VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction

Recent Multimodal Large Language Models (MLLMs) have typically focused on integrating visual and textual modalities, with less emphasis placed on the role of speech in enhancing interaction. However, speech plays a crucial role in multimodal dialogue systems, and implementing high-performance in both vision and speech tasks remains a significant challenge due to the fundamental modality differences. In this paper, we propose a carefully designed multi-stage training methodology that progressively trains LLM to understand both visual and speech information, ultimately enabling fluent vision and speech interaction. Our approach not only preserves strong vision-language capacity, but also enables efficient speech-to-speech dialogue capabilities without separate ASR and TTS modules, significantly accelerating multimodal end-to-end response speed. By comparing our method against state-of-the-art counterparts across benchmarks for image, video, and speech tasks, we demonstrate that our model is equipped with both strong visual and speech capabilities, making near real-time vision and speech interaction.

SVFR: A Unified Framework for Generalized Video Face Restoration

Face Restoration (FR) is a crucial area within image and video processing, focusing on reconstructing high-quality portraits from degraded inputs. Despite advancements in image FR, video FR remains relatively under-explored, primarily due to challenges related to temporal consistency, motion artifacts, and the limited availability of high-quality video data. Moreover, traditional face restoration typically prioritizes enhancing resolution and may not give as much consideration to related tasks such as facial colorization and inpainting. In this paper, we propose a novel approach for the Generalized Video Face Restoration (GVFR) task, which integrates video BFR, inpainting, and colorization tasks that we empirically show to benefit each other. We present a unified framework, termed as stable video face restoration (SVFR), which leverages the generative and motion priors of Stable Video Diffusion (SVD) and incorporates task-specific information through a unified face restoration framework. A learnable task embedding is introduced to enhance task identification. Meanwhile, a novel Unified Latent Regularization (ULR) is employed to encourage the shared feature representation learning among different subtasks. To further enhance the restoration quality and temporal stability, we introduce the facial prior learning and the self-referred refinement as auxiliary strategies used for both training and inference. The proposed framework effectively combines the complementary strengths of these tasks, enhancing temporal coherence and achieving superior restoration quality. This work advances the state-of-the-art in video FR and establishes a new paradigm for generalized video face restoration. Code and video demo are available at https://github.com/wangzhiyaoo/SVFR.git.

Semantics Prompting Data-Free Quantization for Low-Bit Vision Transformers

Data-free quantization (DFQ), which facilitates model quantization without real data to address increasing concerns about data security, has garnered significant attention within the model compression community. Recently, the unique architecture of vision transformers (ViTs) has driven the development of specialized DFQ techniques. However, we observe that the synthetic images from existing methods suffer from the deficient semantics issue compared to real images, thereby compromising performance. Motivated by this, we propose SPDFQ, a Semantics Prompting Data-Free Quantization method for ViTs. First, SPDFQ incorporates Attention Priors Alignment (APA), which uses randomly generated attention priors to enhance the semantics of synthetic images. Second, SPDFQ introduces Multi-Semantic Reinforcement (MSR), which utilizes localized patch optimization to prompt efficient parameterization and diverse semantics in synthetic images. Finally, SPDFQ employs Softlabel Learning (SL), where soft learning targets are adapted to encourage more complex semantics and accommodate images augmented by MSR. Experimental results demonstrate that SPDFQ significantly outperforms existing methods. For instance, SPDFQ achieves a 15.52% increase in top-1 accuracy on ImageNet for W4A4 ViT-B

DiffusionTrend: A Minimalist Approach to Virtual Fashion Try-On

We introduce DiffusionTrend for virtual fashion try-on, which forgoes the need for retraining diffusion models. Using advanced diffusion models, DiffusionTrend harnesses latent information rich in prior information to capture the nuances of garment details. Throughout the diffusion denoising process, these details are seamlessly integrated into the model image generation, expertly directed by a precise garment mask crafted by a lightweight and compact CNN. Although our DiffusionTrend model initially demonstrates suboptimal metric performance, our exploratory approach offers some important advantages: (1) It circumvents resource-intensive retraining of diffusion models on large datasets. (2) It eliminates the necessity for various complex and user-unfriendly model inputs. (3) It delivers a visually compelling try-on experience, underscoring the potential of training-free diffusion model. This initial foray into the application of untrained diffusion models in virtual try-on technology potentially paves the way for further exploration and refinement in this industrially and academically valuable field.

