$γ-$MoD: Exploring Mixture-of-Depth Adaptation for Multimodal Large Language Models

Despite the significant progress in multimodal large language models (MLLMs), their high computational cost remains a barrier to real-world deployment. Inspired by the mixture of depths (MoDs) in natural language processing, we aim to address this limitation from the perspective of ``activated tokens''. Our key insight is that if most tokens are redundant for the layer computation, then can be skipped directly via the MoD layer. However, directly converting the dense layers of MLLMs to MoD layers leads to substantial performance degradation. To address this issue, we propose an innovative MoD adaptation strategy for existing MLLMs called $\gamma$-MoD. In $\gamma$-MoD, a novel metric is proposed to guide the deployment of MoDs in the MLLM, namely rank of attention maps (ARank). Through ARank, we can effectively identify which layer is redundant and should be replaced with the MoD layer. Based on ARank, we further propose two novel designs to maximize the computational sparsity of MLLM while maintaining its performance, namely shared vision-language router and masked routing learning. With these designs, more than 90% dense layers of the MLLM can be effectively converted to the MoD ones. To validate our method, we apply it to three popular MLLMs, and conduct extensive experiments on 9 benchmark datasets. Experimental results not only validate the significant efficiency benefit of $\gamma$-MoD to existing MLLMs but also confirm its generalization ability on various MLLMs. For example, with a minor performance drop, i.e., -1.5%, $\gamma$-MoD can reduce the training and inference time of LLaVA-HR by 31.0% and 53.2%, respectively.

Mono-InternVL: Pushing the Boundaries of Monolithic Multimodal Large Language Models with Endogenous Visual Pre-training

The rapid advancement of Large Language Models (LLMs) has led to an influx of efforts to extend their capabilities to multimodal tasks. Among them, growing attention has been focused on monolithic Multimodal Large Language Models (MLLMs) that integrate visual encoding and language decoding into a single LLM. Despite the structural simplicity and deployment-friendliness, training a monolithic MLLM with promising performance still remains challenging. In particular, the popular approaches adopt continuous pre-training to extend a pre-trained LLM to a monolithic MLLM, which suffers from catastrophic forgetting and leads to performance degeneration. In this paper, we aim to overcome this limitation from the perspective of delta tuning. Specifically, our core idea is to embed visual parameters into a pre-trained LLM, thereby incrementally learning visual knowledge from massive data via delta tuning, i.e., freezing the LLM when optimizing the visual parameters. Based on this principle, we present Mono-InternVL, a novel monolithic MLLM that seamlessly integrates a set of visual experts via a multimodal mixture-of-experts structure. Moreover, we propose an innovative pre-training strategy to maximize the visual capability of Mono-InternVL, namely Endogenous Visual Pre-training (EViP). In particular, EViP is designed as a progressive learning process for visual experts, which aims to fully exploit the visual knowledge from noisy data to high-quality data. To validate our approach, we conduct extensive experiments on 16 benchmarks. Experimental results not only validate the superior performance of Mono-InternVL compared to the state-of-the-art MLLM on 6 multimodal benchmarks, e.g., +113 points over InternVL-1.5 on OCRBench, but also confirm its better deployment efficiency, with first token latency reduced by up to 67%.

3D-GRES: Generalized 3D Referring Expression Segmentation

3D Referring Expression Segmentation (3D-RES) is dedicated to segmenting a specific instance within a 3D space based on a natural language description. However, current approaches are limited to segmenting a single target, restricting the versatility of the task. To overcome this limitation, we introduce Generalized 3D Referring Expression Segmentation (3D-GRES), which extends the capability to segment any number of instances based on natural language instructions. In addressing this broader task, we propose the Multi-Query Decoupled Interaction Network (MDIN), designed to break down multi-object segmentation tasks into simpler, individual segmentations. MDIN comprises two fundamental components: Text-driven Sparse Queries (TSQ) and Multi-object Decoupling Optimization (MDO). TSQ generates sparse point cloud features distributed over key targets as the initialization for queries. Meanwhile, MDO is tasked with assigning each target in multi-object scenarios to different queries while maintaining their semantic consistency. To adapt to this new task, we build a new dataset, namely Multi3DRes. Our comprehensive evaluations on this dataset demonstrate substantial enhancements over existing models, thus charting a new path for intricate multi-object 3D scene comprehension. The benchmark and code are available at https://github.com/sosppxo/MDIN.

