DiffSensei: Bridging Multi-Modal LLMs and Diffusion Models for Customized Manga Generation

Story visualization, the task of creating visual narratives from textual descriptions, has seen progress with text-to-image generation models. However, these models often lack effective control over character appearances and interactions, particularly in multi-character scenes. To address these limitations, we propose a new task: \textbf{customized manga generation} and introduce \textbf{DiffSensei}, an innovative framework specifically designed for generating manga with dynamic multi-character control. DiffSensei integrates a diffusion-based image generator with a multimodal large language model (MLLM) that acts as a text-compatible identity adapter. Our approach employs masked cross-attention to seamlessly incorporate character features, enabling precise layout control without direct pixel transfer. Additionally, the MLLM-based adapter adjusts character features to align with panel-specific text cues, allowing flexible adjustments in character expressions, poses, and actions. We also introduce \textbf{MangaZero}, a large-scale dataset tailored to this task, containing 43,264 manga pages and 427,147 annotated panels, supporting the visualization of varied character interactions and movements across sequential frames. Extensive experiments demonstrate that DiffSensei outperforms existing models, marking a significant advancement in manga generation by enabling text-adaptable character customization. The project page is https://jianzongwu.github.io/projects/diffsensei/.

RTAGrasp: Learning Task-Oriented Grasping from Human Videos via Retrieval, Transfer, and Alignment

Task-oriented grasping (TOG) is crucial for robots to accomplish manipulation tasks, requiring the determination of TOG positions and directions. Existing methods either rely on costly manual TOG annotations or only extract coarse grasping positions or regions from human demonstrations, limiting their practicality in real-world applications. To address these limitations, we introduce RTAGrasp, a Retrieval, Transfer, and Alignment framework inspired by human grasping strategies. Specifically, our approach first effortlessly constructs a robot memory from human grasping demonstration videos, extracting both TOG position and direction constraints. Then, given a task instruction and a visual observation of the target object, RTAGrasp retrieves the most similar human grasping experience from its memory and leverages semantic matching capabilities of vision foundation models to transfer the TOG constraints to the target object in a training-free manner. Finally, RTAGrasp aligns the transferred TOG constraints with the robot's action for execution. Evaluations on the public TOG benchmark, TaskGrasp dataset, show the competitive performance of RTAGrasp on both seen and unseen object categories compared to existing baseline methods. Real-world experiments further validate its effectiveness on a robotic arm. Our code, appendix, and video are available at \url{https://sites.google.com/view/rtagrasp/home}.

Scene-wise Adaptive Network for Dynamic Cold-start Scenes Optimization in CTR Prediction

In the realm of modern mobile E-commerce, providing users with nearby commercial service recommendations through location-based online services has become increasingly vital. While machine learning approaches have shown promise in multi-scene recommendation, existing methodologies often struggle to address cold-start problems in unprecedented scenes: the increasing diversity of commercial choices, along with the short online lifespan of scenes, give rise to the complexity of effective recommendations in online and dynamic scenes. In this work, we propose Scene-wise Adaptive Network (SwAN), a novel approach that emphasizes high-performance cold-start online recommendations for new scenes. Our approach introduces several crucial capabilities, including scene similarity learning, user-specific scene transition cognition, scene-specific information construction for the new scene, and enhancing the diverged logical information between scenes. We demonstrate SwAN's potential to optimize dynamic multi-scene recommendation problems by effectively online handling cold-start recommendations for any newly arrived scenes. More encouragingly, SwAN has been successfully deployed in Meituan's online catering recommendation service, which serves millions of customers per day, and SwAN has achieved a 5.64% CTR index improvement relative to the baselines and a 5.19% increase in daily order volume proportion.

