Search

In this paper, we introduce the Generalist Virtual Agent (GVA), an autonomous entity engineered to function across diverse digital platforms and environments, assisting users by executing a variety of tasks. This survey delves into the evolution of GVAs, tracing their progress from early intelligent assistants to contemporary implementations that incorporate large-scale models. We explore both the philosophical underpinnings and practical foundations of GVAs, addressing their developmental challenges and the methodologies currently employed in their design and operation. By presenting a detailed taxonomy of GVA environments, tasks, and capabilities, this paper aims to bridge the theoretical and practical aspects of GVAs, concluding those that operate in environments closely mirroring the real world are more likely to demonstrate human-like intelligence. We discuss potential future directions for GVA research, highlighting the necessity for realistic evaluation metrics and the enhancement of long-sequence decision-making capabilities to advance the field toward more systematic or embodied applications. This work not only synthesizes the existing body of literature but also proposes frameworks for future investigations, contributing significantly to the ongoing development of intelligent systems.

Sleep monitoring plays a crucial role in maintaining good health, with sleep staging serving as an essential metric in the monitoring process. Traditional methods, utilizing medical sensors like EEG and ECG, can be effective but often present challenges such as unnatural user experience, complex deployment, and high costs. Ballistocardiography~(BCG), a type of piezoelectric sensor signal, offers a non-invasive, user-friendly, and easily deployable alternative for long-term home monitoring. However, reliable BCG-based sleep staging is challenging due to the limited sleep monitoring data available for BCG. A restricted training dataset prevents the model from generalization across populations. Additionally, transferring to BCG faces difficulty ensuring model robustness when migrating from other data sources. To address these issues, we introduce SleepNetZero, a zero-shot learning based approach for sleep staging. To tackle the generalization challenge, we propose a series of BCG feature extraction methods that align BCG components with corresponding respiratory, cardiac, and movement channels in PSG. This allows models to be trained on large-scale PSG datasets that are diverse in population. For the migration challenge, we employ data augmentation techniques, significantly enhancing generalizability. We conducted extensive training and testing on large datasets~(12393 records from 9637 different subjects), achieving an accuracy of 0.803 and a Cohen's Kappa of 0.718. ZeroSleepNet was also deployed in real prototype~(monitoring pads) and tested in actual hospital settings~(265 users), demonstrating an accuracy of 0.697 and a Cohen's Kappa of 0.589. To the best of our knowledge, this work represents the first known reliable BCG-based sleep staging effort and marks a significant step towards in-home health monitoring., Comment: 25 pages

Real-world DeepFake videos often undergo various compression operations, resulting in a range of video qualities. These varying qualities diversify the pattern of forgery traces, significantly increasing the difficulty of DeepFake detection. To address this challenge, we introduce a new Dual Progressive Learning (DPL) framework for cross-quality DeepFake detection. We liken this task to progressively drilling for underground water, where low-quality videos require more effort than high-quality ones. To achieve this, we develop two sequential-based branches to "drill waters" with different efforts. The first branch progressively excavates the forgery traces according to the levels of video quality, i.e., time steps, determined by a dedicated CLIP-based indicator. In this branch, a Feature Selection Module is designed to adaptively assign appropriate features to the corresponding time steps. Considering that different techniques may introduce varying forgery traces within the same video quality, we design a second branch targeting forgery identifiability as complementary. This branch operates similarly and shares the feature selection module with the first branch. Our design takes advantage of the sequential model where computational units share weights across different time steps and can memorize previous progress, elegantly achieving progressive learning while maintaining reasonable memory costs. Extensive experiments demonstrate the superiority of our method for cross-quality DeepFake detection., Comment: ACCV 2024

