Abstract:As Artificial Intelligence (AI) increasingly integrates into our daily lives, fairness has emerged as a critical concern, particularly in medical AI, where datasets often reflect inherent biases due to social factors like the underrepresentation of marginalized communities and socioeconomic barriers to data collection. Traditional approaches to mitigating these biases have focused on data augmentation and the development of fairness-aware training algorithms. However, this paper argues that the architecture of neural networks, a core component of Machine Learning (ML), plays a crucial role in ensuring fairness. We demonstrate that addressing fairness effectively requires a holistic approach that simultaneously considers data, algorithms, and architecture. Utilizing Automated ML (AutoML) technology, specifically Neural Architecture Search (NAS), we introduce a novel framework, BiaslessNAS, designed to achieve fair outcomes in analyzing skin lesion datasets. BiaslessNAS incorporates fairness considerations at every stage of the NAS process, leading to the identification of neural networks that are not only more accurate but also significantly fairer. Our experiments show that BiaslessNAS achieves a 2.55% increase in accuracy and a 65.50% improvement in fairness compared to traditional NAS methods, underscoring the importance of integrating fairness into neural network architecture for better outcomes in medical AI applications.
Abstract:Enabling robotic agents to perform complex long-horizon tasks has been a long-standing goal in robotics and artificial intelligence (AI). Despite the potential shown by large language models (LLMs), their planning capabilities remain limited to short-horizon tasks and they are unable to replace the symbolic planning approach. Symbolic planners, on the other hand, may encounter execution errors due to their common assumption of complete domain knowledge which is hard to manually prepare for an open-world setting. In this paper, we introduce a Language-Augmented Symbolic Planner (LASP) that integrates pre-trained LLMs to enable conventional symbolic planners to operate in an open-world environment where only incomplete knowledge of action preconditions, objects, and properties is initially available. In case of execution errors, LASP can utilize the LLM to diagnose the cause of the error based on the observation and interact with the environment to incrementally build up its knowledge base necessary for accomplishing the given tasks. Experiments demonstrate that LASP is proficient in solving planning problems in the open-world setting, performing well even in situations where there are multiple gaps in the knowledge.
Abstract:Different classes of safe reinforcement learning algorithms have shown satisfactory performance in various types of safety requirement scenarios. However, the existing methods mainly address one or several classes of specific safety requirement scenario problems and cannot be applied to arbitrary safety requirement scenarios. In addition, the optimization objectives of existing reinforcement learning algorithms are misaligned with the task requirements. Based on the need to address these issues, we propose $\mathrm{E^{2}CFD}$, an effective and efficient cost function design framework. $\mathrm{E^{2}CFD}$ leverages the capabilities of a large language model (LLM) to comprehend various safety scenarios and generate corresponding cost functions. It incorporates the \textit{fast performance evaluation (FPE)} method to facilitate rapid and iterative updates to the generated cost function. Through this iterative process, $\mathrm{E^{2}CFD}$ aims to obtain the most suitable cost function for policy training, tailored to the specific tasks within the safety scenario. Experiments have proven that the performance of policies trained using this framework is superior to traditional safe reinforcement learning algorithms and policies trained with carefully designed cost functions.
Abstract:Fabric manipulation dynamically is commonly seen in manufacturing and domestic settings. While dynamically manipulating a fabric piece to reach a target state is highly efficient, this task presents considerable challenges due to the varying properties of different fabrics, complex dynamics when interacting with environments, and meeting required goal conditions. To address these challenges, we present \textit{One Fling to Goal}, an algorithm capable of handling fabric pieces with diverse shapes and physical properties across various scenarios. Our method learns a graph-based dynamics model equipped with environmental awareness. With this dynamics model, we devise a real-time controller to enable high-speed fabric manipulation in one attempt, requiring less than 3 seconds to finish the goal-conditioned task. We experimentally validate our method on a goal-conditioned manipulation task in five diverse scenarios. Our method significantly improves this goal-conditioned task, achieving an average error of 13.2mm in complex scenarios. Our method can be seamlessly transferred to real-world robotic systems and generalized to unseen scenarios in a zero-shot manner.
Abstract:LiDAR-based sparse 3D object detection plays a crucial role in autonomous driving applications due to its computational efficiency advantages. Existing methods either use the features of a single central voxel as an object proxy, or treat an aggregated cluster of foreground points as an object proxy. However, the former lacks the ability to aggregate contextual information, resulting in insufficient information expression in object proxies. The latter relies on multi-stage pipelines and auxiliary tasks, which reduce the inference speed. To maintain the efficiency of the sparse framework while fully aggregating contextual information, in this work, we propose SparseDet which designs sparse queries as object proxies. It introduces two key modules, the Local Multi-scale Feature Aggregation (LMFA) module and the Global Feature Aggregation (GFA) module, aiming to fully capture the contextual information, thereby enhancing the ability of the proxies to represent objects. Where LMFA sub-module achieves feature fusion across different scales for sparse key voxels %which does this through via coordinate transformations and using nearest neighbor relationships to capture object-level details and local contextual information, GFA sub-module uses self-attention mechanisms to selectively aggregate the features of the key voxels across the entire scene for capturing scene-level contextual information. Experiments on nuScenes and KITTI demonstrate the effectiveness of our method. Specifically, on nuScene, SparseDet surpasses the previous best sparse detector VoxelNeXt by 2.2\% mAP with 13.5 FPS, and on KITTI, it surpasses VoxelNeXt by 1.12\% $\mathbf{AP_{3D}}$ on hard level tasks with 17.9 FPS.