Estimating before Debiasing: A Bayesian Approach to Detaching Prior Bias in Federated Semi-Supervised Learning

Federated Semi-Supervised Learning (FSSL) leverages both labeled and unlabeled data on clients to collaboratively train a model.In FSSL, the heterogeneous data can introduce prediction bias into the model, causing the model's prediction to skew towards some certain classes. Existing FSSL methods primarily tackle this issue by enhancing consistency in model parameters or outputs. However, as the models themselves are biased, merely constraining their consistency is not sufficient to alleviate prediction bias. In this paper, we explore this bias from a Bayesian perspective and demonstrate that it principally originates from label prior bias within the training data. Building upon this insight, we propose a debiasing method for FSSL named FedDB. FedDB utilizes the Average Prediction Probability of Unlabeled Data (APP-U) to approximate the biased prior.During local training, FedDB employs APP-U to refine pseudo-labeling through Bayes' theorem, thereby significantly reducing the label prior bias. Concurrently, during the model aggregation, FedDB uses APP-U from participating clients to formulate unbiased aggregate weights, thereby effectively diminishing bias in the global model. Experimental results show that FedDB can surpass existing FSSL methods. The code is available at https://github.com/GuogangZhu/FedDB.

FoundationGrasp: Generalizable Task-Oriented Grasping with Foundation Models

Task-oriented grasping (TOG), which refers to the problem of synthesizing grasps on an object that are configurationally compatible with the downstream manipulation task, is the first milestone towards tool manipulation. Analogous to the activation of two brain regions responsible for semantic and geometric reasoning during cognitive processes, modeling the complex relationship between objects, tasks, and grasps requires rich prior knowledge about objects and tasks. Existing methods typically limit the prior knowledge to a closed-set scope and cannot support the generalization to novel objects and tasks out of the training set. To address such a limitation, we propose FoundationGrasp, a foundation model-based TOG framework that leverages the open-ended knowledge from foundation models to learn generalizable TOG skills. Comprehensive experiments are conducted on the contributed Language and Vision Augmented TaskGrasp (LaViA-TaskGrasp) dataset, demonstrating the superiority of FoudationGrasp over existing methods when generalizing to novel object instances, object classes, and tasks out of the training set. Furthermore, the effectiveness of FoudationGrasp is validated in real-robot grasping and manipulation experiments on a 7 DoF robotic arm. Our code, data, appendix, and video are publicly available at https://sites.google.com/view/foundationgrasp.

Commonsense Scene Graph-based Target Localization for Object Search

Object search is a fundamental skill for household robots, yet the core problem lies in the robot's ability to locate the target object accurately. The dynamic nature of household environments, characterized by the arbitrary placement of daily objects by users, makes it challenging to perform target localization. To efficiently locate the target object, the robot needs to be equipped with knowledge at both the object and room level. However, existing approaches rely solely on one type of knowledge, leading to unsatisfactory object localization performance and, consequently, inefficient object search processes. To address this problem, we propose a commonsense scene graph-based target localization, CSG-TL, to enhance target object search in the household environment. Given the pre-built map with stationary items, the robot models the room-level knowledge with object-level commonsense knowledge generated by a large language model (LLM) to a commonsense scene graph (CSG), supporting both types of knowledge for CSG-TL. To demonstrate the superiority of CSG-TL on target localization, extensive experiments are performed on the real-world ScanNet dataset and the AI2THOR simulator. Moreover, we have extended CSG-TL to an object search framework, CSG-OS, validated in both simulated and real-world environments. Code and videos are available at https://sites.google.com/view/csg-os.

Scalable Non-Cartesian Magnetic Resonance Imaging with R2D2

We propose a new approach for non-Cartesian magnetic resonance image reconstruction. While unrolled architectures provide robustness via data-consistency layers, embedding measurement operators in Deep Neural Network (DNN) can become impractical at large scale. Alternative Plug-and-Play (PnP) approaches, where the denoising DNNs are blind to the measurement setting, are not affected by this limitation and have also proven effective, but their highly iterative nature also affects scalability. To address this scalability challenge, we leverage the "Residual-to-Residual DNN series for high-Dynamic range imaging (R2D2)" approach recently introduced in astronomical imaging. R2D2's reconstruction is formed as a series of residual images, iteratively estimated as outputs of DNNs taking the previous iteration's image estimate and associated data residual as inputs. The method can be interpreted as a learned version of the Matching Pursuit algorithm. We demonstrate R2D2 in simulation, considering radial k-space sampling acquisition sequences. Our preliminary results suggest that R2D2 achieves: (i) suboptimal performance compared to its unrolled incarnation R2D2-Net, which is however non-scalable due to the necessary embedding of NUFFT-based data-consistency layers; (ii) superior reconstruction quality to a scalable version of R2D2-Net embedding an FFT-based approximation for data consistency; (iii) superior reconstruction quality to PnP, while only requiring few iterations.