Representation learning on text-attributed graphs (TAGs) is vital for real-world applications, as they combine semantic textual and contextual structural information. Research in this field generally consist of two main perspectives: local-level encoding and global-level aggregating, respectively refer to textual node information unification (e.g., using Language Models) and structure-augmented modeling (e.g., using Graph Neural Networks). Most existing works focus on combining different information levels but overlook the interconnections, i.e., the contextual textual information among nodes, which provides semantic insights to bridge local and global levels. In this paper, we propose GraphBridge, a multi-granularity integration framework that bridges local and global perspectives by leveraging contextual textual information, enhancing fine-grained understanding of TAGs. Besides, to tackle scalability and efficiency challenges, we introduce a graphaware token reduction module. Extensive experiments across various models and datasets show that our method achieves state-of-theart performance, while our graph-aware token reduction module significantly enhances efficiency and solves scalability issues., Comment: Accepted by EMNLP 2024(Main)

Sequential DeepFake detection is an emerging task that predicts the manipulation sequence in order. Existing methods typically formulate it as an image-to-sequence problem, employing conventional Transformer architectures. However, these methods lack dedicated design and consequently result in limited performance. As such, this paper describes a new Transformer design, called TSOM, by exploring three perspectives: Texture, Shape, and Order of Manipulations. Our method features four major improvements: \ding{182} we describe a new texture-aware branch that effectively captures subtle manipulation traces with a Diversiform Pixel Difference Attention module. \ding{183} Then we introduce a Multi-source Cross-attention module to seek deep correlations among spatial and sequential features, enabling effective modeling of complex manipulation traces. \ding{184} To further enhance the cross-attention, we describe a Shape-guided Gaussian mapping strategy, providing initial priors of the manipulation shape. \ding{185} Finally, observing that the subsequent manipulation in a sequence may influence traces left in the preceding one, we intriguingly invert the prediction order from forward to backward, leading to notable gains as expected. Extensive experimental results demonstrate that our method outperforms others by a large margin, highlighting the superiority of our method., Comment: WACV 2024

This letter proposes a novel hybrid automatic repeat request with chase combining assisted sparse code multiple access (HARQ-CC-SCMA) scheme. Depending on whether the same superimposed packet are retransmitted, synchronous and asynchronous modes are considered for retransmissions. Moreover, factor graph aggregation (FGA) and Log-likelihood ratio combination (LLRC) are proposed for multi-user detection. Regarding FGA, a large-scale factor graph is constructed by combining all the received superimposed signals and message passing algorithm (MAP) is applied to calculate log-likelihood ratio (LLR). Whereas, owing to the same unsuccessful messages required to be retransmitted, LLRC adds up LLRs of erroneously received packets in previous HARQ rounds together with currently received packets for channel decoding and saves the LLRs for failed users. Finally, Monte Carlo simulations are preformed to show that FGA surpasses LLRC and HARQ with incremental redundancy (HARQ-IR) in synchronous mode. However, LLRC performs better than FGA at low signal-to-noise ratio (SNR) in asynchronous mode. This is because failed messages after the maximum allowable HARQ rounds in this mode can yield significant error propagation in low SNR regime.

We present a large language model (LLM) based system to empower quadrupedal robots with problem-solving abilities for long-horizon tasks beyond short-term motions. Long-horizon tasks for quadrupeds are challenging since they require both a high-level understanding of the semantics of the problem for task planning and a broad range of locomotion and manipulation skills to interact with the environment. Our system builds a high-level reasoning layer with large language models, which generates hybrid discrete-continuous plans as robot code from task descriptions. It comprises multiple LLM agents: a semantic planner for sketching a plan, a parameter calculator for predicting arguments in the plan, and a code generator to convert the plan into executable robot code. At the low level, we adopt reinforcement learning to train a set of motion planning and control skills to unleash the flexibility of quadrupeds for rich environment interactions. Our system is tested on long-horizon tasks that are infeasible to complete with one single skill. Simulation and real-world experiments show that it successfully figures out multi-step strategies and demonstrates non-trivial behaviors, including building tools or notifying a human for help. Demos are available on our project page: https://sites.google.com/view/long-horizon-robot.

