This paper introduces MM-Instruct, a large-scale dataset of diverse and high-quality visual instruction data designed to enhance the instruction-following capabilities of large multimodal models (LMMs). While existing visual instruction datasets often focus on question-answering, they struggle to generalize to broader application scenarios such as creative writing, summarization, or image analysis. To address these limitations, we propose a novel approach to constructing MM-Instruct that leverages the strong instruction-following capabilities of existing LLMs to generate novel visual instruction data from large-scale but conventional image captioning datasets. MM-Instruct first leverages ChatGPT to automatically generate diverse instructions from a small set of seed instructions through augmenting and summarization. It then matches these instructions with images and uses an open-sourced large language model (LLM) to generate coherent answers to the instruction-image pairs. The LLM is grounded by the detailed text descriptions of images in the whole answer generation process to guarantee the alignment of the instruction data. Moreover, we introduce a benchmark based on the generated instruction data to evaluate the instruction-following capabilities of existing LMMs. We demonstrate the effectiveness of MM-Instruct by training a LLaVA-1.5 model on the generated data, denoted as LLaVA-Instruct, which exhibits significant improvements in instruction-following capabilities compared to LLaVA-1.5 models.

Spiking Neural Networks (SNNs) have gained considerable attention due to the energy-efficient and multiplication-free characteristics. The continuous growth in scale of deep SNNs poses challenges for model deployment. Network pruning reduces hardware resource requirements of model deployment by compressing the network scale. However, existing SNN pruning methods cause high pruning costs and performance loss because the pruning iterations amplify the training difficulty of SNNs. In this paper, inspired by the critical brain hypothesis in neuroscience, we propose a regeneration mechanism based on the neuron criticality for SNN pruning to enhance feature extraction and accelerate the pruning process. Firstly, we propose a low-cost metric for the criticality in SNNs. Then, we re-rank the pruned structures after pruning and regenerate those with higher criticality to obtain the critical network. Our method achieves higher performance than the current state-of-the-art (SOTA) method with up to 95.26% reduction of pruning cost. Moreover, we investigate the underlying mechanism of our method and find that it efficiently selects potential structures and learns the consistent feature representation.

Multi-view camera-based 3D detection is a challenging problem in computer vision. Recent works leverage a pretrained LiDAR detection model to transfer knowledge to a camera-based student network. However, we argue that there is a major domain gap between the LiDAR BEV features and the camera-based BEV features, as they have different characteristics and are derived from different sources. In this paper, we propose Geometry Enhanced Masked Image Modeling (GeoMIM) to transfer the knowledge of the LiDAR model in a pretrain-finetune paradigm for improving the multi-view camera-based 3D detection. GeoMIM is a multi-camera vision transformer with Cross-View Attention (CVA) blocks that uses LiDAR BEV features encoded by the pretrained BEV model as learning targets. During pretraining, GeoMIM's decoder has a semantic branch completing dense perspective-view features and the other geometry branch reconstructing dense perspective-view depth maps. The depth branch is designed to be camera-aware by inputting the camera's parameters for better transfer capability. Extensive results demonstrate that GeoMIM outperforms existing methods on nuScenes benchmark, achieving state-of-the-art performance for camera-based 3D object detection and 3D segmentation. Code and pretrained models are available at https://github.com/Sense-X/GeoMIM.

Reinforcement learning (RL)-based neural architecture search (NAS) generally guarantees better convergence yet suffers from the requirement of huge computational resources compared with gradient-based approaches, due to the rollout bottleneck - exhaustive training of each sampled architecture on the proxy tasks. In this paper, we propose a general pipeline to accelerate the convergence of the rollout process as well as the RL process in NAS. It is motivated by the interesting observation that both the architecture and the parameter knowledge can be transferred between different search processes and even different tasks. We first introduce an uncertainty-aware critic (value function) in Proximal Policy Optimization (PPO) [27] to take advantage of the architecture knowledge in previous search processes, which stabilizes the training process and reduce the searching time by 4 times. In addition, an architecture knowledge pool together with a block similarity function is proposed to utilize parameter knowledge and reduces the searching time by 2 times. To the best of our knowledge, this is the first method that introduces a block-level weight sharing scheme in RL-based NAS. The block similarity function guarantees a 100% hit ratio with strict fairness [5]. Besides, we show that an off-policy correction factor used in "replay buffer" of RL optimization can further reduce half of the searching time. Experiments on the Mobile Neural Architecture Search (MNAS) [30] search space show that the proposed Fast Neural Architecture Search (FNAS) accelerates the standard RL-based NAS process by 10x (e.g., 20,000 GPU hours to 2,000 GPU hours for MNAS), and guarantees better performance on various vision tasks.