Knowing Where to Focus: Attention-Guided Alignment for Text-based Person Search

In the realm of Text-Based Person Search (TBPS), mainstream methods aim to explore more efficient interaction frameworks between text descriptions and visual data. However, recent approaches encounter two principal challenges. Firstly, the widely used random-based Masked Language Modeling (MLM) considers all the words in the text equally during training. However, massive semantically vacuous words ('with', 'the', etc.) be masked fail to contribute efficient interaction in the cross-modal MLM and hampers the representation alignment. Secondly, manual descriptions in TBPS datasets are tedious and inevitably contain several inaccuracies. To address these issues, we introduce an Attention-Guided Alignment (AGA) framework featuring two innovative components: Attention-Guided Mask (AGM) Modeling and Text Enrichment Module (TEM). AGM dynamically masks semantically meaningful words by aggregating the attention weight derived from the text encoding process, thereby cross-modal MLM can capture information related to the masked word from text context and images and align their representations. Meanwhile, TEM alleviates low-quality representations caused by repetitive and erroneous text descriptions by replacing those semantically meaningful words with MLM's prediction. It not only enriches text descriptions but also prevents overfitting. Extensive experiments across three challenging benchmarks demonstrate the effectiveness of our AGA, achieving new state-of-the-art results with Rank-1 accuracy reaching 78.36%, 67.31%, and 67.4% on CUHK-PEDES, ICFG-PEDES, and RSTPReid, respectively.

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression

Despite a big leap forward in capability, multimodal large language models (MLLMs) tend to behave like a sloth in practical use, i.e., slow response and large latency. Recent efforts are devoted to building tiny MLLMs for better efficiency, but the plethora of visual tokens still used limit their actual speedup. In this paper, we propose a powerful and fast tiny MLLM called FlashSloth. Different from previous efforts, FlashSloth focuses on improving the descriptive power of visual tokens in the process of compressing their redundant semantics. In particular, FlashSloth introduces embedded visual compression designs to capture both visually salient and instruction-related image information, so as to achieving superior multimodal performance with fewer visual tokens. Extensive experiments are conducted to validate the proposed FlashSloth, and a bunch of tiny but strong MLLMs are also comprehensively compared, e.g., InternVL2, MiniCPM-V2 and Qwen2-VL. The experimental results show that compared with these advanced tiny MLLMs, our FlashSloth can greatly reduce the number of visual tokens, training memory and computation complexity while retaining high performance on various VL tasks.

RG-SAN: Rule-Guided Spatial Awareness Network for End-to-End 3D Referring Expression Segmentation

3D Referring Expression Segmentation (3D-RES) aims to segment 3D objects by correlating referring expressions with point clouds. However, traditional approaches frequently encounter issues like over-segmentation or mis-segmentation, due to insufficient emphasis on spatial information of instances. In this paper, we introduce a Rule-Guided Spatial Awareness Network (RG-SAN) by utilizing solely the spatial information of the target instance for supervision. This approach enables the network to accurately depict the spatial relationships among all entities described in the text, thus enhancing the reasoning capabilities. The RG-SAN consists of the Text-driven Localization Module (TLM) and the Rule-guided Weak Supervision (RWS) strategy. The TLM initially locates all mentioned instances and iteratively refines their positional information. The RWS strategy, acknowledging that only target objects have supervised positional information, employs dependency tree rules to precisely guide the core instance's positioning. Extensive testing on the ScanRefer benchmark has shown that RG-SAN not only establishes new performance benchmarks, with an mIoU increase of 5.1 points, but also exhibits significant improvements in robustness when processing descriptions with spatial ambiguity. All codes are available at https://github.com/sosppxo/RG-SAN.