Model-free reinforcement learning is a promising approach for autonomously solving challenging robotics control problems, but faces exploration difficulty without information of the robot's kinematics and dynamics morphology. The under-exploration of multiple modalities with symmetric states leads to behaviors that are often unnatural and sub-optimal. This issue becomes particularly pronounced in the context of robotic systems with morphological symmetries, such as legged robots for which the resulting asymmetric and aperiodic behaviors compromise performance, robustness, and transferability to real hardware. To mitigate this challenge, we can leverage symmetry to guide and improve the exploration in policy learning via equivariance/invariance constraints. In this paper, we investigate the efficacy of two approaches to incorporate symmetry: modifying the network architectures to be strictly equivariant/invariant, and leveraging data augmentation to approximate equivariant/invariant actor-critics. We implement the methods on challenging loco-manipulation and bipedal locomotion tasks and compare with an unconstrained baseline. We find that the strictly equivariant policy consistently outperforms other methods in sample efficiency and task performance in simulation. In addition, symmetry-incorporated approaches exhibit better gait quality, higher robustness and can be deployed zero-shot in real-world experiments.

This paper focuses on the challenge of jointly optimizing location and path loss exponent (PLE) in distance-dependent noise. Departing from the conventional independent noise model used in localization and path loss exponent estimation problems, we consider a more realistic model incorporating distance-dependent noise variance, as revealed in recent theoretical analyses and experimental results. The distance-dependent noise introduces a complex noise model with unknown noise power and PLE, resulting in an exceptionally challenging non-convex and nonlinear optimization problem. In this study, we address a joint localization and path loss exponent estimation problem encompassing distance-dependent noise, unknown parameters, and uncertainties in sensor node locations. To surmount the intractable nonlinear and non-convex objective function inherent in the problem, we introduce a variational Bayesian learning-based framework that enables the joint optimization of localization, path loss exponent, and reference noise parameters by leveraging an effective approximation to the true posterior distribution. Furthermore, the proposed joint learning algorithm provides an iterative closed-form solution and exhibits superior performance in terms of computational complexity compared to existing algorithms. Computer simulation results demonstrate that the proposed algorithm approaches the performance of the Bayesian Cramer-Rao bound (BCRB), achieves localization performance comparable to the (maximum likelihood-Gaussian message passing) ML-GMP algorithm in some cases, and outperforms the other comparison algorithm in all cases.

The emerging immersive and autonomous services have posed stringent requirements on both communications and localization. By considering the great potential of reconfigurable intelligent surface (RIS), this paper focuses on the joint channel estimation and localization for RIS-aided wireless systems. As opposed to existing works that treat channel estimation and localization independently, this paper exploits the intrinsic coupling and nonlinear relationships between the channel parameters and user location for enhancement of both localization and channel reconstruction. By noticing the non-convex, nonlinear objective function and the sparser angle pattern, a variational Bayesian learning-based framework is developed to jointly estimate the channel parameters and user location through leveraging an effective approximation of the posterior distribution. The proposed framework is capable of unifying near-field and far-field scenarios owing to exploitation of sparsity of the angular domain. Since the joint channel and location estimation problem has a closed-form solution in each iteration, our proposed iterative algorithm performs better than the conventional particle swarm optimization (PSO) and maximum likelihood (ML) based ones in terms of computational complexity. Simulations demonstrate that the proposed algorithm almost reaches the Bayesian Cramer-Rao bound (BCRB) and achieves a superior estimation accuracy by comparing to the PSO and the ML algorithms.

