emerge within these models. Notably, prevailing linguistic reasoning techniques (e.g., chain-of-thought, self-consistency, tree-of-thoughts) fail to improve performance, whereas explicitly generating cognitive maps during question-answering enhances MLLMs’ spatial distance ability.

Video instance segmentation on mobile devices is an important yet very challenging edge AI problem. It mainly suffers from (1) heavy computation and memory costs for frame-by-frame pixel-level instance perception and (2) complicated heuristics for tracking objects. To address these issues, we present MobileInst, a lightweight and mobile-friendly framework for video instance segmentation on mobile devices. Firstly, MobileInst adopts a mobile vision transformer to extract multi-level semantic features and presents an efficient query-based dual-transformer instance decoder for mask kernels and a semantic-enhanced mask decoder to generate instance segmentation per frame. Secondly, MobileInst exploits simple yet effective kernel reuse and kernel association to track objects for video instance segmentation. Further, we propose temporal query passing to enhance the tracking ability for kernels. We conduct experiments on COCO and YouTube-VIS datasets to demonstrate the superiority of MobileInst and evaluate the inference latency on one single CPU core of the Snapdragon 778G Mobile Platform, without other methods of acceleration. On the COCO dataset, MobileInst achieves 31.2 mask AP and 433 ms on the mobile CPU, which reduces the latency by 50% compared to the previous SOTA. For video instance segmentation, MobileInst achieves 35.0 AP and 30.1 AP on YouTube-VIS 2019 & 2021.

This study addresses the challenges of assessing and enhancing social-pragmatic inference in large language models (LLMs).We first highlight the inadequacy of current accuracy-based multiple choice question answering (MCQA) formats in assessing socialpragmatic reasoning, and propose the direct evaluation of models' free-form responses as measure, which correlates better with human judgment.Furthermore, we explore methods to improve pragmatic abilities in LLMs, advocating for preference optimization (PO) over supervised finetuning (SFT), given the absence of a definitive "gold" answer in social contexts.Our results show that preferential tuning consistently outperforms SFT across pragmatic phenomena and offers a near-free launch in pragmatic abilities without compromising general capabilities.Lastly, we examine the internal structure of LLMs, revealing that the significant boost in pragmatic reasoning is tied to deeper layer representations, analogous to human highlevel thinking.Our experiments span a variety of pragmatic and social reasoning datasets, as well as an image referential game requiring a multimodal theory of mind (ToM).With our refined paradigms for evaluating and enhancing pragmatic inference, this paper offers key insights into building more socially aware language models.

We introduce Cambrian-1, a family of multimodal LLMs (MLLMs) designed with a vision-centric approach. While stronger language models can enhance multimodal capabilities, the design choices for vision components are often insufficiently explored and disconnected from visual representation learning research. This gap hinders accurate sensory grounding in real-world scenarios. Our study uses LLMs and visual instruction tuning as an interface to evaluate various visual representations, offering new insights into different models and architectures—self-supervised, strongly supervised, or combinations thereof—based on experiments with over 15 vision models. We critically examine existing MLLM benchmarks, addressing the difficulties involved in consolidating and interpreting results from various tasks. To further improve visual grounding, we propose spatial vision aggregator (SVA), a dynamic and spatially-aware connector that integrates vision features with LLMs while reducing the number of tokens. Additionally, we discuss the curation of high-quality visual instruction-tuning data from publicly available sources, emphasizing the importance of distribution balancing. Collectively, Cambrian-1 not only achieves state-of-the-art performances but also serves as a comprehensive, open cookbook for instruction-tuned MLLMs. We provide model weights, code, supporting tools, datasets, and detailed instruction-tuning and evaluation recipes. We hope our release will inspire and accelerate advancements in multimodal systems and visual representation learning.

Both masked image modeling (MIM) and natural language supervision have facilitated the progress of transferable visual pre-training. In this work, we seek the synergy between two paradigms and study the emerging properties when MIM meets natural language supervision. To this end, we present a novel masked visual Reconstruction In Language semantic Space (RILS) pre-training framework, in which sentence representations, encoded by the text encoder, serve as prototypes to transform the vision-only signals into patch-sentence probabilities as semantically meaningful MIM reconstruction targets. The vision models can therefore capture useful components with structured information by predicting proper semantic of masked tokens. Better visual representations could, in turn, improve the text encoder via the image-text alignment objective, which is essential for the effective MIM target transformation. Extensive experimental results demonstrate that our method not only enjoys the best of previous MIM and CLIP but also achieves further improvements on various tasks due to their mutual benefits. RILS exhibits advanced transferability on downstream classification, detection, and segmentation, especially for low-shot regimes. Code is available at https://github.com/hustvl/RILS.

