arXiv subjects

Yuan Shen

Publications and source records attributed to Yuan Shen.

At least 55 records · Page 3Linked to original sources

arXiv2024

Beware of Metacognitive Laziness: Effects of Generative Artificial Intelligence on Learning Motivation, Processes, and Performance

With the continuous development of technological and educational innovation, learners nowadays can obtain a variety of support from agents such as teachers, peers, education technologies, and recently, generative artificial intelligence such as ChatGPT. The concept of hybrid intelligence is still at a nascent stage, and how learners can benefit from a symbiotic relationship with various agents such as AI, human experts and intelligent learning systems is still unknown. The emerging concept of hybrid intelligence also lacks deep insights and understanding of the mechanisms and consequences of hybrid human-AI learning based on strong empirical research. In order to address this gap, we conducted a randomised experimental study and compared learners' motivations, self-regulated learning processes and learning performances on a writing task among different groups who had support from different agents (ChatGPT, human expert, writing analytics tools, and no extra tool). A total of 117 university students were recruited, and their multi-channel learning, performance and motivation data were collected and analysed. The results revealed that: learners who received different learning support showed no difference in post-task intrinsic motivation; there were significant differences in the frequency and sequences of the self-regulated learning processes among groups; ChatGPT group outperformed in the essay score improvement but their knowledge gain and transfer were not significantly different. Our research found that in the absence of differences in motivation, learners with different supports still exhibited different self-regulated learning processes, ultimately leading to differentiated performance. What is particularly noteworthy is that AI technologies such as ChatGPT may promote learners' dependence on technology and potentially trigger metacognitive laziness.

cs.AI↗

arXiv2024

On the Existence of Linear Observed Systems on Manifolds with Connection

Linear observed systems on manifolds are a special class of nonlinear systems whose state spaces are smooth manifolds but possess properties similar to linear systems. Such properties can be characterized by preintegration and exact linearization with Jacobians independent of the linearization point. Non-biased IMU dynamics in navigation can be constructed into linear observed settings, leading to invariant filters with guaranteed behaviors such as local convergence and consistency. In this letter, we establish linear observed property for systems evolving on a smooth manifold through the connection structure endowed upon this space. Our key findings are the existence of linear observed systems on manifolds poses constraints on the curvature of the state space, beyond requiring the dynamics to be compatible with some connection-preserving transformations. Specifically, the flat connection case reproduces the characterization of linear observed systems on Lie groups, showing our theory is a true generalization.

eess.SY↗

arXiv2024

Scale-free flocking and giant fluctuations in epithelial active solids

The collective motion of epithelial cells is a fundamental biological process which plays a significant role in embryogenesis, wound healing and tumor metastasis. While it has been broadly investigated for over a decade both in vivo and in vitro, large scale coherent flocking phases remain underexplored and have so far been mostly described as fluid. In this work, we report a mode of large-scale collective motion for different epithelial cell types in vitro with distinctive new features. By tracking individual cells, we show that cells move over long time scales coherently not as a fluid, but as a polar elastic solid with negligible cell rearrangements. Our analysis reveals that this solid flocking phase exhibits signatures of long-range polar order, unprecedented in cellular systems, such as scale-free correlations, anomalously large density fluctuations, and shear waves. Based on a general theory of active polar solids, we argue that these features result from massless Goldstone modes, which, in contrast to polar fluids where they are generic, require the decoupling of global rotations of the polarity and in-plane elastic deformations in polar solids. We theoretically show and consistently observe in experiments that the fluctuations of elastic deformations diverge for large system size in such polar active solid phases, leading eventually to rupture and thus potentially loss of tissue integrity at large scales.

cond-mat.soft↗

arXiv2024

Reward-Robust RLHF in LLMs

As Large Language Models (LLMs) continue to progress toward more advanced forms of intelligence, Reinforcement Learning from Human Feedback (RLHF) is increasingly seen as a key pathway toward achieving Artificial General Intelligence (AGI). However, the reliance on reward-model-based (RM-based) alignment methods introduces significant challenges due to the inherent instability and imperfections of Reward Models (RMs), which can lead to critical issues such as reward hacking and misalignment with human intentions. In this paper, we introduce a reward-robust RLHF framework aimed at addressing these fundamental challenges, paving the way for more reliable and resilient learning in LLMs. Our approach introduces a novel optimization objective that carefully balances performance and robustness by incorporating Bayesian Reward Model Ensembles (BRME) to model the uncertainty set of reward functions. This allows the framework to integrate both nominal performance and minimum reward signals, ensuring more stable learning even with imperfect RMs. Empirical results demonstrate that our framework consistently outperforms baselines across diverse benchmarks, showing improved accuracy and long-term stability. We also provide a theoretical analysis, demonstrating that reward-robust RLHF approaches the stability of constant reward settings, which proves to be acceptable even in a stochastic-case analysis. Together, these contributions highlight the framework potential to enhance both the performance and stability of LLM alignment.