Can a quadrupedal robot perform bipedal motions like humans? Although developing human-like behaviors is more often studied on costly bipedal robot platforms, we present a solution over a lightweight quadrupedal robot that unlocks the agility of the quadruped in an upright standing pose and is capable of a variety of human-like motions. Our framework is with a hierarchical structure. At the low level is a motion-conditioned control policy that allows the quadrupedal robot to track desired base and front limb movements while balancing on two hind feet. The policy is commanded by a high-level motion generator that gives trajectories of parameterized human-like motions to the robot from multiple modalities of human input. We for the first time demonstrate various bipedal motions on a quadrupedal robot, and showcase interesting human-robot interaction modes including mimicking human videos, following natural language instructions, and physical interaction. The video is available at https://sites.google.com/view/bipedal-motions-quadruped., Comment: Camera ready for ICRA 2024

Learning Nash equilibrium (NE) in complex zero-sum games with multi-agent reinforcement learning (MARL) can be extremely computationally expensive. Curriculum learning is an effective way to accelerate learning, but an under-explored dimension for generating a curriculum is the difficulty-to-learn of the subgames -- games induced by starting from a specific state. In this work, we present a novel subgame curriculum learning framework for zero-sum games. It adopts an adaptive initial state distribution by resetting agents to some previously visited states where they can quickly learn to improve performance. Building upon this framework, we derive a subgame selection metric that approximates the squared distance to NE values and further adopt a particle-based state sampler for subgame generation. Integrating these techniques leads to our new algorithm, Subgame Automatic Curriculum Learning (SACL), which is a realization of the subgame curriculum learning framework. SACL can be combined with any MARL algorithm such as MAPPO. Experiments in the particle-world environment and Google Research Football environment show SACL produces much stronger policies than baselines. In the challenging hide-and-seek quadrant environment, SACL produces all four emergent stages and uses only half the samples of MAPPO with self-play. The project website is at https://sites.google.com/view/sacl-rl.

Many physical, biological, and social systems exhibit emergent properties that arise from the interactions between their components (cells). In this study, we systematically treat every-pair interactions (a) that exhibit power-law dependence on the Euclidean distance and (b) act in structures that can be characterized using fractal geometry. We analytically derive the mean interaction field of the cells and find that (i) in a long-range interaction regime, the mean interaction field increases following a power law with the size of the system, (ii) in a short-range interaction regime, the field saturates, and (iii) in the intermediate range it follows a logarithmic behaviour. To validate our analytical solution, we perform numerical simulations. In the case of short-range interactions, we observe that discreteness significantly impacts the continuum approximation used in the derivation, leading to incorrect asymptotic behaviour in this regime. To address this issue, we propose an expansion that substantially improves the accuracy of the analytical expression. Furthermore, our results motivate us to explore a framework for estimating the fractal dimension of unknown structures. This approach offers an alternative to established methods such as box-counting or sandbox methods. Overall, we believe that our analytical work will have broad applicability in systems where every-pair interactions play a crucial role. The insights gained from this study can contribute to a better understanding of various complex systems and facilitate more accurate modelling and analysis in a wide range of disciplines.

Grounded understanding of natural language in physical scenes can greatly benefit robots that follow human instructions. In object manipulation scenarios, existing end-to-end models are proficient at understanding semantic concepts, but typically cannot handle complex instructions involving spatial relations among multiple objects. which require both reasoning object-level spatial relations and learning precise pixel-level manipulation affordances. We take an initial step to this challenge with a decoupled two-stage solution. In the first stage, we propose an object-centric semantic-spatial reasoner to select which objects are relevant for the language instructed task. The segmentation of selected objects are then fused as additional input to the affordance learning stage. Simply incorporating the inductive bias of relevant objects to a vision-language affordance learning agent can effectively boost its performance in a custom testbed designed for object manipulation with spatial-related language instructions., Comment: AAAI 2023 RL Ready for Production Workshop

