Wireless short-packet communications pose challenges to the security and reliability of the transmission. Besides, the proactive warder compounds these challenges, who detects and interferes with the potential transmission. An extra jamming channel is introduced by the proactive warder compared with the passive one, resulting in the inapplicability of analytical methods and results in exsiting works. Thus, effective system design schemes are required for short-packet communications against the proactive warder. To address this issue, we consider the analysis and design of covert and reliable transmissions for above systems. Specifically, to investigate the reliable and covert performance of the system, detection error probability at the warder and decoding error probability at the receiver are derived, which is affected by both the transmit power and the jamming power. Furthermore, to maximize the effective throughput, an optimization framework is proposed under reliability and covertness constraints. Numerical results verify the accuracy of analytical results and the feasibility of the optimization framework. It is shown that the tradeoff between transmission reliability and covertness is changed by the proactive warder compared with the passive one. Besides, it is shown that longer blocklength is always beneficial to improve the throughput for systems with optimized transmission rates. But when transmission rates are fixed, the blocklength should be carefully designed since the maximum one is not optimal in this case.
We introduce AvatarBooth, a novel method for generating high-quality 3D avatars using text prompts or specific images. Unlike previous approaches that can only synthesize avatars based on simple text descriptions, our method enables the creation of personalized avatars from casually captured face or body images, while still supporting text-based model generation and editing. Our key contribution is the precise avatar generation control by using dual fine-tuned diffusion models separately for the human face and body. This enables us to capture intricate details of facial appearance, clothing, and accessories, resulting in highly realistic avatar generations. Furthermore, we introduce pose-consistent constraint to the optimization process to enhance the multi-view consistency of synthesized head images from the diffusion model and thus eliminate interference from uncontrolled human poses. In addition, we present a multi-resolution rendering strategy that facilitates coarse-to-fine supervision of 3D avatar generation, thereby enhancing the performance of the proposed system. The resulting avatar model can be further edited using additional text descriptions and driven by motion sequences. Experiments show that AvatarBooth outperforms previous text-to-3D methods in terms of rendering and geometric quality from either text prompts or specific images. Please check our project website at https://zeng-yifei.github.io/avatarbooth_page/.
The actuation of a soft robot involves transforming its shape from an initial state to a desired operational state. To achieve task-specific design, it is necessary to map the shape between these two states to the robot's design parameters. This requires both a kinematic model of the soft robot and a shape-matching algorithm. However, existing kinematic models for soft robots are often limited in accuracy and generality due to the robot's flexibility and nonlinearity, and current shape-matching algorithms are not well-suited for 3D cases. To address this challenge, this paper presents a shape-matching design framework for bellow soft pneumatic actuators (SPAs) to expedite the actuator design process. First, a kinematic model of the bellow SPA is developed based on its novel modular design and a surrogate model, which is trained using an Artificial Neural Network and a dataset from Finite Element Method (FEM) simulations. Then, a 3D shape-matching algorithm, composed of a 3D piecewise-constant curvature segmentation and a bi-level Bayesian optimisation algorithm based on the surrogate model, is presented to find the optimal actuator design parameters that match the desired shape. An open-source design toolbox SPADA (Soft Pneumatic Actuator Design frAmework) is also developed to facilitate the use of the proposed design framework, including FEM simulation, shape-matching optimisation based on surrogate modelling, and automatic generation of the ready-to-print CAD file. Experimental results show an averaged root-mean-square error of 2.74 mm, validating the accuracy of the kinematics model. To demonstrate the proposed design framework, actuators are designed to match the predefined shapes in 2D and 3D space.
With the widespread use of large language models (LLMs) in NLP tasks, researchers have discovered the potential of Chain-of-thought (CoT) to assist LLMs in accomplishing complex reasoning tasks by generating intermediate steps. However, human thought processes are often non-linear, rather than simply sequential chains of thoughts. Therefore, we propose Graph-of-Thought (GoT) reasoning, which models human thought processes not only as a chain but also as a graph. By representing thought units as nodes and connections between them as edges, our approach captures the non-sequential nature of human thinking and allows for a more realistic modeling of thought processes. Similar to Multimodal-CoT, we modeled GoT reasoning as a two-stage framework, generating rationales first and then producing the final answer. Specifically, we employ an additional graph-of-thoughts encoder for GoT representation learning and fuse the GoT representation with the original input representation through a gated fusion mechanism. We implement a GoT reasoning model on the T5 pre-trained model and evaluate its performance on a text-only reasoning task (GSM8K) and a multimodal reasoning task (ScienceQA). Our model achieves significant improvement over the strong CoT baseline with 3.41% and 5.08% on the GSM8K test set with T5-base and T5-large architectures, respectively. Additionally, our model boosts accuracy from 84.91% to 91.54% using the T5-base model and from 91.68% to 92.77% using the T5-large model over the state-of-the-art Multimodal-CoT on the ScienceQA test set. Experiments have shown that GoT achieves comparable results to Multimodal-CoT(large) with over 700M parameters, despite having fewer than 250M backbone model parameters, demonstrating the effectiveness of GoT.