cs.LG↗

arXiv2024

EarthGen: Generating the World from Top-Down Views

In this work, we present a novel method for extensive multi-scale generative terrain modeling. At the core of our model is a cascade of superresolution diffusion models that can be combined to produce consistent images across multiple resolutions. Pairing this concept with a tiled generation method yields a scalable system that can generate thousands of square kilometers of realistic Earth surfaces at high resolution. We evaluate our method on a dataset collected from Bing Maps and show that it outperforms super-resolution baselines on the extreme super-resolution task of 1024x zoom. We also demonstrate its ability to create diverse and coherent scenes via an interactive gigapixel-scale generated map. Finally, we demonstrate how our system can be extended to enable novel content creation applications including controllable world generation and 3D scene generation.

cs.CV↗

arXiv2024

Towards Quantum Federated Learning

Quantum Federated Learning (QFL) is an emerging interdisciplinary field that merges the principles of Quantum Computing (QC) and Federated Learning (FL), with the goal of leveraging quantum technologies to enhance privacy, security, and efficiency in the learning process. Currently, there is no comprehensive survey for this interdisciplinary field. This review offers a thorough, holistic examination of QFL. We aim to provide a comprehensive understanding of the principles, techniques, and emerging applications of QFL. We discuss the current state of research in this rapidly evolving field, identify challenges and opportunities associated with integrating these technologies, and outline future directions and open research questions. We propose a unique taxonomy of QFL techniques, categorized according to their characteristics and the quantum techniques employed. As the field of QFL continues to progress, we can anticipate further breakthroughs and applications across various industries, driving innovation and addressing challenges related to data privacy, security, and resource optimization. This review serves as a first-of-its-kind comprehensive guide for researchers and practitioners interested in understanding and advancing the field of QFL.

cs.LG↗

arXiv2024

Exploiting Multipath Information for Integrated Localization and Sensing via PHD Filtering

Accurate localization and perception are pivotal for enhancing the safety and reliability of vehicles. However, current localization methods suffer from reduced accuracy when the line-of-sight (LOS) path is obstructed, or a combination of reflections and scatterings is present. In this paper, we present an integrated localization and sensing method that delivers superior performance in complex environments while being computationally efficient. Our method uniformly leverages various types of multipath components (MPCs) through the lens of random finite sets (RFSs), encompassing reflections, scatterings, and their combinations. This advancement eliminates the need for the multipath identification step and streamlines the filtering process by removing the necessity for distinct filters for different multipath types, a requirement that was critical in previous research. The simulation results demonstrate the superior performance of our method in both robustness and effectiveness, particularly in complex environments where the LOS MPC is obscured and in situations involving clutter and missed detection of MPC measurements.

eess.SP↗

arXiv2024

SuperGaussian: Repurposing Video Models for 3D Super Resolution

We present a simple, modular, and generic method that upsamples coarse 3D models by adding geometric and appearance details. While generative 3D models now exist, they do not yet match the quality of their counterparts in image and video domains. We demonstrate that it is possible to directly repurpose existing (pretrained) video models for 3D super-resolution and thus sidestep the problem of the shortage of large repositories of high-quality 3D training models. We describe how to repurpose video upsampling models, which are not 3D consistent, and combine them with 3D consolidation to produce 3D-consistent results. As output, we produce high quality Gaussian Splat models, which are object centric and effective. Our method is category agnostic and can be easily incorporated into existing 3D workflows. We evaluate our proposed SuperGaussian on a variety of 3D inputs, which are diverse both in terms of complexity and representation (e.g., Gaussian Splats or NeRFs), and demonstrate that our simple method significantly improves the fidelity of the final 3D models. Check our project website for details: supergaussian.github.io

cs.CV↗

arXiv2024

CT Reconstruction using Diffusion Posterior Sampling conditioned on a Nonlinear Measurement Model

