AAAI 2024 Papers

Generating realistic human motion from given action descriptions has experienced significant advancements because of the emerging requirement of digital humans. While recent works have achieved impressive results in generating motion directly from textual action descriptions, they often support only a single modality of the control signal, which limits their application in the real digital human industry. This paper presents a Motion General-Purpose generaTor (MotionGPT) that can use multimodal control signals, e.g., text and single-frame poses, for generating consecutive human motions by treating multimodal signals as special input tokens in large language models (LLMs). Specifically, we first quantize multimodal control signals into discrete codes and then formulate them in a unified prompt instruction to ask the LLMs to generate the motion answer. Our MotionGPT demonstrates a unified human motion generation model with multimodal control signals by tuning a mere 0.4% of LLM parameters. To the best of our knowledge, MotionGPT is the first method to generate human motion by multimodal control signals, which we hope can shed light on this new direction. Visit our webpage at https://qiqiapink.github.io/MotionGPT/.

Motion deblurring can be advanced by exploiting informative features from supplementary sensors such as event cameras, which can capture rich motion information asynchronously with high temporal resolution. Existing event-based motion deblurring methods neither consider the modality redundancy in spatial fusion nor temporal cooperation between events and frames. To tackle these limitations, a novel spatial-temporal collaboration network (STCNet) is proposed for event-based motion deblurring. Firstly, we propose a differential-modality based cross-modal calibration strategy to suppress redundancy for complementarity enhancement, and then bimodal spatial fusion is achieved with an elaborate cross-modal co-attention mechanism to weight the contributions of them for importance balance. Besides, we present a frame-event mutual spatio-temporal attention scheme to alleviate the errors of relying only on frames to compute cross-temporal similarities when the motion blur is significant, and then the spatio-temporal features from both frames and events are aggregated with the custom cross-temporal coordinate attention. Extensive experiments on both synthetic and real-world datasets demonstrate that our method achieves state-of-the-art performance. Project website: https://github.com/wyang-vis/STCNet.

Graphs are typical non-Euclidean data of complex structures. In recent years, Riemannian graph representation learning has emerged as an exciting alternative to Euclidean ones. However, Riemannian methods are still in an early stage: most of them present a single curvature (radius) regardless of structural complexity, suffer from numerical instability due to the exponential/logarithmic map, and lack the ability to capture motif regularity. In light of the issues above, we propose the problem of Motif-aware Riemannian Graph Representation Learning, seeking a numerically stable encoder to capture motif regularity in a diverse-curvature manifold without labels. To this end, we present a novel Motif-aware Riemannian model with Generative-Contrastive learning (MotifRGC), which conducts a minmax game in Riemannian manifold in a self-supervised manner. First, we propose a new type of Riemannian GCN (D-GCN), in which we construct a diverse-curvature manifold by a product layer with the diversified factor, and replace the exponential/logarithmic map by a stable kernel layer. Second, we introduce a motif-aware Riemannian generative-contrastive learning to capture motif regularity in the constructed manifold and learn motif-aware node representation without external labels. Empirical results show the superiority of MofitRGC.

Soft robot design is an intricate field with unique challenges due to its complex and vast search space. In the past literature, evolutionary computation algorithms, including novel probabilistic generative models (PGMs), have shown potential in this realm. However, these methods are sample inefficient and predominantly focus on rigid robots in locomotion tasks, which limit their performance and application in robot design automation. In this work, we propose MorphVAE, an innovative PGM that incorporates a multi-task training scheme and a meticulously crafted sampling technique termed ``continuous natural selection'', aimed at bolstering sample efficiency. This method empowers us to gain insights from assessed samples across diverse tasks and temporal evolutionary stages, while simultaneously maintaining a delicate balance between optimization efficiency and biodiversity. Through extensive experiments in various locomotion and manipulation tasks, we substantiate the efficiency of MorphVAE in generating high-performing and diverse designs, surpassing the performance of competitive baselines.

While there is universal agreement that agents ought to act ethically, there is no agreement as to what constitutes ethical behaviour. To address this problem, recent philosophical approaches to `moral uncertainty' propose aggregation of multiple ethical theories to guide agent behaviour. However, one of the foundational proposals for aggregation - Maximising Expected Choiceworthiness (MEC) - has been criticised as being vulnerable to fanaticism; the problem of an ethical theory dominating agent behaviour despite low credence (confidence) in said theory. Fanaticism thus undermines the `democratic' motivation for accommodating multiple ethical perspectives. The problem of fanaticism has not yet been mathematically defined. Representing moral uncertainty as an instance of social welfare aggregation, this paper contributes to the field of moral uncertainty by 1) formalising the problem of fanaticism as a property of social welfare functionals and 2) providing non-fanatical alternatives to MEC, i.e. Highest k-trimmed Mean and Highest Median.