ControlMLLM: Training-Free Visual Prompt Learning for Multimodal Large Language Models

In this work, we propose a training-free method to inject visual referring into Multimodal Large Language Models (MLLMs) through learnable visual token optimization. We observe the relationship between text prompt tokens and visual tokens in MLLMs, where attention layers model the connection between them. Our approach involves adjusting visual tokens from the MLP output during inference, controlling which text prompt tokens attend to which visual tokens. We optimize a learnable visual token based on an energy function, enhancing the strength of referential regions in the attention map. This enables detailed region description and reasoning without the need for substantial training costs or model retraining. Our method offers a promising direction for integrating referential abilities into MLLMs. Our method support referring with box, mask, scribble and point. The results demonstrate that our method exhibits controllability and interpretability.

Deep Instruction Tuning for Segment Anything Model

Segment Anything Model (SAM) exhibits powerful yet versatile capabilities on (un) conditional image segmentation tasks recently. Although SAM can support various segmentation prompts, we note that, compared to point- and box-guided segmentation, it performs much worse on text-instructed tasks. We argue that deep text instruction tuning is key to mitigate such shortcoming caused by the shallow fusion scheme in its default light-weight mask decoder. In this paper, two \emph{deep instruction tuning} (DIT) methods are proposed, one is end-to-end and the other is layer-wise. With these tuning methods, we can regard the image encoder of SAM as a stand-alone vision-language learner in contrast to building another deep fusion branch. Extensive experiments on three highly competitive benchmark datasets of referring image segmentation show that a simple end-to-end DIT improves SAM by a large margin, with layer-wise DIT further boosts the performance to state-of-the-art. Our code is anonymously released at: https://github.com/wysnzzzz/DIT.

Fast Text-to-3D-Aware Face Generation and Manipulation via Direct Cross-modal Mapping and Geometric Regularization

Text-to-3D-aware face (T3D Face) generation and manipulation is an emerging research hot spot in machine learning, which still suffers from low efficiency and poor quality. In this paper, we propose an End-to-End Efficient and Effective network for fast and accurate T3D face generation and manipulation, termed $E^3$-FaceNet. Different from existing complex generation paradigms, $E^3$-FaceNet resorts to a direct mapping from text instructions to 3D-aware visual space. We introduce a novel Style Code Enhancer to enhance cross-modal semantic alignment, alongside an innovative Geometric Regularization objective to maintain consistency across multi-view generations. Extensive experiments on three benchmark datasets demonstrate that $E^3$-FaceNet can not only achieve picture-like 3D face generation and manipulation, but also improve inference speed by orders of magnitudes. For instance, compared with Latent3D, $E^3$-FaceNet speeds up the five-view generations by almost 470 times, while still exceeding in generation quality. Our code are released at https://github.com/Aria-Zhangjl/E3-FaceNet.

Feast Your Eyes: Mixture-of-Resolution Adaptation for Multimodal Large Language Models

Despite remarkable progress, existing multimodal large language models (MLLMs) are still inferior in granular visual recognition. Contrary to previous works, we study this problem from the perspective of image resolution, and reveal that a combination of low- and high-resolution visual features can effectively mitigate this shortcoming. Based on this observation, we propose a novel and efficient method for MLLMs, termed Mixture-of-Resolution Adaptation (MRA). In particular, MRA adopts two visual pathways for images with different resolutions, where high-resolution visual information is embedded into the low-resolution pathway via the novel mixture-of-resolution adapters (MR-Adapters). This design also greatly reduces the input sequence length of MLLMs. To validate MRA, we apply it to a recent MLLM called LLaVA, and term the new model LLaVA-HR. We conduct extensive experiments on 11 vision-language (VL) tasks, which show that LLaVA-HR outperforms existing MLLMs on 8 VL tasks, e.g., +9.4% on TextVQA. More importantly, both training and inference of LLaVA-HR remain efficient with MRA, e.g., 20 training hours and 3$\times$ inference speed than LLaVA-1.5. Source codes are released at: https://github.com/luogen1996/LLaVA-HR.

