Searcharxiv⌕ Search

arXiv subjects

Li He

Publications and source records attributed to Li He.

At least 55 records · Page 3Linked to original sources
arXiv2023

Debunking Disinformation: Revolutionizing Truth with NLP in Fake News Detection

The Internet and social media have altered how individuals access news in the age of instantaneous information distribution. While this development has increased access to information, it has also created a significant problem: the spread of fake news and information. Fake news is rapidly spreading on digital platforms, which has a negative impact on the media ecosystem, public opinion, decision-making, and social cohesion. Natural Language Processing(NLP), which offers a variety of approaches to identify content as authentic, has emerged as a potent weapon in the growing war against disinformation. This paper takes an in-depth look at how NLP technology can be used to detect fake news and reveals the challenges and opportunities it presents.

cs.AI↗
arXiv2023

Control over cavity exciton polaritons in monolayer semiconductors

Integrating two-dimensional van der Waals materials with optical cavities has revealed a fascinating platform to study exciton-polariton physics. Manipulating exciton polaritons often requires external control over the electrical and optical properties of materials. Here we demonstrate the electrical control of 2D exciton polaritons by strongly coupling a transition metal dichalcogenides (TMD) heterostructure to a photonic crystal nanocavity. Through precise control of the doping level in the TMD monolayers using electrostatic gating, we demonstrate a wide range of tunability in the exciton oscillator strength and hence the exciton photon hybridization. This tunability leads to the demonstration of a continuous transition from weak to strong coupling regime, as manifested by the disappearance and emergence of exciton polaritons, showcasing the versatility of our approach. Our work paves the way to further exploring nonlinear and quantum exciton polaritons in 2D materials and their device applications.

physics.optics↗
arXiv2023

Combating Bilateral Edge Noise for Robust Link Prediction

Although link prediction on graphs has achieved great success with the development of graph neural networks (GNNs), the potential robustness under the edge noise is still less investigated. To close this gap, we first conduct an empirical study to disclose that the edge noise bilaterally perturbs both input topology and target label, yielding severe performance degradation and representation collapse. To address this dilemma, we propose an information-theory-guided principle, Robust Graph Information Bottleneck (RGIB), to extract reliable supervision signals and avoid representation collapse. Different from the basic information bottleneck, RGIB further decouples and balances the mutual dependence among graph topology, target labels, and representation, building new learning objectives for robust representation against the bilateral noise. Two instantiations, RGIB-SSL and RGIB-REP, are explored to leverage the merits of different methodologies, i.e., self-supervised learning and data reparameterization, for implicit and explicit data denoising, respectively. Extensive experiments on six datasets and three GNNs with diverse noisy scenarios verify the effectiveness of our RGIB instantiations. The code is publicly available at: https://github.com/tmlr-group/RGIB.

cs.LG↗
arXiv2023

CEIL: Generalized Contextual Imitation Learning

In this paper, we present \textbf{C}ont\textbf{E}xtual \textbf{I}mitation \textbf{L}earning~(CEIL), a general and broadly applicable algorithm for imitation learning (IL). Inspired by the formulation of hindsight information matching, we derive CEIL by explicitly learning a hindsight embedding function together with a contextual policy using the hindsight embeddings. To achieve the expert matching objective for IL, we advocate for optimizing a contextual variable such that it biases the contextual policy towards mimicking expert behaviors. Beyond the typical learning from demonstrations (LfD) setting, CEIL is a generalist that can be effectively applied to multiple settings including: 1)~learning from observations (LfO), 2)~offline IL, 3)~cross-domain IL (mismatched experts), and 4) one-shot IL settings. Empirically, we evaluate CEIL on the popular MuJoCo tasks (online) and the D4RL dataset (offline). Compared to prior state-of-the-art baselines, we show that CEIL is more sample-efficient in most online IL tasks and achieves better or competitive performances in offline tasks.