Monte Carlo Tree Search (MCTS) is an immensely popular search-based framework used for decision making. It is traditionally applied to domains where a perfect simulation model of the environment is available. We study and improve MCTS in the context where the environment model is given but imperfect. We show that the discrepancy between the model and the actual environment can lead to significant performance degradation with standard MCTS. We therefore develop Uncertainty Adapted MCTS (UA-MCTS), a more robust algorithm within the MCTS framework. We estimate the transition uncertainty in the given model, and direct the search towards more certain transitions in the state space. We modify all four MCTS phases to improve the search behavior by considering these estimates. We prove, in the corrupted bandit case, that adding uncertainty information to adapt UCB leads to tighter regret bound than standard UCB. Empirically, we evaluate UA-MCTS and its individual components on the deterministic domains from the MinAtar test suite. Our results demonstrate that UA-MCTS strongly improves MCTS in the presence of model transition errors.

Current parametric models have made notable progress in 3D hand pose and shape estimation. However, due to the fixed hand topology and complex hand poses, current models are hard to generate meshes that are aligned with the image well. To tackle this issue, we introduce a dual noise estimation method in this paper. Given a single-view image as input, we first adopt a baseline parametric regressor to obtain the coarse hand meshes. We assume the mesh vertices and their image-plane projections are noisy, and can be associated in a unified probabilistic model. We then learn the distributions of noise to refine mesh vertices and their projections. The refined vertices are further utilized to refine camera parameters in a closed-form manner. Consequently, our method obtains well-aligned and high-quality 3D hand meshes. Extensive experiments on the large-scale Interhand2.6M dataset demonstrate that the proposed method not only improves the performance of its baseline by more than 10% but also achieves state-of-the-art performance. Project page: https://github.com/hanhuili/DNE4Hand.

We introduce a novel task of 3D visual grounding in monocular RGB images using language descriptions with both appearance and geometry information. Specifically, we build a large-scale dataset, Mono3DRefer, which contains 3D object targets with their corresponding geometric text descriptions, generated by ChatGPT and refined manually. To foster this task, we propose Mono3DVG-TR, an end-to-end transformer-based network, which takes advantage of both the appearance and geometry information in text embeddings for multi-modal learning and 3D object localization. Depth predictor is designed to explicitly learn geometry features. The dual text-guided adapter is proposed to refine multiscale visual and geometry features of the referred object. Based on depth-text-visual stacking attention, the decoder fuses object-level geometric cues and visual appearance into a learnable query. Comprehensive benchmarks and some insightful analyses are provided for Mono3DVG. Extensive comparisons and ablation studies show that our method significantly outperforms all baselines. The dataset and code will be released.

This paper investigates runtime monitoring of perception systems. Perception is a critical component of high-integrity applications of robotics and autonomous systems, such as self-driving cars. In these applications, failure of perception systems may put human life at risk, and a broad adoption of these technologies requires the development of methodologies to guarantee and monitor safe operation. Despite the paramount importance of perception, currently there is no formal approach for system-level perception monitoring. In this paper, we formalize the problem of runtime fault detection and identification in perception systems and present a framework to model diagnostic information using a diagnostic graph. We then provide a set of deterministic, probabilistic, and learning-based algorithms that use diagnostic graphs to perform fault detection and identification. Moreover, we investigate fundamental limits and provide deterministic and probabilistic guarantees on the fault detection and identification results. We conclude the paper with an extensive experimental evaluation, which recreates several realistic failure modes in the LGSVL open-source autonomous driving simulator, and applies the proposed system monitors to a state-of-the-art autonomous driving software stack (Baidu's Apollo Auto). The results show that the proposed system monitors outperform baselines, have the potential of preventing accidents in realistic autonomous driving scenarios, and incur a negligible computational overhead.