Diffusion models have been demonstrated as powerful deep learning tools for image generation in CT reconstruction and restoration. Recently, diffusion posterior sampling, where a score-based diffusion prior is combined with a likelihood model, has been used to produce high quality CT images given low-quality measurements. This technique is attractive since it permits a one-time, unsupervised training of a CT prior; which can then be incorporated with an arbitrary data model. However, current methods rely on a linear model of x-ray CT physics to reconstruct or restore images. While it is common to linearize the transmission tomography reconstruction problem, this is an approximation to the true and inherently nonlinear forward model. We propose a new method that solves the inverse problem of nonlinear CT image reconstruction via diffusion posterior sampling. We implement a traditional unconditional diffusion model by training a prior score function estimator, and apply Bayes rule to combine this prior with a measurement likelihood score function derived from the nonlinear physical model to arrive at a posterior score function that can be used to sample the reverse-time diffusion process. This plug-and-play method allows incorporation of a diffusion-based prior with generalized nonlinear CT image reconstruction into multiple CT system designs with different forward models, without the need for any additional training. We develop the algorithm that performs this reconstruction, including an ordered-subsets variant for accelerated processing and demonstrate the technique in both fully sampled low dose data and sparse-view geometries using a single unsupervised training of the prior.

physics.med-ph↗

arXiv2024

Skew Knörrer's periodicity Theorem

In this paper, we introduce a class of twisted matrix algebras of $M_2(E)$ and twisted direct products of $E\times E$ for an algebra $E$. Let $A$ be a noetherian Koszul Artin-Schelter regular algebra, $z\in A_2$ be a regular central element of $A$ and $B=A_P[y_1,y_2;σ]$ be a graded double Ore extension of $A$. We use the Clifford deformation $C_{A^!}(z)$ of Koszul dual $A^!$ to study the noncommutative quadric hypersurface $B/(z+y_1^2+y_2^2)$. We prove that the stable category of graded maximal Cohen-Macaulay modules over $B/(z+y_1^2+y_2^2)$ is equivalent to certain bounded derived categories, which involve a twisted matrix algebra of $M_2(C_{A^!}(z))$ or a twisted direct product of $C_{A^!}(z)\times C_{A^!}(z)$ depending on the values of $P$. These results are presented as skew versions of Knörrer's periodicity theorem. Moreover, we show $B/(z+y_1^2+y_2^2)$ may not be a noncommutative graded isolated singularity even if $A/(z)$ is.

math.RA↗

arXiv2024

The Integrated Sensing and Communication Revolution for 6G: Vision, Techniques, and Applications

Future wireless networks will integrate sensing, learning and communication to provide new services beyond communication and to become more resilient. Sensors at the network infrastructure, sensors on the user equipment, and the sensing capability of the communication signal itself provide a new source of data that connects the physical and radio frequency environments. A wireless network that harnesses all these sensing data can not only enable additional sensing services, but also become more resilient to channel-dependent effects like blockage and better support adaptation in dynamic environments as networks reconfigure. In this paper, we provide a vision for integrated sensing and communication (ISAC) networks and an overview of how signal processing, optimization and machine learning techniques can be leveraged to make them a reality in the context of 6G. We also include some examples of the performance of several of these strategies when evaluated using a simulation framework based on a combination of ray tracing measurements and mathematical models that mix the digital and physical worlds.

eess.SP↗

arXiv2024

Physical Property Understanding from Language-Embedded Feature Fields

Can computers perceive the physical properties of objects solely through vision? Research in cognitive science and vision science has shown that humans excel at identifying materials and estimating their physical properties based purely on visual appearance. In this paper, we present a novel approach for dense prediction of the physical properties of objects using a collection of images. Inspired by how humans reason about physics through vision, we leverage large language models to propose candidate materials for each object. We then construct a language-embedded point cloud and estimate the physical properties of each 3D point using a zero-shot kernel regression approach. Our method is accurate, annotation-free, and applicable to any object in the open world. Experiments demonstrate the effectiveness of the proposed approach in various physical property reasoning tasks, such as estimating the mass of common objects, as well as other properties like friction and hardness.

cs.CV↗

arXiv2024

Distributed Policy Gradient for Linear Quadratic Networked Control with Limited Communication Range

This paper proposes a scalable distributed policy gradient method and proves its convergence to near-optimal solution in multi-agent linear quadratic networked systems. The agents engage within a specified network under local communication constraints, implying that each agent can only exchange information with a limited number of neighboring agents. On the underlying graph of the network, each agent implements its control input depending on its nearby neighbors' states in the linear quadratic control setting. We show that it is possible to approximate the exact gradient only using local information. Compared with the centralized optimal controller, the performance gap decreases to zero exponentially as the communication and control ranges increase. We also demonstrate how increasing the communication range enhances system stability in the gradient descent process, thereby elucidating a critical trade-off. The simulation results verify our theoretical findings.