AccDiffusion v2: Towards More Accurate Higher-Resolution Diffusion Extrapolation

Diffusion models suffer severe object repetition and local distortion when the inference resolution differs from its pre-trained resolution. We propose AccDiffusion v2, an accurate method for patch-wise higher-resolution diffusion extrapolation without training. Our in-depth analysis in this paper shows that using an identical text prompt for different patches leads to repetitive generation, while the absence of a prompt undermines image details. In response, our AccDiffusion v2 novelly decouples the vanilla image-content-aware prompt into a set of patch-content-aware prompts, each of which serves as a more precise description of a patch. Further analysis reveals that local distortion arises from inaccurate descriptions in prompts about the local structure of higher-resolution images. To address this issue, AccDiffusion v2, for the first time, introduces an auxiliary local structural information through ControlNet during higher-resolution diffusion extrapolation aiming to mitigate the local distortions. Finally, our analysis indicates that global semantic information is conducive to suppressing both repetitive generation and local distortion. Hence, our AccDiffusion v2 further proposes dilated sampling with window interaction for better global semantic information during higher-resolution diffusion extrapolation. We conduct extensive experiments, including both quantitative and qualitative comparisons, to demonstrate the efficacy of our AccDiffusion v2. The quantitative comparison shows that AccDiffusion v2 achieves state-of-the-art performance in image generation extrapolation without training. The qualitative comparison intuitively illustrates that AccDiffusion v2 effectively suppresses the issues of repetitive generation and local distortion in image generation extrapolation. Our code is available at \url{https://github.com/lzhxmu/AccDiffusion_v2}.

Accelerating Multimodal Large Language Models via Dynamic Visual-Token Exit and the Empirical Findings

The excessive use of visual tokens in existing Multimoal Large Language Models (MLLMs) often exhibits obvious redundancy and brings in prohibitively expensive computation. To gain insights into this problem, we first conduct extensive empirical studies on the attention behaviors of MLLMs, and summarize three main inference stages in MLLMs: (i) Early fusion between tokens is first accomplished quickly. (ii) Intra-modality modeling then comes to play. (iii) Multimodal reasoning} resumes and lasts until the end of inference. In particular, we reveal that visual tokens will stop contributing to reasoning when the text tokens receive enough image information, yielding obvious visual redundancy. Based on these generalized observations, we propose a simple yet effective method to improve the efficiency of MLLMs, termed dynamic visual-token exit (DyVTE). DyVTE uses lightweight hyper-networks to perceive the text token status and decide the removal of all visual tokens after a certain layer, thereby addressing the observed visual redundancy. To validate VTE, we apply it to a set of MLLMs, including LLaVA, VILA, Eagle and InternVL, and conduct extensive experiments on a bunch of benchmarks. The experiment results not only show the effectiveness of our VTE in improving MLLMs' efficiency, but also yield the general modeling patterns of MLLMs, well facilitating the in-depth understanding of MLLMs. Our code is anonymously released at https://github.com/DoubtedSteam/DyVTE.

Mixed Degradation Image Restoration via Local Dynamic Optimization and Conditional Embedding

Multiple-in-one image restoration (IR) has made significant progress, aiming to handle all types of single degraded image restoration with a single model. However, in real-world scenarios, images often suffer from combinations of multiple degradation factors. Existing multiple-in-one IR models encounter challenges related to degradation diversity and prompt singularity when addressing this issue. In this paper, we propose a novel multiple-in-one IR model that can effectively restore images with both single and mixed degradations. To address degradation diversity, we design a Local Dynamic Optimization (LDO) module which dynamically processes degraded areas of varying types and granularities. To tackle the prompt singularity issue, we develop an efficient Conditional Feature Embedding (CFE) module that guides the decoder in leveraging degradation-type-related features, significantly improving the model's performance in mixed degradation restoration scenarios. To validate the effectiveness of our model, we introduce a new dataset containing both single and mixed degradation elements. Experimental results demonstrate that our proposed model achieves state-of-the-art (SOTA) performance not only on mixed degradation tasks but also on classic single-task restoration benchmarks.