cs.LG↗
arXiv2023

CLUE: Calibrated Latent Guidance for Offline Reinforcement Learning

Offline reinforcement learning (RL) aims to learn an optimal policy from pre-collected and labeled datasets, which eliminates the time-consuming data collection in online RL. However, offline RL still bears a large burden of specifying/handcrafting extrinsic rewards for each transition in the offline data. As a remedy for the labor-intensive labeling, we propose to endow offline RL tasks with a few expert data and utilize the limited expert data to drive intrinsic rewards, thus eliminating the need for extrinsic rewards. To achieve that, we introduce \textbf{C}alibrated \textbf{L}atent g\textbf{U}idanc\textbf{E} (CLUE), which utilizes a conditional variational auto-encoder to learn a latent space such that intrinsic rewards can be directly qualified over the latent space. CLUE's key idea is to align the intrinsic rewards consistent with the expert intention via enforcing the embeddings of expert data to a calibrated contextual representation. We instantiate the expert-driven intrinsic rewards in sparse-reward offline RL tasks, offline imitation learning (IL) tasks, and unsupervised offline RL tasks. Empirically, we find that CLUE can effectively improve the sparse-reward offline RL performance, outperform the state-of-the-art offline IL baselines, and discover diverse skills from static reward-free offline data.

cs.LG↗
arXiv2023

Developing and Refining a Multifunctional Facial Recognition System for Older Adults with Cognitive Impairments: A Journey Towards Enhanced Quality of Life

In an era where the global population is aging significantly, cognitive impairments among the elderly have become a major health concern. The need for effective assistive technologies is clear, and facial recognition systems are emerging as promising tools to address this issue. This document discusses the development and evaluation of a new Multifunctional Facial Recognition System (MFRS), designed specifically to assist older adults with cognitive impairments. The MFRS leverages face_recognition [1], a powerful open-source library capable of extracting, identifying, and manipulating facial features. Our system integrates the face recognition and retrieval capabilities of face_recognition, along with additional functionalities to capture images and record voice memos. This combination of features notably enhances the system's usability and versatility, making it a more user-friendly and universally applicable tool for end-users. The source code for this project can be accessed at https://github.com/Li-8023/Multi-function-face-recognition.git.

cs.CV↗
arXiv2023

LiteTrack: Layer Pruning with Asynchronous Feature Extraction for Lightweight and Efficient Visual Tracking

The recent advancements in transformer-based visual trackers have led to significant progress, attributed to their strong modeling capabilities. However, as performance improves, running latency correspondingly increases, presenting a challenge for real-time robotics applications, especially on edge devices with computational constraints. In response to this, we introduce LiteTrack, an efficient transformer-based tracking model optimized for high-speed operations across various devices. It achieves a more favorable trade-off between accuracy and efficiency than the other lightweight trackers. The main innovations of LiteTrack encompass: 1) asynchronous feature extraction and interaction between the template and search region for better feature fushion and cutting redundant computation, and 2) pruning encoder layers from a heavy tracker to refine the balnace between performance and speed. As an example, our fastest variant, LiteTrack-B4, achieves 65.2% AO on the GOT-10k benchmark, surpassing all preceding efficient trackers, while running over 100 fps with ONNX on the Jetson Orin NX edge device. Moreover, our LiteTrack-B9 reaches competitive 72.2% AO on GOT-10k and 82.4% AUC on TrackingNet, and operates at 171 fps on an NVIDIA 2080Ti GPU. The code and demo materials will be available at https://github.com/TsingWei/LiteTrack.

cs.CV↗
arXiv2023

STRAPPER: Preference-based Reinforcement Learning via Self-training Augmentation and Peer Regularization

Preference-based reinforcement learning (PbRL) promises to learn a complex reward function with binary human preference. However, such human-in-the-loop formulation requires considerable human effort to assign preference labels to segment pairs, hindering its large-scale applications. Recent approache has tried to reuse unlabeled segments, which implicitly elucidates the distribution of segments and thereby alleviates the human effort. And consistency regularization is further considered to improve the performance of semi-supervised learning. However, we notice that, unlike general classification tasks, in PbRL there exits a unique phenomenon that we defined as similarity trap in this paper. Intuitively, human can have diametrically opposite preferredness for similar segment pairs, but such similarity may trap consistency regularization fail in PbRL. Due to the existence of similarity trap, such consistency regularization improperly enhances the consistency possiblity of the model's predictions between segment pairs, and thus reduces the confidence in reward learning, since the augmented distribution does not match with the original one in PbRL. To overcome such issue, we present a self-training method along with our proposed peer regularization, which penalizes the reward model memorizing uninformative labels and acquires confident predictions. Empirically, we demonstrate that our approach is capable of learning well a variety of locomotion and robotic manipulation behaviors using different semi-supervised alternatives and peer regularization.