Towards Omni-supervised Referring Expression Segmentation

Referring Expression Segmentation (RES) is an emerging task in computer vision, which segments the target instances in images based on text descriptions. However, its development is plagued by the expensive segmentation labels. To address this issue, we propose a new learning task for RES called Omni-supervised Referring Expression Segmentation (Omni-RES), which aims to make full use of unlabeled, fully labeled and weakly labeled data, e.g., referring points or grounding boxes, for efficient RES training. To accomplish this task, we also propose a novel yet strong baseline method for Omni-RES based on the recently popular teacher-student learning, where where the weak labels are not directly transformed into supervision signals but used as a yardstick to select and refine high-quality pseudo-masks for teacher-student learning. To validate the proposed Omni-RES method, we apply it to a set of state-of-the-art RES models and conduct extensive experiments on a bunch of RES datasets. The experimental results yield the obvious merits of Omni-RES than the fully-supervised and semi-supervised training schemes. For instance, with only 10% fully labeled data, Omni-RES can help the base model achieve 100% fully supervised performance, and it also outperform the semi-supervised alternative by a large margin, e.g., +14.93% on RefCOCO and +14.95% on RefCOCO+, respectively. More importantly, Omni-RES also enable the use of large-scale vision-langauges like Visual Genome to facilitate low-cost RES training, and achieve new SOTA performance of RES, e.g., 80.66 on RefCOCO.

3D-STMN: Dependency-Driven Superpoint-Text Matching Network for End-to-End 3D Referring Expression Segmentation

In 3D Referring Expression Segmentation (3D-RES), the earlier approach adopts a two-stage paradigm, extracting segmentation proposals and then matching them with referring expressions. However, this conventional paradigm encounters significant challenges, most notably in terms of the generation of lackluster initial proposals and a pronounced deceleration in inference speed. Recognizing these limitations, we introduce an innovative end-to-end Superpoint-Text Matching Network (3D-STMN) that is enriched by dependency-driven insights. One of the keystones of our model is the Superpoint-Text Matching (STM) mechanism. Unlike traditional methods that navigate through instance proposals, STM directly correlates linguistic indications with their respective superpoints, clusters of semantically related points. This architectural decision empowers our model to efficiently harness cross-modal semantic relationships, primarily leveraging densely annotated superpoint-text pairs, as opposed to the more sparse instance-text pairs. In pursuit of enhancing the role of text in guiding the segmentation process, we further incorporate the Dependency-Driven Interaction (DDI) module to deepen the network's semantic comprehension of referring expressions. Using the dependency trees as a beacon, this module discerns the intricate relationships between primary terms and their associated descriptors in expressions, thereby elevating both the localization and segmentation capacities of our model. Comprehensive experiments on the ScanRefer benchmark reveal that our model not only set new performance standards, registering an mIoU gain of 11.7 points but also achieve a staggering enhancement in inference speed, surpassing traditional methods by 95.7 times. The code and models are available at https://github.com/sosppxo/3D-STMN.

Cheap and Quick: Efficient Vision-Language Instruction Tuning for Large Language Models

Recently, growing interest has been aroused in extending the multimodal capability of large language models (LLMs), e.g., vision-language (VL) learning, which is regarded as the next milestone of artificial general intelligence. However, existing solutions are prohibitively expensive, which not only need to optimize excessive parameters, but also require another large-scale pre-training before VL instruction tuning. In this paper, we propose a novel and affordable solution for the effective VL adaption of LLMs, called Mixture-of-Modality Adaptation (MMA). Instead of using large neural networks to connect the image encoder and LLM, MMA adopts lightweight modules, i.e., adapters, to bridge the gap between LLMs and VL tasks, which also enables the joint optimization of the image and language models. Meanwhile, MMA is also equipped with a routing algorithm to help LLMs achieve an automatic shift between single- and multi-modal instructions without compromising their ability of natural language understanding. To validate MMA, we apply it to a recent LLM called LLaMA and term this formed large vision-language instructed model as LaVIN. To validate MMA and LaVIN, we conduct extensive experiments under two setups, namely multimodal science question answering and multimodal dialogue. The experimental results not only demonstrate the competitive performance and the superior training efficiency of LaVIN than existing multimodal LLMs, but also confirm its great potential as a general-purpose chatbot. More importantly, the actual expenditure of LaVIN is extremely cheap, e.g., only 1.4 training hours with 3.8M trainable parameters, greatly confirming the effectiveness of MMA. Our project is released at https://luogen1996.github.io/lavin.