Plug-and-play imaging with model uncertainty quantification in radio astronomy

Plug-and-Play (PnP) algorithms are appealing alternatives to proximal algorithms when solving inverse imaging problems. By learning a Deep Neural Network (DNN) behaving as a proximal operator, one waives the computational complexity of optimisation algorithms induced by sophisticated image priors, and the sub-optimality of handcrafted priors compared to DNNs. At the same time, these methods inherit the versatility of optimisation algorithms allowing the minimisation of a large class of objective functions. Such features are highly desirable in radio-interferometric (RI) imaging in astronomy, where the data size, the ill-posedness of the problem and the dynamic range of the target reconstruction are critical. In a previous work, we introduced a class of convergent PnP algorithms, dubbed AIRI, relying on a forward-backward algorithm, with a differentiable data-fidelity term and dynamic range-specific denoisers trained on highly pre-processed unrelated optical astronomy images. Here, we show that AIRI algorithms can benefit from a constrained data fidelity term at the mere cost of transferring to a primal-dual forward-backward algorithmic backbone. Moreover, we show that AIRI algorithms are robust to strong variations in the nature of the training dataset: denoisers trained on MRI images yield similar reconstructions to those trained on astronomical data. We additionally quantify the model uncertainty introduced by the randomness in the training process and suggest that AIRI algorithms are robust to model uncertainty. Finally, we propose an exhaustive comparison with methods from the radio-astronomical imaging literature and show the superiority of the proposed method over the current state-of-the-art.

HKTGNN: Hierarchical Knowledge Transferable Graph Neural Network-based Supply Chain Risk Assessment

The strength of a supply chain is an important measure of a country's or region's technical advancement and overall competitiveness. Establishing supply chain risk assessment models for effective management and mitigation of potential risks has become increasingly crucial. As the number of businesses grows, the important relationships become more complicated and difficult to measure. This emphasizes the need of extracting relevant information from graph data. Previously, academics mostly employed knowledge inference to increase the visibility of links between nodes in the supply chain. However, they have not solved the data hunger problem of single node feature characteristics. We propose a hierarchical knowledge transferable graph neural network-based (HKTGNN) supply chain risk assessment model to address these issues. Our approach is based on current graph embedding methods for assessing corporate investment risk assessment. We embed the supply chain network corresponding to individual goods in the supply chain using the graph embedding module, resulting in a directed homogeneous graph with just product nodes. This reduces the complicated supply chain network into a basic product network. It addresses difficulties using the domain difference knowledge transferable module based on centrality, which is presented by the premise that supply chain feature characteristics may be biased in the actual world. Meanwhile, the feature complement and message passing will alleviate the data hunger problem, which is driven by domain differences. Our model outperforms in experiments on a real-world supply chain dataset. We will give an equation to prove that our comparative experiment is both effective and fair.

Efficient Object Rearrangement via Multi-view Fusion

The prospect of assistive robots aiding in object organization has always been compelling. In an image-goal setting, the robot rearranges the current scene to match the single image captured from the goal scene. The key to an image-goal rearrangement system is estimating the desired placement pose of each object based on the single goal image and observations from the current scene. In order to establish sufficient associations for accurate estimation, the system should observe an object from a viewpoint similar to that in the goal image. Existing image-goal rearrangement systems, due to their reliance on a fixed viewpoint for perception, often require redundant manipulations to randomly adjust an object's pose for a better perspective. Addressing this inefficiency, we introduce a novel object rearrangement system that employs multi-view fusion. By observing the current scene from multiple viewpoints before manipulating objects, our approach can estimate a more accurate pose without redundant manipulation times. A standard visual localization pipeline at the object level is developed to capitalize on the advantages of multi-view observations. Simulation results demonstrate that the efficiency of our system outperforms existing single-view systems. The effectiveness of our system is further validated in a physical experiment.