cs.LG↗
arXiv2023

Adversarial Constrained Bidding via Minimax Regret Optimization with Causality-Aware Reinforcement Learning

The proliferation of the Internet has led to the emergence of online advertising, driven by the mechanics of online auctions. In these repeated auctions, software agents participate on behalf of aggregated advertisers to optimize for their long-term utility. To fulfill the diverse demands, bidding strategies are employed to optimize advertising objectives subject to different spending constraints. Existing approaches on constrained bidding typically rely on i.i.d. train and test conditions, which contradicts the adversarial nature of online ad markets where different parties possess potentially conflicting objectives. In this regard, we explore the problem of constrained bidding in adversarial bidding environments, which assumes no knowledge about the adversarial factors. Instead of relying on the i.i.d. assumption, our insight is to align the train distribution of environments with the potential test distribution meanwhile minimizing policy regret. Based on this insight, we propose a practical Minimax Regret Optimization (MiRO) approach that interleaves between a teacher finding adversarial environments for tutoring and a learner meta-learning its policy over the given distribution of environments. In addition, we pioneer to incorporate expert demonstrations for learning bidding strategies. Through a causality-aware policy design, we improve upon MiRO by distilling knowledge from the experts. Extensive experiments on both industrial data and synthetic data show that our method, MiRO with Causality-aware reinforcement Learning (MiROCL), outperforms prior methods by over 30%.

cs.LG↗
arXiv2023

Beyond Reward: Offline Preference-guided Policy Optimization

This study focuses on the topic of offline preference-based reinforcement learning (PbRL), a variant of conventional reinforcement learning that dispenses with the need for online interaction or specification of reward functions. Instead, the agent is provided with fixed offline trajectories and human preferences between pairs of trajectories to extract the dynamics and task information, respectively. Since the dynamics and task information are orthogonal, a naive approach would involve using preference-based reward learning followed by an off-the-shelf offline RL algorithm. However, this requires the separate learning of a scalar reward function, which is assumed to be an information bottleneck of the learning process. To address this issue, we propose the offline preference-guided policy optimization (OPPO) paradigm, which models offline trajectories and preferences in a one-step process, eliminating the need for separately learning a reward function. OPPO achieves this by introducing an offline hindsight information matching objective for optimizing a contextual policy and a preference modeling objective for finding the optimal context. OPPO further integrates a well-performing decision policy by optimizing the two objectives iteratively. Our empirical results demonstrate that OPPO effectively models offline preferences and outperforms prior competing baselines, including offline RL algorithms performed over either true or pseudo reward function specifications. Our code is available on the project website: https://sites.google.com/view/oppo-icml-2023 .

cs.LG↗
arXiv2023

Exploring Model Dynamics for Accumulative Poisoning Discovery

Adversarial poisoning attacks pose huge threats to various machine learning applications. Especially, the recent accumulative poisoning attacks show that it is possible to achieve irreparable harm on models via a sequence of imperceptible attacks followed by a trigger batch. Due to the limited data-level discrepancy in real-time data streaming, current defensive methods are indiscriminate in handling the poison and clean samples. In this paper, we dive into the perspective of model dynamics and propose a novel information measure, namely, Memorization Discrepancy, to explore the defense via the model-level information. By implicitly transferring the changes in the data manipulation to that in the model outputs, Memorization Discrepancy can discover the imperceptible poison samples based on their distinct dynamics from the clean samples. We thoroughly explore its properties and propose Discrepancy-aware Sample Correction (DSC) to defend against accumulative poisoning attacks. Extensive experiments comprehensively characterized Memorization Discrepancy and verified its effectiveness. The code is publicly available at: https://github.com/tmlr-group/Memorization-Discrepancy.

cs.LG↗
arXiv2023

Direct Observation of Landau Levels in Silicon Photonic Crystals

We experimentally observe photonic Landau levels that arise due to a strain-induced pseudomagnetic field in a silicon photonic crystal slab. The Landau levels are dispersive (i.e., they are not flat bands) due to the distortion of the unit cell by the strain. We employ an additional strain which induces a pseudoelectric potential to flatten them.

