Are We on the Right Way for Evaluating Large Vision-Language Models?

Large vision-language models (LVLMs) have recently achieved rapid progress, sparking numerous studies to evaluate their multi-modal capabilities. However, we dig into current evaluation works and identify two primary issues: 1) Visual content is unnecessary for many samples. The answers can be directly inferred from the questions and options, or the world knowledge embedded in LLMs. This phenomenon is prevalent across current benchmarks. For instance, GeminiPro achieves 42.9% on the MMMU benchmark without any visual input, and outperforms the random choice baseline across six benchmarks over 24% on average. 2) Unintentional data leakage exists in LLM and LVLM training. LLM and LVLM could still answer some visual-necessary questions without visual content, indicating the memorizing of these samples within large-scale training data. For example, Sphinx-X-MoE gets 43.6% on MMMU without accessing images, surpassing its LLM backbone with 17.9%. Both problems lead to misjudgments of actual multi-modal gains and potentially misguide the study of LVLM. To this end, we present MMStar, an elite vision-indispensable multi-modal benchmark comprising 1,500 samples meticulously selected by humans. MMStar benchmarks 6 core capabilities and 18 detailed axes, aiming to evaluate LVLMs' multi-modal capacities with carefully balanced and purified samples. These samples are first roughly selected from current benchmarks with an automated pipeline, human review is then involved to ensure each curated sample exhibits visual dependency, minimal data leakage, and requires advanced multi-modal capabilities. Moreover, two metrics are developed to measure data leakage and actual performance gain in multi-modal training. We evaluate 16 leading LVLMs on MMStar to assess their multi-modal capabilities, and on 7 benchmarks with the proposed metrics to investigate their data leakage and actual multi-modal gain.

SA$^2$VP: Spatially Aligned-and-Adapted Visual Prompt

As a prominent parameter-efficient fine-tuning technique in NLP, prompt tuning is being explored its potential in computer vision. Typical methods for visual prompt tuning follow the sequential modeling paradigm stemming from NLP, which represents an input image as a flattened sequence of token embeddings and then learns a set of unordered parameterized tokens prefixed to the sequence representation as the visual prompts for task adaptation of large vision models. While such sequential modeling paradigm of visual prompt has shown great promise, there are two potential limitations. First, the learned visual prompts cannot model the underlying spatial relations in the input image, which is crucial for image encoding. Second, since all prompt tokens play the same role of prompting for all image tokens without distinction, it lacks the fine-grained prompting capability, i.e., individual prompting for different image tokens. In this work, we propose the \mymodel model (\emph{SA$^2$VP}), which learns a two-dimensional prompt token map with equal (or scaled) size to the image token map, thereby being able to spatially align with the image map. Each prompt token is designated to prompt knowledge only for the spatially corresponding image tokens. As a result, our model can conduct individual prompting for different image tokens in a fine-grained manner. Moreover, benefiting from the capability of preserving the spatial structure by the learned prompt token map, our \emph{SA$^2$VP} is able to model the spatial relations in the input image, leading to more effective prompting. Extensive experiments on three challenging benchmarks for image classification demonstrate the superiority of our model over other state-of-the-art methods for visual prompt tuning. Code is available at \emph{https://github.com/tommy-xq/SA2VP}.

ShareGPT4V: Improving Large Multi-Modal Models with Better Captions

In the realm of large multi-modal models (LMMs), efficient modality alignment is crucial yet often constrained by the scarcity of high-quality image-text data. To address this bottleneck, we introduce the ShareGPT4V dataset, a pioneering large-scale resource featuring 1.2 million highly descriptive captions, which surpasses existing datasets in diversity and information content, covering world knowledge, object properties, spatial relationships, and aesthetic evaluations. Specifically, ShareGPT4V originates from a curated 100K high-quality captions collected from advanced GPT4-Vision and has been expanded to 1.2M with a superb caption model trained on this subset. ShareGPT4V first demonstrates its effectiveness for the Supervised Fine-Tuning (SFT) phase, by substituting an equivalent quantity of detailed captions in existing SFT datasets with a subset of our high-quality captions, significantly enhancing the LMMs like LLaVA-7B, LLaVA-1.5-13B, and Qwen-VL-Chat-7B on the MME and MMBench benchmarks, with respective gains of 222.8/22.0/22.3 and 2.7/1.3/1.5. We further incorporate ShareGPT4V data into both the pre-training and SFT phases, obtaining ShareGPT4V-7B, a superior LMM based on a simple architecture that has remarkable performance across a majority of the multi-modal benchmarks. This project is available at https://ShareGPT4V.github.io to serve as a pivotal resource for advancing the LMMs community.

Lightweight Neural Path Planning

Learning-based path planning is becoming a promising robot navigation methodology due to its adaptability to various environments. However, the expensive computing and storage associated with networks impose significant challenges for their deployment on low-cost robots. Motivated by this practical challenge, we develop a lightweight neural path planning architecture with a dual input network and a hybrid sampler for resource-constrained robotic systems. Our architecture is designed with efficient task feature extraction and fusion modules to translate the given planning instance into a guidance map. The hybrid sampler is then applied to restrict the planning within the prospective regions indicated by the guide map. To enable the network training, we further construct a publicly available dataset with various successful planning instances. Numerical simulations and physical experiments demonstrate that, compared with baseline approaches, our approach has nearly an order of magnitude fewer model size and five times lower computational while achieving promising performance. Besides, our approach can also accelerate the planning convergence process with fewer planning iterations compared to sample-based methods.

TSAM: Temporal Link Prediction in Directed Networks based on Self-Attention Mechanism

The development of graph neural networks (GCN) makes it possible to learn structural features from evolving complex networks. Even though a wide range of realistic networks are directed ones, few existing works investigated the properties of directed and temporal networks. In this paper, we address the problem of temporal link prediction in directed networks and propose a deep learning model based on GCN and self-attention mechanism, namely TSAM. The proposed model adopts an autoencoder architecture, which utilizes graph attentional layers to capture the structural feature of neighborhood nodes, as well as a set of graph convolutional layers to capture motif features. A graph recurrent unit layer with self-attention is utilized to learn temporal variations in the snapshot sequence. We run comparative experiments on four realistic networks to validate the effectiveness of TSAM. Experimental results show that TSAM outperforms most benchmarks under two evaluation metrics.