We consider the problem of cooperative exploration where multiple robots need to cooperatively explore an unknown region as fast as possible. Multi-agent reinforcement learning (MARL) has recently become a trending paradigm for solving this challenge. However, existing MARL-based methods adopt action-making steps as the metric for exploration efficiency by assuming all the agents are acting in a fully synchronous manner: i.e., every single agent produces an action simultaneously and every single action is executed instantaneously at each time step. Despite its mathematical simplicity, such a synchronous MARL formulation can be problematic for real-world robotic applications. It can be typical that different robots may take slightly different wall-clock times to accomplish an atomic action or even periodically get lost due to hardware issues. Simply waiting for every robot being ready for the next action can be particularly time-inefficient. Therefore, we propose an asynchronous MARL solution, Asynchronous Coordination Explorer (ACE), to tackle this real-world challenge. We first extend a classical MARL algorithm, multi-agent PPO (MAPPO), to the asynchronous setting and additionally apply action-delay randomization to enforce the learned policy to generalize better to varying action delays in the real world. Moreover, each navigation agent is represented as a team-size-invariant CNN-based policy, which greatly benefits real-robot deployment by handling possible robot lost and allows bandwidth-efficient intra-agent communication through low-dimensional CNN features. We first validate our approach in a grid-based scenario. Both simulation and real-robot results show that ACE reduces over 10% actual exploration time compared with classical approaches. We also apply our framework to a high-fidelity visual-based environment, Habitat, achieving 28% improvement in exploration efficiency., Comment: This paper is accepted by AAMAS 2023. The source code can be found in https://github.com/yang-xy20/async_mappo

Although terahertz (THz) communications can provide mobile broadband services, it usually has a large path loss and is vulnerable to antenna misalignment. This significantly degrades the reception reliability. To address this issue, the hybrid automatic repeat request (HARQ) is proposed to further enhance the reliability of THz communications. This paper provides an in-depth investigation on the outage performance of two different types of HARQ-aided THz communications, including Type-I HARQ and HARQ with chase combining (HARQ-CC). Moreover, the effects of both fading and stochastic antenna misalignment are considered in this paper. The exact outage probabilities of HARQ-aided THz communications are derived in closed-form, with which the asymptotic outage analysis is enabled to explore helpful insights. In particular, it is revealed that full time diversity can be achieved by using HARQ assisted schemes. Besides, the HARQ-CC-aided scheme performs better than the Type-I HARQ-aided one due to its high diversity combining gain. The analytical results are eventually validated via Monte-Carlo simulations.

It has been a recent trend to leverage the power of supervised learning (SL) towards more effective reinforcement learning (RL) methods. We propose a novel phasic approach by alternating online RL and offline SL for tackling sparse-reward goal-conditioned problems. In the online phase, we perform RL training and collect rollout data while in the offline phase, we perform SL on those successful trajectories from the dataset. To further improve sample efficiency, we adopt additional techniques in the online phase including task reduction to generate more feasible trajectories and a value-difference-based intrinsic reward to alleviate the sparse-reward issue. We call this overall algorithm, PhAsic self-Imitative Reduction (PAIR). PAIR substantially outperforms both non-phasic RL and phasic SL baselines on sparse-reward goal-conditioned robotic control problems, including a challenging stacking task. PAIR is the first RL method that learns to stack 6 cubes with only 0/1 success rewards from scratch., Comment: Accepted at ICML 2022

Can a robot autonomously learn to design and construct a bridge from varying-sized blocks without a blueprint? It is a challenging task with long horizon and sparse reward -- the robot has to figure out physically stable design schemes and feasible actions to manipulate and transport blocks. Due to diverse block sizes, the state space and action trajectories are vast to explore. In this paper, we propose a hierarchical approach for this problem. It consists of a reinforcement-learning designer to propose high-level building instructions and a motion-planning-based action generator to manipulate blocks at the low level. For high-level learning, we develop a novel technique, prioritized memory resetting (PMR) to improve exploration. PMR adaptively resets the state to those most critical configurations from a replay buffer so that the robot can resume training on partial architectures instead of from scratch. Furthermore, we augment PMR with auxiliary training objectives and fine-tune the designer with the locomotion generator. Our experiments in simulation and on a real deployed robotic system demonstrate that it is able to effectively construct bridges with blocks of varying sizes at a high success rate. Demos can be found at https://sites.google.com/view/bridge-pmr., Comment: To be published in ICRA 2022