physics.optics↗
arXiv2023

Quantum Criticality of Liquid-Gas Transition in a Binary Bose Mixture

Quantum liquid, in the form of a self-bound droplet, is stabilized by a subtle balance between the mean-field contribution and quantum fluctuations. While a liquid-gas transition is expected when such a balance is broken, it remains elusive whether liquid-gas critical points exist in the quantum regime. Here we study the quantum criticality in a binary Bose mixture undergoing the liquid-gas transition. We show that, beyond a narrow stability window of the self-bound liquid, a liquid-gas coexistence persists, which eventually transits into a homogeneous mixture. Importantly, we identify two distinct critical points where the liquid-gas coexistence terminates. These critical points are characterized by rich critical behaviors in their vicinity, including divergent susceptibility, unique phonon-mode softening, and enhanced density correlations. The liquid-gas transition and the critical points can be readily explored in ultracold atoms confined to a box potential. Our work highlights the thermodynamic approach as a powerful tool in revealing the quantum liquid-gas criticality, and paves the way for further studies of critical phenomena in quantum liquids.

cond-mat.quant-gas↗
arXiv2023

Observation of Floquet Chern insulators of light

The field of topological photonics studies unique and robust photonic systems that are immune to defects and disorders due to the protection of their underlying topological phases. Mostly implemented in static systems, the studied topological phases are often defined in linear photonic band structures. In this study, we experimentally demonstrate Floquet Chern insulators in periodically driven nonlinear photonic crystals, where the topological phase is controlled by the polarization and the frequency of the driving field. Mediated by strong material nonlinearity, our system enters what we call the 'strong Floquet coupling regime', where the photonic Floquet bands cross and open new energy gaps with non-trivial topology as observed in our transient sum-frequency generation measurements. Our work offers new opportunities to explore the role of classical optical nonlinearity in topological phases and their applications in nonlinear optoelectronics.

physics.optics↗
arXiv2023

Geometric similarities and topological phases in surface magnon polaritons

Highly spatially-squeezed polaritons, with propagation momentum significantly larger than free-space modes at the same frequency, enable varied and extreme control over light-matter interaction. Compared to other polaritons, surface magnon polaritons, the magnetic counterpart of surface phonon polaritons, have received relatively little attention. Here, we investigate the dispersion and properties of surface-magnon polaritons, highlighting the impact of geometric similarities and applying them to various surface-magnon polariton devices in both conventional and topological settings. Our theory predicts a method for strongly localizing and significantly enhancing magnetic fields in the microwave range and developing compact and lossless connectors capable of interconnecting waveguides with vastly different input and output impedances. Our work opens new avenues for manipulating magnetic fields in the microwave regime and for exploring topological phases in polariton platforms.

cond-mat.mes-hall↗
arXiv2023

Composition operators with closed range on the Dirichlet space

It is well known that the composition operator on Hardy or Bergman space has a closed range if and only if its Navanlinna counting function induces a reverse Carleson measure. Similar conclusion is not available on the Dirichlet space. Specifically, the reverse Carleson measure is not enough to ensure that the range of the corresponding composition operator is closed. However, under certain assumptions, we in this paper set the necessary and sufficient condition for a composition operator on the Dirichlet space to have closed range.

math.FA↗
arXiv2023

3D nonlinear optical metamaterials from twisted 2D van der Waals interfaces

To enable new nonlinear responses, metamaterials are created by organizing structural units (meta-atoms) which are typically on the scale of about a hundred nanometers. However, truly altering atomic symmetry and enabling new nonlinear responses requires control at the atomic-scale, down to a few angstroms. Here we report the discovery of 3D nonlinear optical metamaterials realized by the precise control and twist of individual 2D van der Waals interfaces. Specifically, new nonlinear crystals are achieved by adding pseudo screw symmetries to a multiple of 4-layer WS2 stacks (e.g. 4-layer, 8-layer, etc). The nonlinear susceptibility of the resulting 3D crystal is fundamentally different from natural WS2. Furthermore, we show that the magnitude of the newly enabled nonlinearity is enhanced by controlling the number of interfaces and the excitation wavelength. Our findings suggest a new approach to redesigning intrinsic nonlinearity in artificial atomic configurations, scalable from a few nanometer-thick unit cells to bulk materials.

physics.optics↗
arXiv2023

Efimov K-theory and universal localizing invariant

We give some basic properties of Efimov K-theory. In particular, Efimov K-theory is corepresentable, lax symmetric monoidal functor, preserves any small products and sends Milnor squares satisfying base change to cartesian squares.

math.KT↗