We present a novel differentiable rendering framework for joint geometry, material, and lighting estimation from multi-view images. In contrast to previous methods which assume a simplified environment map or co-located flashlights, in this work, we formulate the lighting of a static scene as one neural incident light field (NeILF) and one outgoing neural radiance field (NeRF). The key insight of the proposed method is the union of the incident and outgoing light fields through physically-based rendering and inter-reflections between surfaces, making it possible to disentangle the scene geometry, material, and lighting from image observations in a physically-based manner. The proposed incident light and inter-reflection framework can be easily applied to other NeRF systems. We show that our method can not only decompose the outgoing radiance into incident lights and surface materials, but also serve as a surface refinement module that further improves the reconstruction detail of the neural surface. We demonstrate on several datasets that the proposed method is able to achieve state-of-the-art results in terms of geometry reconstruction quality, material estimation accuracy, and the fidelity of novel view rendering.
As machine learning being used increasingly in making high-stakes decisions, an arising challenge is to avoid unfair AI systems that lead to discriminatory decisions for protected population. A direct approach for obtaining a fair predictive model is to train the model through optimizing its prediction performance subject to fairness constraints, which achieves Pareto efficiency when trading off performance against fairness. Among various fairness metrics, the ones based on the area under the ROC curve (AUC) are emerging recently because they are threshold-agnostic and effective for unbalanced data. In this work, we formulate the training problem of a fairness-aware machine learning model as an AUC optimization problem subject to a class of AUC-based fairness constraints. This problem can be reformulated as a min-max optimization problem with min-max constraints, which we solve by stochastic first-order methods based on a new Bregman divergence designed for the special structure of the problem. We numerically demonstrate the effectiveness of our approach on real-world data under different fairness metrics.
Heterogeneous graph neural network has unleashed great potential on graph representation learning and shown superior performance on downstream tasks such as node classification and clustering. Existing heterogeneous graph learning networks are primarily designed to either rely on pre-defined meta-paths or use attention mechanisms for type-specific attentive message propagation on different nodes/edges, incurring many customization efforts and computational costs. To this end, we design a relation-centered Pooling and Convolution for Heterogeneous Graph learning Network, namely PC-HGN, to enable relation-specific sampling and cross-relation convolutions, from which the structural heterogeneity of the graph can be better encoded into the embedding space through the adaptive training process. We evaluate the performance of the proposed model by comparing with state-of-the-art graph learning models on three different real-world datasets, and the results show that PC-HGN consistently outperforms all the baseline and improves the performance maximumly up by 17.8%.
Neural implicit functions have recently shown promising results on surface reconstructions from multiple views. However, current methods still suffer from excessive time complexity and poor robustness when reconstructing unbounded or complex scenes. In this paper, we present RegSDF, which shows that proper point cloud supervisions and geometry regularizations are sufficient to produce high-quality and robust reconstruction results. Specifically, RegSDF takes an additional oriented point cloud as input, and optimizes a signed distance field and a surface light field within a differentiable rendering framework. We also introduce the two critical regularizations for this optimization. The first one is the Hessian regularization that smoothly diffuses the signed distance values to the entire distance field given noisy and incomplete input. And the second one is the minimal surface regularization that compactly interpolates and extrapolates the missing geometry. Extensive experiments are conducted on DTU, BlendedMVS, and Tanks and Temples datasets. Compared with recent neural surface reconstruction approaches, RegSDF is able to reconstruct surfaces with fine details even for open scenes with complex topologies and unstructured camera trajectories.
Input features play a crucial role in the predictive performance of DNN-based industrial recommender systems with thousands of categorical and continuous fields from users, items, contexts, and their interactions. Noisy features and inappropriate embedding dimension assignments can impair the performance of recommender systems and introduce unnecessary complexity in model training and online serving. Optimizing the input configuration of DNN models, including feature selection and embedding dimension assignment, has become one of the essential topics in feature engineering. Typically, feature selection and embedding dimension search are optimized sequentially, i.e., feature selection is performed first, followed by embedding dimension search to determine the optimal dimension size for each selected feature. In contrast, this paper studies the joint optimization of feature selection and embedding dimension search. To this end, we propose a differentiable neural \textbf{i}nput \textbf{razor}, namely \textbf{i-Razor}. Specifically, inspired by recent advances in neural architecture search, we introduce an end-to-end differentiable model to learn the relative importance between different embedding regions of each feature. Furthermore, a flexible pruning algorithm is proposed to simultaneously achieve feature filtering and dimension size derivation. Extensive experiments on two large-scale public datasets in the Click-Through-Rate (CTR) prediction task demonstrate the efficacy and superiority of i-Razor in balancing model complexity and performance.
We present a differentiable rendering framework for material and lighting estimation from multi-view images and a reconstructed geometry. In the framework, we represent scene lightings as the Neural Incident Light Field (NeILF) and material properties as the surface BRDF modelled by multi-layer perceptrons. Compared with recent approaches that approximate scene lightings as the 2D environment map, NeILF is a fully 5D light field that is capable of modelling illuminations of any static scenes. In addition, occlusions and indirect lights can be handled naturally by the NeILF representation without requiring multiple bounces of ray tracing, making it possible to estimate material properties even for scenes with complex lightings and geometries. We also propose a smoothness regularization and a Lambertian assumption to reduce the material-lighting ambiguity during the optimization. Our method strictly follows the physically-based rendering equation, and jointly optimizes material and lighting through the differentiable rendering process. We have intensively evaluated the proposed method on our in-house synthetic dataset, the DTU MVS dataset, and real-world BlendedMVS scenes. Our method is able to outperform previous methods by a significant margin in terms of novel view rendering quality, setting a new state-of-the-art for image-based material and lighting estimation.