Abstract:Recently, 3D assets created via reconstruction and generation have matched the quality of manually crafted assets, highlighting their potential for replacement. However, this potential is largely unrealized because these assets always need to be converted to meshes for 3D industry applications, and the meshes produced by current mesh extraction methods are significantly inferior to Artist-Created Meshes (AMs), i.e., meshes created by human artists. Specifically, current mesh extraction methods rely on dense faces and ignore geometric features, leading to inefficiencies, complicated post-processing, and lower representation quality. To address these issues, we introduce MeshAnything, a model that treats mesh extraction as a generation problem, producing AMs aligned with specified shapes. By converting 3D assets in any 3D representation into AMs, MeshAnything can be integrated with various 3D asset production methods, thereby enhancing their application across the 3D industry. The architecture of MeshAnything comprises a VQ-VAE and a shape-conditioned decoder-only transformer. We first learn a mesh vocabulary using the VQ-VAE, then train the shape-conditioned decoder-only transformer on this vocabulary for shape-conditioned autoregressive mesh generation. Our extensive experiments show that our method generates AMs with hundreds of times fewer faces, significantly improving storage, rendering, and simulation efficiencies, while achieving precision comparable to previous methods.
Abstract:2D diffusion model, which often contains unwanted baked-in shading effects and results in unrealistic rendering effects in the downstream applications. Generating Physically Based Rendering (PBR) materials instead of just RGB textures would be a promising solution. However, directly distilling the PBR material parameters from 2D diffusion models still suffers from incorrect material decomposition, such as baked-in shading effects in albedo. We introduce DreamMat, an innovative approach to resolve the aforementioned problem, to generate high-quality PBR materials from text descriptions. We find out that the main reason for the incorrect material distillation is that large-scale 2D diffusion models are only trained to generate final shading colors, resulting in insufficient constraints on material decomposition during distillation. To tackle this problem, we first finetune a new light-aware 2D diffusion model to condition on a given lighting environment and generate the shading results on this specific lighting condition. Then, by applying the same environment lights in the material distillation, DreamMat can generate high-quality PBR materials that are not only consistent with the given geometry but also free from any baked-in shading effects in albedo. Extensive experiments demonstrate that the materials produced through our methods exhibit greater visual appeal to users and achieve significantly superior rendering quality compared to baseline methods, which are preferable for downstream tasks such as game and film production.
Abstract:In the field of 3D object detection tasks, fusing heterogeneous features from LiDAR and camera sensors into a unified Bird's Eye View (BEV) representation is a widely adopted paradigm. However, existing methods are often compromised by imprecise sensor calibration, resulting in feature misalignment in LiDAR-camera BEV fusion. Moreover, such inaccuracies result in errors in depth estimation for the camera branch, ultimately causing misalignment between LiDAR and camera BEV features. In this work, we propose a novel ContrastAlign approach that utilizes contrastive learning to enhance the alignment of heterogeneous modalities, thereby improving the robustness of the fusion process. Specifically, our approach includes the L-Instance module, which directly outputs LiDAR instance features within LiDAR BEV features. Then, we introduce the C-Instance module, which predicts camera instance features through RoI (Region of Interest) pooling on the camera BEV features. We propose the InstanceFusion module, which utilizes contrastive learning to generate similar instance features across heterogeneous modalities. We then use graph matching to calculate the similarity between the neighboring camera instance features and the similarity instance features to complete the alignment of instance features. Our method achieves state-of-the-art performance, with an mAP of 70.3%, surpassing BEVFusion by 1.8% on the nuScenes validation set. Importantly, our method outperforms BEVFusion by 7.3% under conditions with misalignment noise.
Abstract:The remarkable generative capabilities of diffusion models have motivated extensive research in both image and video editing. Compared to video editing which faces additional challenges in the time dimension, image editing has witnessed the development of more diverse, high-quality approaches and more capable software like Photoshop. In light of this gap, we introduce a novel and generic solution that extends the applicability of image editing tools to videos by propagating edits from a single frame to the entire video using a pre-trained image-to-video model. Our method, dubbed I2VEdit, adaptively preserves the visual and motion integrity of the source video depending on the extent of the edits, effectively handling global edits, local edits, and moderate shape changes, which existing methods cannot fully achieve. At the core of our method are two main processes: Coarse Motion Extraction to align basic motion patterns with the original video, and Appearance Refinement for precise adjustments using fine-grained attention matching. We also incorporate a skip-interval strategy to mitigate quality degradation from auto-regressive generation across multiple video clips. Experimental results demonstrate our framework's superior performance in fine-grained video editing, proving its capability to produce high-quality, temporally consistent outputs.
Abstract:V2X cooperation, through the integration of sensor data from both vehicles and infrastructure, is considered a pivotal approach to advancing autonomous driving technology. Current research primarily focuses on enhancing perception accuracy, often overlooking the systematic improvement of accident prediction accuracy through end-to-end learning, leading to insufficient attention to the safety issues of autonomous driving. To address this challenge, this paper introduces the UniE2EV2X framework, a V2X-integrated end-to-end autonomous driving system that consolidates key driving modules within a unified network. The framework employs a deformable attention-based data fusion strategy, effectively facilitating cooperation between vehicles and infrastructure. The main advantages include: 1) significantly enhancing agents' perception and motion prediction capabilities, thereby improving the accuracy of accident predictions; 2) ensuring high reliability in the data fusion process; 3) superior end-to-end perception compared to modular approaches. Furthermore, We implement the UniE2EV2X framework on the challenging DeepAccident, a simulation dataset designed for V2X cooperative driving.