cs.MA↗

arXiv2023

Robust Communicative Multi-Agent Reinforcement Learning with Active Defense

Communication in multi-agent reinforcement learning (MARL) has been proven to effectively promote cooperation among agents recently. Since communication in real-world scenarios is vulnerable to noises and adversarial attacks, it is crucial to develop robust communicative MARL technique. However, existing research in this domain has predominantly focused on passive defense strategies, where agents receive all messages equally, making it hard to balance performance and robustness. We propose an active defense strategy, where agents automatically reduce the impact of potentially harmful messages on the final decision. There are two challenges to implement this strategy, that are defining unreliable messages and adjusting the unreliable messages' impact on the final decision properly. To address them, we design an Active Defense Multi-Agent Communication framework (ADMAC), which estimates the reliability of received messages and adjusts their impact on the final decision accordingly with the help of a decomposable decision structure. The superiority of ADMAC over existing methods is validated by experiments in three communication-critical tasks under four types of attacks.

cs.MA↗

arXiv2023

On the Performance Tradeoff of an ISAC System with Finite Blocklength

Integrated sensing and communication (ISAC) has been proposed as a promising paradigm in the future wireless networks, where the spectral and hardware resources are shared to provide a considerable performance gain. It is essential to understand how sensing and communication (S\&C) influences each other to guide the practical algorithm and system design in ISAC. In this paper, we investigate the performance tradeoff between S\&C in a single-input single-output (SISO) ISAC system with finite blocklength. In particular, we present the system model and the ISAC scheme, after which the rate-error tradeoff is introduced as the performance metric. Then we derive the achievability and converse bounds for the rate-error tradeoff, determining the boundary of the joint S\&C performance. Furthermore, we develop the asymptotic analysis at large blocklength regime, where the performance tradeoff between S\&C is proved to vanish as the blocklength tends to infinity. Finally, our theoretical analysis is consolidated by simulation results.

cs.IT↗

arXiv2023

Enhancing quantum synchronization through homodyne measurement, noise and squeezing

Quantum synchronization has been a central topic in quantum nonlinear dynamics. Despite rapid development in this field, very few have studied how to efficiently boost synchronization. Homodyne measurement emerges as one of the successful candidates for this task, but preferably in the semi-classical regime. In our work, we focus on the phase synchronization of a harmonic-driven quantum Stuart-Landau oscillator, and show that the enhancement induced by homodyne measurement persists into the quantum regime. Interestingly, optimal two-photon damping rates exist when the oscillator and driving are at resonance and with a small single-photon damping rate. We also report noise-induced enhancement in quantum synchronization when the single-photon damping rate is sufficiently large. Apart from these results, we discover that adding a squeezing Hamiltonian can further boost synchronization, especially in the semi-classical regime. Furthermore, the addition of squeezing causes the optimal two-photon pumping rates to shift and converge.

quant-ph↗

arXiv2023

Quantum synchronization effects induced by strong nonlinearities

A paradigm for quantum synchronization is the quantum analog of the Stuart--Landau oscillator, which corresponds to a van der Pol oscillator in the limit of weak (i.e. vanishingly small) nonlinearity. Due to this limitation, the quantum Stuart--Landau oscillator fails to capture interesting nonlinearity-induced phenomena such as relaxation oscillations. To overcome this deficiency we propose an alternative model which approximates the van der Pol oscillator to finitely large nonlinearities while remaining numerically tractable. This allows us to uncover interesting phenomena in the deep-quantum strongly-nonlinear regime with no classical analog, such as the persistence of amplitude death on resonance. We also report nonlinearity-induced position correlations in reactively coupled quantum oscillators. Such coupled oscillations become more and more correlated with increasing nonlinearity before reaching some maximum. Again, this behavior is absent classically. We also show how strong nonlinearity can enlarge the synchronization bandwidth in both single and coupled oscillators. This effect can be harnessed to induce mutual synchronization between two oscillators initially in amplitude death.

quant-ph↗

arXiv2023

Sim-on-Wheels: Physical World in the Loop Simulation for Self-Driving

We present Sim-on-Wheels, a safe, realistic, and vehicle-in-loop framework to test autonomous vehicles' performance in the real world under safety-critical scenarios. Sim-on-wheels runs on a self-driving vehicle operating in the physical world. It creates virtual traffic participants with risky behaviors and seamlessly inserts the virtual events into images perceived from the physical world in real-time. The manipulated images are fed into autonomy, allowing the self-driving vehicle to react to such virtual events. The full pipeline runs on the actual vehicle and interacts with the physical world, but the safety-critical events it sees are virtual. Sim-on-Wheels is safe, interactive, realistic, and easy to use. The experiments demonstrate the potential of Sim-on-Wheels to facilitate the process of testing autonomous driving in challenging real-world scenes with high fidelity and low risk.

cs.RO↗