Abstract:Large Language Models (LLMs) have demonstrated exceptional task-solving capabilities, increasingly adopting roles akin to human-like assistants. The broader integration of LLMs into society has sparked interest in whether they manifest psychological attributes, and whether these attributes are stable-inquiries that could deepen the understanding of their behaviors. Inspired by psychometrics, this paper presents a framework for investigating psychology in LLMs, including psychological dimension identification, assessment dataset curation, and assessment with results validation. Following this framework, we introduce a comprehensive psychometrics benchmark for LLMs that covers six psychological dimensions: personality, values, emotion, theory of mind, motivation, and intelligence. This benchmark includes thirteen datasets featuring diverse scenarios and item types. Our findings indicate that LLMs manifest a broad spectrum of psychological attributes. We also uncover discrepancies between LLMs' self-reported traits and their behaviors in real-world scenarios. This paper demonstrates a thorough psychometric assessment of LLMs, providing insights into reliable evaluation and potential applications in AI and social sciences.
Abstract:Large Language Models (LLMs) have garnered significant attention due to their remarkable ability to process information across various languages. Despite their capabilities, they exhibit inconsistencies in handling identical queries in different languages, presenting challenges for further advancement. This paper introduces a method to enhance the multilingual performance of LLMs by aggregating knowledge from diverse languages. This approach incorporates a low-resource knowledge detector specific to a language, a language selection process, and mechanisms for answer replacement and integration. Our experiments demonstrate notable performance improvements, particularly in reducing language performance disparity. An ablation study confirms that each component of our method significantly contributes to these enhancements. This research highlights the inherent potential of LLMs to harmonize multilingual capabilities and offers valuable insights for further exploration.
Abstract:Single-image relighting is a challenging task that involves reasoning about the complex interplay between geometry, materials, and lighting. Many prior methods either support only specific categories of images, such as portraits, or require special capture conditions, like using a flashlight. Alternatively, some methods explicitly decompose a scene into intrinsic components, such as normals and BRDFs, which can be inaccurate or under-expressive. In this work, we propose a novel end-to-end 2D relighting diffusion model, called Neural Gaffer, that takes a single image of any object and can synthesize an accurate, high-quality relit image under any novel environmental lighting condition, simply by conditioning an image generator on a target environment map, without an explicit scene decomposition. Our method builds on a pre-trained diffusion model, and fine-tunes it on a synthetic relighting dataset, revealing and harnessing the inherent understanding of lighting present in the diffusion model. We evaluate our model on both synthetic and in-the-wild Internet imagery and demonstrate its advantages in terms of generalization and accuracy. Moreover, by combining with other generative methods, our model enables many downstream 2D tasks, such as text-based relighting and object insertion. Our model can also operate as a strong relighting prior for 3D tasks, such as relighting a radiance field.
Abstract:3D Gaussian splatting has demonstrated impressive performance in real-time novel view synthesis. However, achieving successful reconstruction from RGB images generally requires multiple input views captured under static conditions. To address the challenge of sparse input views, previous approaches have incorporated depth supervision into the training of 3D Gaussians to mitigate overfitting, using dense predictions from pretrained depth networks as pseudo-ground truth. Nevertheless, depth predictions from monocular depth estimation models inherently exhibit significant uncertainty in specific areas. Relying solely on pixel-wise L2 loss may inadvertently incorporate detrimental noise from these uncertain areas. In this work, we introduce a novel method to supervise the depth distribution of 3D Gaussians, utilizing depth priors with integrated uncertainty estimates. To address these localized errors in depth predictions, we integrate a patch-wise optimal transport strategy to complement traditional L2 loss in depth supervision. Extensive experiments conducted on the LLFF, DTU, and Blender datasets demonstrate that our approach, UGOT, achieves superior novel view synthesis and consistently outperforms state-of-the-art methods.
Abstract:Forecasting future scenarios in dynamic environments is essential for intelligent decision-making and navigation, a challenge yet to be fully realized in computer vision and robotics. Traditional approaches like video prediction and novel-view synthesis either lack the ability to forecast from arbitrary viewpoints or to predict temporal dynamics. In this paper, we introduce GaussianPrediction, a novel framework that empowers 3D Gaussian representations with dynamic scene modeling and future scenario synthesis in dynamic environments. GaussianPrediction can forecast future states from any viewpoint, using video observations of dynamic scenes. To this end, we first propose a 3D Gaussian canonical space with deformation modeling to capture the appearance and geometry of dynamic scenes, and integrate the lifecycle property into Gaussians for irreversible deformations. To make the prediction feasible and efficient, a concentric motion distillation approach is developed by distilling the scene motion with key points. Finally, a Graph Convolutional Network is employed to predict the motions of key points, enabling the rendering of photorealistic images of future scenarios. Our framework shows outstanding performance on both synthetic and real-world datasets, demonstrating its efficacy in predicting and rendering future environments.