In drug development, molecular optimization is a crucial challenge that involves generating novel molecules given a lead molecule as input. The task requires maintaining molecular similarity to the original molecule while simultaneously optimizing multiple chemical attributes. To aid in this process, numerous generative models have been proposed. However, in practical applications, it is crucial for these models not only to generate novel molecules with the above constraints but also to generate molecules that significantly differ from any existing patented compounds. In this work, we present a multi-optimization molecular framework to address this challenge. Our framework trains a model to prioritize both enhanced properties and substantial dissimilarity from patented compounds. By jointly learning continuous representations of optimized and patentable molecules, we ensure that the generated molecules are significantly distant from any patented compounds while improving chemical properties. Through empirical evaluation, we demonstrate the superior performance of our approach compared to state-of-the-art molecular optimization methods both in chemical property optimization and patentability.

Deep learning is now widely used in drug discovery, providing significant acceleration and cost reduction. As the most fundamental building block, molecular representation is essential for predicting molecular properties to enable various downstream applications. Most existing methods attempt to incorporate more information to learn better representations. However, not all features are equally important for a specific task. Ignoring this would potentially compromise the training efficiency and predictive accuracy. To address this issue, we propose a novel approach, which treats language models as an agent and molecular pretraining models as a knowledge base. The agent accentuates task-relevant features in the molecular representation by understanding the natural language description of the task, just as a tailor customizes clothes for clients. Thus, we call this approach MolTailor. Evaluations demonstrate MolTailor's superior performance over baselines, validating the efficacy of enhancing relevance for molecular representation learning. This illustrates the potential of language model guided optimization to better exploit and unleash the capabilities of existing powerful molecular representation methods. Our code and appendix are available at https://github.com/SCIR-HI/MolTailor.

Confidence calibration in Graph Neural Networks (GNNs) aims to align a model's predicted confidence with its actual accuracy. Recent studies have indicated that GNNs exhibit an under-confidence bias, which contrasts the over-confidence bias commonly observed in deep neural networks. However, our deeper investigation into this topic reveals that not all GNNs exhibit this behavior. Upon closer examination of message passing in GNNs, we found a clear link between message aggregation and confidence levels. Specifically, GNNs with extensive message aggregation, often seen in deep architectures or when leveraging large amounts of labeled data, tend to exhibit overconfidence. This overconfidence can be attributed to factors like over-learning and over-smoothing. Conversely, GNNs with fewer layers, known for their balanced message passing and superior node representation, may exhibit under-confidence. To counter these confidence biases, we introduce the Adaptive Unified Label Smoothing (AU-LS) technique. Our experiments show that AU-LS outperforms existing methods, addressing both over and under-confidence in various GNN scenarios.

We propose a novel stereo-confidence that can be measured externally to various stereo-matching networks, offering an alternative input modality choice of the cost volume for learning-based approaches, especially in safety-critical systems. Grounded in the foundational concepts of disparity definition and the disparity plane sweep, the proposed stereo-confidence method is built upon the idea that any shift in a stereo-image pair should be updated in a corresponding amount shift in the disparity map. Based on this idea, the proposed stereo-confidence method can be summarized in three folds. 1) Using the disparity plane sweep, multiple disparity maps can be obtained and treated as a 3-D volume (predicted disparity volume), like the cost volume is constructed. 2) One of these disparity maps serves as an anchor, allowing us to define a desirable (or ideal) disparity profile at every spatial point. 3) By comparing the desirable and predicted disparity profiles, we can quantify the level of matching ambiguity between left and right images for confidence measurement. Extensive experimental results using various stereo-matching networks and datasets demonstrate that the proposed stereo-confidence method not only shows competitive performance on its own but also consistent performance improvements when it is used as an input modality for learning-based stereo-confidence methods.

The ability to combine multiple pieces of existing knowledge to infer new knowledge is both crucial and challenging. In this paper, we explore how facts of various entities are combined in the context of knowledge graph completion (KGC). We use composite reasoning to unify the views from different KGC models, including translational models, tensor factorization (TF)-based models, instance-based learning models, and KGC regularizers. Moreover, our comprehensive examination of composite reasoning revealed an unexpected phenomenon: certain TF-based models learn embeddings with erroneous composite reasoning, which ultimately violates their fundamental collaborative filtering assumption and reduces their effects. This motivates us to reduce their composition error. Empirical evaluations demonstrate that mitigating the composition risk not only enhances the performance of TF-based models across all tested settings, but also surpass or is competitive with the state-of-the-art performance on two out of four benchmarks.

