Video Token Merging for Long-form Video Understanding

As the scale of data and models for video understanding rapidly expand, handling long-form video input in transformer-based models presents a practical challenge. Rather than resorting to input sampling or token dropping, which may result in information loss, token merging shows promising results when used in collaboration with transformers. However, the application of token merging for long-form video processing is not trivial. We begin with the premise that token merging should not rely solely on the similarity of video tokens; the saliency of tokens should also be considered. To address this, we explore various video token merging strategies for long-form video classification, starting with a simple extension of image token merging, moving to region-concentrated merging, and finally proposing a learnable video token merging (VTM) algorithm that dynamically merges tokens based on their saliency. Extensive experimental results show that we achieve better or comparable performances on the LVU, COIN, and Breakfast datasets. Moreover, our approach significantly reduces memory costs by 84% and boosts throughput by approximately 6.89 times compared to baseline algorithms.

DPDEdit: Detail-Preserved Diffusion Models for Multimodal Fashion Image Editing

Fashion image editing is a crucial tool for designers to convey their creative ideas by visualizing design concepts interactively. Current fashion image editing techniques, though advanced with multimodal prompts and powerful diffusion models, often struggle to accurately identify editing regions and preserve the desired garment texture detail. To address these challenges, we introduce a new multimodal fashion image editing architecture based on latent diffusion models, called Detail-Preserved Diffusion Models (DPDEdit). DPDEdit guides the fashion image generation of diffusion models by integrating text prompts, region masks, human pose images, and garment texture images. To precisely locate the editing region, we first introduce Grounded-SAM to predict the editing region based on the user's textual description, and then combine it with other conditions to perform local editing. To transfer the detail of the given garment texture into the target fashion image, we propose a texture injection and refinement mechanism. Specifically, this mechanism employs a decoupled cross-attention layer to integrate textual descriptions and texture images, and incorporates an auxiliary U-Net to preserve the high-frequency details of generated garment texture. Additionally, we extend the VITON-HD dataset using a multimodal large language model to generate paired samples with texture images and textual descriptions. Extensive experiments show that our DPDEdit outperforms state-of-the-art methods in terms of image fidelity and coherence with the given multimodal inputs.

FlexEdit: Marrying Free-Shape Masks to VLLM for Flexible Image Editing

Combining Vision Large Language Models (VLLMs) with diffusion models offers a powerful method for executing image editing tasks based on human language instructions. However, language instructions alone often fall short in accurately conveying user requirements, particularly when users want to add, replace elements in specific areas of an image. Luckily, masks can effectively indicate the exact locations or elements to be edited, while they require users to precisely draw the shapes at the desired locations, which is highly user-unfriendly. To address this, we propose FlexEdit, an end-to-end image editing method that leverages both free-shape masks and language instructions for Flexible Editing. Our approach employs a VLLM in comprehending the image content, mask, and user instructions. Additionally, we introduce the Mask Enhance Adapter (MEA) that fuses the embeddings of the VLLM with the image data, ensuring a seamless integration of mask information and model output embeddings. Furthermore, we construct FSMI-Edit, a benchmark specifically tailored for free-shape mask, including 8 types of free-shape mask. Extensive experiments show that our method achieves state-of-the-art (SOTA) performance in LLM-based image editing, and our simple prompting technique stands out in its effectiveness. The code and data can be found at https://github.com/A-new-b/flex_edit.

Text-Guided Video Masked Autoencoder

Recent video masked autoencoder (MAE) works have designed improved masking algorithms focused on saliency. These works leverage visual cues such as motion to mask the most salient regions. However, the robustness of such visual cues depends on how often input videos match underlying assumptions. On the other hand, natural language description is an information dense representation of video that implicitly captures saliency without requiring modality-specific assumptions, and has not been explored yet for video MAE. To this end, we introduce a novel text-guided masking algorithm (TGM) that masks the video regions with highest correspondence to paired captions. Without leveraging any explicit visual cues for saliency, our TGM is competitive with state-of-the-art masking algorithms such as motion-guided masking. To further benefit from the semantics of natural language for masked reconstruction, we next introduce a unified framework for joint MAE and masked video-text contrastive learning. We show that across existing masking algorithms, unifying MAE and masked video-text contrastive learning improves downstream performance compared to pure MAE on a variety of video recognition tasks, especially for linear probe. Within this unified framework, our TGM achieves the best relative performance on five action recognition and one egocentric datasets, highlighting the complementary nature of natural language for masked video modeling.

Ada-adapter:Fast Few-shot Style Personlization of Diffusion Model with Pre-trained Image Encoder

Fine-tuning advanced diffusion models for high-quality image stylization usually requires large training datasets and substantial computational resources, hindering their practical applicability. We propose Ada-Adapter, a novel framework for few-shot style personalization of diffusion models. Ada-Adapter leverages off-the-shelf diffusion models and pre-trained image feature encoders to learn a compact style representation from a limited set of source images. Our method enables efficient zero-shot style transfer utilizing a single reference image. Furthermore, with a small number of source images (three to five are sufficient) and a few minutes of fine-tuning, our method can capture intricate style details and conceptual characteristics, generating high-fidelity stylized images that align well with the provided text prompts. We demonstrate the effectiveness of our approach on various artistic styles, including flat art, 3D rendering, and logo design. Our experimental results show that Ada-Adapter outperforms existing zero-shot and few-shot stylization methods in terms of output quality, diversity, and training efficiency.