We present an approach to efficiently and effectively adapt a masked image modeling (MIM) pre-trained vanilla Vision Transformer (ViT) for object detection, which is based on our two novel observations: (i) A MIM pre-trained vanilla ViT encoder can work surprisingly well in the challenging object-level recognition scenario even with randomly sampled partial observations, e.g., only 25% ~ 50% of the input embeddings. (ii) In order to construct multi-scale representations for object detection from single-scale ViT, a randomly initialized compact convolutional stem supplants the pre-trained patchify stem, and its intermediate features can naturally serve as the higher resolution inputs of a feature pyramid network without further upsampling or other manipulations. While the pre-trained ViT is only regarded as the 3rd-stage of our detector’s backbone instead of the whole feature extractor. This naturally results in a ConvNet-ViT hybrid architecture. The proposed detector, named MimDet, enables a MIM pre-trained vanilla ViT to outperform leading hierarchical architectures such as Swin Transformer, MViTv2 and ConvNeXt on COCO object detection & instance segmentation, and achieves better results compared with the previous best adapted vanilla ViT detector using a more modest fine-tuning recipe while converging 2.8× faster. Code and pre-trained models are available at https://github.com/hustvl/MIMDet.

Recently vision transformer has achieved tremendous success on image-level visual recognition tasks. To effectively and efficiently model the crucial temporal information within a video clip, we propose a Temporally Efficient Vision Transformer (TeViT) for video instance segmentation (VIS). Different from previous transformer-based VIS methods, TeViT is nearly convolution-free, which contains a transformer backbone and a query-based video instance segmentation head. In the backbone stage, we propose a nearly parameter-free messenger shift mechanism for early temporal context fusion. In the head stages, we propose a parameter-shared spatiotemporal query interaction mechanism to build the one-to-one correspondence between video instances and queries. Thus, TeViT fully utilizes both frame-level and instance-level temporal context information and obtains strong temporal modeling capacity with negligible extra computational cost. On three widely adopted VIS benchmarks, i.e., YouTube-VIS-2019, YouTube-VIS-2021, and OVIS, TeViT obtains state-of-the-art results and maintains high inference speed, e.g., 46.6 AP with 68.9 FPS on YouTube-VIS-2019. Code is available at https://github.com/hustvl/TeViT.

We present QueryInst, a new perspective for instance segmentation. QueryInst is a multi-stage end-to-end system that treats instances of interest as learnable queries, enabling query based object detectors, e.g., Sparse RCNN, to have strong instance segmentation performance. The attributes of instances such as categories, bounding boxes, instance masks, and instance association embeddings are represented by queries in a unified manner. In QueryInst, a query is shared by both detection and segmentation via dynamic convolutions and driven by parallellysupervised multi-stage learning. We conduct extensive experiments on three challenging benchmarks, i.e., COCO, CityScapes, and YouTube-VIS to evaluate the effectiveness of QueryInst in object detection, instance segmentation, and video instance segmentation tasks. For the first time, we demonstrate that a simple end-to-end query based framework can achieve the state-of-the-art performance in various instance-level recognition tasks. Code is available at https://github.com/hustvl/QueryInst.

Modeling temporal visual context across frames is critical for video instance segmentation (VIS) and other video understanding tasks. In this paper, we propose a fast on-line VIS model termed CrossVIS. For temporal information modeling in VIS, we present a novel crossover learning scheme that uses the instance feature in the current frame to pixel-wisely localize the same instance in other frames. Different from previous schemes, crossover learning does not require any additional network parameters for feature enhancement. By integrating with the instance segmentation loss, crossover learning enables efficient cross-frame instance-to-pixel relation learning and brings cost-free improvement during inference. Besides, a global balanced instance embedding branch is proposed for better and more stable online instance association. We conduct extensive experiments on three challenging VIS benchmarks, i.e., YouTube-VIS-2019, OVIS, and YouTube-VIS-2021 to evaluate our methods. CrossVIS achieves state-of-the-art online VIS performance and shows a decent trade-off between latency and accuracy. Code is available at https://github.com/hustvl/CrossVIS.