The task of 3D single object tracking (SOT) with LiDAR point clouds is crucial for various applications, such as autonomous driving and robotics. However, existing approaches have primarily relied on appearance matching or motion modeling within only two successive frames, thereby overlooking the long-range continuous motion property of objects in 3D space. To address this issue, this paper presents a novel approach that views each tracklet as a continuous stream: at each timestamp, only the current frame is fed into the network to interact with multi-frame historical features stored in a memory bank, enabling efficient exploitation of sequential information. To achieve effective cross-frame message passing, a hybrid attention mechanism is designed to account for both long-range relation modeling and local geometric feature extraction. Furthermore, to enhance the utilization of multi-frame features for robust tracking, a contrastive sequence enhancement strategy is proposed, which uses ground truth tracklets to augment training sequences and promote discrimination against false positives in a contrastive manner. Extensive experiments demonstrate that the proposed method outperforms the state-of-the-art method by significant margins on multiple benchmarks.

Aspect prediction (AP) and sentiment prediction (SP) are representative applications in fine-grained sentiment anal- ysis. They can be considered as sequential tasks, where AP identifies mentioned aspects in a sentence, and SP infers fine-grained sentiments for these aspects. Recent models perform the aspect-sentiment prediction in a joint man-ner, but heavily rely on the feature interactions of aspect and sentiment. One drawback is that they ignore correlation strength varies between aspect features and sentiment fea- tures across different sentences, and employ a fixed feature interaction strategy may limit effective knowledge transfer across tasks. To tackle this issue, in this paper, we propose an Adaptive Inter-task Feature Interaction framework, AIFI, for joint aspect-sentiment prediction. Specifically, we introduce a novel contrast-based alignment method based on contrastive learning. Our approach considers the AP-specific and SP-specific representations of a given sentence as a positive pair, while representation of another random sentence serves as a negative example. Moreover, we propose an inter-task feature correlation network to predict the contrast strength, which is determined by the temperature coefficient in the InfoNCE loss. This dynamic correlation adjustment enhances model’s ability to capture proper feature interactions more efficiently. Experimental results on three datasets validate the effectiveness of our approach.

High-accuracy positioning has become a fundamental enabler for intelligent connected devices. Nevertheless, the present wireless networks still rely on model-driven approaches to achieve positioning functionality, which are susceptible to performance degradation in practical scenarios, primarily due to hardware impairments. Integrating artificial intelligence into the positioning framework presents a promising solution to revolutionize the accuracy and robustness of location-based services. In this study, we address this challenge by reformulating the problem of angle-of-arrival (AoA) estimation into image reconstruction of spatial spectrum. To this end, we design a model-driven deep neural network (MoD-DNN), which can automatically calibrate the angular-dependent phase error. The proposed MoD-DNN approach employs an iterative optimization scheme between a convolutional neural network and a sparse conjugate gradient algorithm. Simulation and experimental results are presented to demonstrate the effectiveness of the proposed method in enhancing spectrum calibration and AoA estimation.

In data-rich domains such as vision, language, and speech, deep learning prevails to deliver high-performance task-specific models and can even learn general task-agnostic representations for efficient finetuning to downstream tasks. However, deep learning in resource-limited domains still faces multiple challenges including (i) limited data, (ii) constrained model development cost, and (iii) lack of adequate pre-trained models for effective finetuning. This paper provides an overview of model reprogramming to bridge this gap. Model reprogramming enables resource-efficient cross-domain machine learning by repurposing and reusing a well-developed pre-trained model from a source domain to solve tasks in a target domain without model finetuning, where the source and target domains can be vastly different. In many applications, model reprogramming outperforms transfer learning and training from scratch. This paper elucidates the methodology of model reprogramming, summarizes existing use cases, provides a theoretical explanation of the success of model reprogramming, and concludes with a discussion on open-ended research questions and opportunities.

Many decision and optimization problems have natural extensions as counting problems. The best known example is the Boolean satisfiability problem (SAT), where we want to count the satisfying assignments of truth values to the variables, which is known as the #SAT problem. Likewise, for discrete optimization problems, we want to count the states on which the objective function attains the optimal value. Both SAT and discrete optimization can be formulated as selective marginalize a product function (MPF) queries. Here, we show how general selective MPF queries can be extended for model counting. MPF queries are encoded as tensor hypernetworks over suitable semirings that can be solved by generic tensor hypernetwork contraction algorithms. Our model counting extension is again an MPF query, on an extended semiring, that can be solved by the same contraction algorithms. Model counting is required for uniform model sampling. We show how the counting extension can be further extended for model sampling by constructing yet another semiring. We have implemented the model counting and sampling extensions. Experiments show that our generic approach is competitive with the state of the art in model counting and model sampling.