Abstract:Recently, we have witnessed the explosive growth of various volumetric representations in modeling animatable head avatars. However, due to the diversity of frameworks, there is no practical method to support high-level applications like 3D head avatar editing across different representations. In this paper, we propose a generic avatar editing approach that can be universally applied to various 3DMM driving volumetric head avatars. To achieve this goal, we design a novel expression-aware modification generative model, which enables lift 2D editing from a single image to a consistent 3D modification field. To ensure the effectiveness of the generative modification process, we develop several techniques, including an expression-dependent modification distillation scheme to draw knowledge from the large-scale head avatar model and 2D facial texture editing tools, implicit latent space guidance to enhance model convergence, and a segmentation-based loss reweight strategy for fine-grained texture inversion. Extensive experiments demonstrate that our method delivers high-quality and consistent results across multiple expression and viewpoints. Project page: https://zju3dv.github.io/geneavatar/
Abstract:Swarm robots have sparked remarkable developments across a range of fields. While it is necessary for various applications in swarm robots, a fast and robust coordinate initialization in vision-based drone swarms remains elusive. To this end, our paper proposes a complete system to recover a swarm's initial relative pose on platforms with size, weight, and power (SWaP) constraints. To overcome limited coverage of field-of-view (FoV), the drones rotate in place to obtain observations. To tackle the anonymous measurements, we formulate a non-convex rotation estimation problem and transform it into a semi-definite programming (SDP) problem, which can steadily obtain global optimal values. Then we utilize the Hungarian algorithm to recover relative translation and correspondences between observations and drone identities. To safely acquire complete observations, we actively search for positions and generate feasible trajectories to avoid collisions. To validate the practicability of our system, we conduct experiments on a vision-based drone swarm with only stereo cameras and inertial measurement units (IMUs) as sensors. The results demonstrate that the system can robustly get accurate relative poses in real time with limited onboard computation resources. The source code is released.
Abstract:Sora is a text-to-video generative AI model, released by OpenAI in February 2024. The model is trained to generate videos of realistic or imaginative scenes from text instructions and show potential in simulating the physical world. Based on public technical reports and reverse engineering, this paper presents a comprehensive review of the model's background, related technologies, applications, remaining challenges, and future directions of text-to-video AI models. We first trace Sora's development and investigate the underlying technologies used to build this "world simulator". Then, we describe in detail the applications and potential impact of Sora in multiple industries ranging from film-making and education to marketing. We discuss the main challenges and limitations that need to be addressed to widely deploy Sora, such as ensuring safe and unbiased video generation. Lastly, we discuss the future development of Sora and video generation models in general, and how advancements in the field could enable new ways of human-AI interaction, boosting productivity and creativity of video generation.
Abstract:Synergies between advanced communications, computing and artificial intelligence are unraveling new directions of coordinated operation and resiliency in microgrids. On one hand, coordination among sources is facilitated by distributed, privacy-minded processing at multiple locations, whereas on the other hand, it also creates exogenous data arrival paths for adversaries that can lead to cyber-physical attacks amongst other reliability issues in the communication layer. This long-standing problem necessitates new intrinsic ways of exchanging information between converters through power lines to optimize the system's control performance. Going beyond the existing power and data co-transfer technologies that are limited by efficiency and scalability concerns, this paper proposes neuromorphic learning to implant communicative features using spiking neural networks (SNNs) at each node, which is trained collaboratively in an online manner simply using the power exchanges between the nodes. As opposed to the conventional neuromorphic sensors that operate with spiking signals, we employ an event-driven selective process to collect sparse data for training of SNNs. Finally, its multi-fold effectiveness and reliable performance is validated under simulation conditions with different microgrid topologies and components to establish a new direction in the sense-actuate-compute cycle for power electronic dominated grids and microgrids.
Abstract:Designing protein sequences with specific biological functions and structural stability is crucial in biology and chemistry. Generative models already demonstrated their capabilities for reliable protein design. However, previous models are limited to the unconditional generation of protein sequences and lack the controllable generation ability that is vital to biological tasks. In this work, we propose TaxDiff, a taxonomic-guided diffusion model for controllable protein sequence generation that combines biological species information with the generative capabilities of diffusion models to generate structurally stable proteins within the sequence space. Specifically, taxonomic control information is inserted into each layer of the transformer block to achieve fine-grained control. The combination of global and local attention ensures the sequence consistency and structural foldability of taxonomic-specific proteins. Extensive experiments demonstrate that TaxDiff can consistently achieve better performance on multiple protein sequence generation benchmarks in both taxonomic-guided controllable generation and unconditional generation. Remarkably, the sequences generated by TaxDiff even surpass those produced by direct-structure-generation models in terms of confidence based on predicted structures and require only a quarter of the time of models based on the diffusion model. The code for generating proteins and training new versions of TaxDiff is available at:https://github.com/Linzy19/TaxDiff.