An I2I Inpainting Approach for Efficient Channel Knowledge Map Construction

Channel knowledge map (CKM) has received widespread attention as an emerging enabling technology for environment-aware wireless communications. It involves the construction of databases containing location-specific channel knowledge, which are then leveraged to facilitate channel state information (CSI) acquisition and transceiver design. In this context, a fundamental challenge lies in efficiently constructing the CKM based on a given wireless propagation environment. Most existing methods are based on stochastic modeling and sequence prediction, which do not fully exploit the inherent physical characteristics of the propagation environment, resulting in low accuracy and high computational complexity. To address these limitations, we propose a Laplacian pyramid (LP)-based CKM construction scheme to predict the channel knowledge at arbitrary locations in a targeted area. Specifically, we first view the channel knowledge as a 2-D image and transform the CKM construction problem into an image-to-image (I2I) inpainting task, which predicts the channel knowledge at a specific location by recovering the corresponding pixel value in the image matrix. Then, inspired by the reversible and closed-form structure of the LP, we show its natural suitability for our task in designing a fast I2I mapping network. For different frequency components of LP decomposition, we design tailored networks accordingly. Besides, to encode the global structural information of the propagation environment, we introduce self-attention and cross-covariance attention mechanisms in different layers, respectively. Finally, experimental results show that the proposed scheme outperforms the benchmark, achieving higher reconstruction accuracy while with lower computational complexity. Moreover, the proposed approach has a strong generalization ability and can be implemented in different wireless communication scenarios.

Mixture-of-Agents Enhances Large Language Model Capabilities

Recent advances in large language models (LLMs) demonstrate substantial capabilities in natural language understanding and generation tasks. With the growing number of LLMs, how to harness the collective expertise of multiple LLMs is an exciting open direction. Toward this goal, we propose a new approach that leverages the collective strengths of multiple LLMs through a Mixture-of-Agents (MoA) methodology. In our approach, we construct a layered MoA architecture wherein each layer comprises multiple LLM agents. Each agent takes all the outputs from agents in the previous layer as auxiliary information in generating its response. MoA models achieves state-of-art performance on AlpacaEval 2.0, MT-Bench and FLASK, surpassing GPT-4 Omni. For example, our MoA using only open-source LLMs is the leader of AlpacaEval 2.0 by a substantial gap, achieving a score of 65.1% compared to 57.5% by GPT-4 Omni.

UniIF: Unified Molecule Inverse Folding

Molecule inverse folding has been a long-standing challenge in chemistry and biology, with the potential to revolutionize drug discovery and material science. Despite specified models have been proposed for different small- or macro-molecules, few have attempted to unify the learning process, resulting in redundant efforts. Complementary to recent advancements in molecular structure prediction, such as RoseTTAFold All-Atom and AlphaFold3, we propose the unified model UniIF for the inverse folding of all molecules. We do such unification in two levels: 1) Data-Level: We propose a unified block graph data form for all molecules, including the local frame building and geometric feature initialization. 2) Model-Level: We introduce a geometric block attention network, comprising a geometric interaction, interactive attention and virtual long-term dependency modules, to capture the 3D interactions of all molecules. Through comprehensive evaluations across various tasks such as protein design, RNA design, and material design, we demonstrate that our proposed method surpasses state-of-the-art methods on all tasks. UniIF offers a versatile and effective solution for general molecule inverse folding.

Invisible Gas Detection: An RGB-Thermal Cross Attention Network and A New Benchmark

The widespread use of various chemical gases in industrial processes necessitates effective measures to prevent their leakage during transportation and storage, given their high toxicity. Thermal infrared-based computer vision detection techniques provide a straightforward approach to identify gas leakage areas. However, the development of high-quality algorithms has been challenging due to the low texture in thermal images and the lack of open-source datasets. In this paper, we present the RGB-Thermal Cross Attention Network (RT-CAN), which employs an RGB-assisted two-stream network architecture to integrate texture information from RGB images and gas area information from thermal images. Additionally, to facilitate the research of invisible gas detection, we introduce Gas-DB, an extensive open-source gas detection database including about 1.3K well-annotated RGB-thermal images with eight variant collection scenes. Experimental results demonstrate that our method successfully leverages the advantages of both modalities, achieving state-of-the-art (SOTA) performance among RGB-thermal methods, surpassing single-stream SOTA models in terms of accuracy, Intersection of Union (IoU), and F2 metrics by 4.86%, 5.65%, and 4.88%, respectively. The code and data will be made available soon.

Harnessing Deep Learning of Point Clouds for Inverse Control of 3D Shape Morphing

Shape-morphing devices, a crucial branch in soft robotics, hold significant application value in areas like human-machine interfaces, biomimetic robotics, and tools for interacting with biological systems. To achieve three-dimensional (3D) programmable shape morphing (PSM), the deployment of array-based actuators is essential. However, a critical knowledge gap impeding the development of 3D PSM is the challenge of controlling the complex systems formed by these soft actuator arrays. This study introduces a novel approach, for the first time, representing the configuration of shape morphing devices using point cloud data and employing deep learning to map these configurations to control inputs. We propose Shape Morphing Net (SMNet), a method that realizes the regression from point cloud data to high-dimensional continuous vectors. Applied to previous 2D PSM actuator arrays, SMNet significantly enhances control precision from 82.23% to 97.68%. Further, we extend its application to 3D PSM devices with three different actuator mechanisms, demonstrating the universal applicability of SMNet to the control of 3D shape morphing technologies. In our demonstrations, we confirm the efficacy of inverse control, where 3D PSM devices successfully replicate target shapes. These shapes are obtained either through 3D scanning of physical objects or via 3D modeling software. The results show that within the deformable range of 3D PSM devices, accurate reproduction of the desired shapes is achievable. The findings of this research represent a substantial advancement in soft robotics, particularly for applications demanding intricate 3D shape transformations, and establish a foundational framework for future developments in the field.