arXiv subjects

Yang Li

Publications and source records attributed to Yang Li.

At least 793 records · Page 44Linked to original sources

arXiv2024

Rich Human Feedback for Text-to-Image Generation

Recent Text-to-Image (T2I) generation models such as Stable Diffusion and Imagen have made significant progress in generating high-resolution images based on text descriptions. However, many generated images still suffer from issues such as artifacts/implausibility, misalignment with text descriptions, and low aesthetic quality. Inspired by the success of Reinforcement Learning with Human Feedback (RLHF) for large language models, prior works collected human-provided scores as feedback on generated images and trained a reward model to improve the T2I generation. In this paper, we enrich the feedback signal by (i) marking image regions that are implausible or misaligned with the text, and (ii) annotating which words in the text prompt are misrepresented or missing on the image. We collect such rich human feedback on 18K generated images (RichHF-18K) and train a multimodal transformer to predict the rich feedback automatically. We show that the predicted rich human feedback can be leveraged to improve image generation, for example, by selecting high-quality training data to finetune and improve the generative models, or by creating masks with predicted heatmaps to inpaint the problematic regions. Notably, the improvements generalize to models (Muse) beyond those used to generate the images on which human feedback data were collected (Stable Diffusion variants). The RichHF-18K data set will be released in our GitHub repository: https://github.com/google-research/google-research/tree/master/richhf_18k.

cs.CV↗

arXiv2024

Chiral two-dimensional MoS2 by molecular functionalization as ultra-sensitive detectors for circularly polarized light

Inducing chirality in optically and electronically active materials is interesting for applications in sensing and quantum information transmission. Two-dimensional (2D) transition metal chalcogenides (TMDs) possess excellent electronic and optical properties but are achiral. Here we demonstrate chirality induction in atomically thin layers of 2D MoS2 by functionalization with chiral thiol molecules. Analysis of X-ray absorption near-edge structure and Raman optical activity with circularly polarized excitation suggest chemical and electronic interactions that leads chirality transfer from the molecules to the MoS2. We confirm chirality induction in 2D MoS2 with circular dichroism measurements that show absorption bands at wavelengths of 380-520 nm and 520-600 nm with giant molar ellipticity of 10^8 deg cm2/dmol 2-3 orders of magnitude higher than 3D chiral materials. Phototransistors fabricated from atomically thin chiral MoS2 for detection of circularly polarized light exhibit responsivity of >10^2 A/W and maximum anisotropy g-factor of 1.98 close to the theoretical maximum of 2.0, which indicates that the chiral states of photons are fully distinguishable by the photodetectors. Our results demonstrate that it is possible achieve chirality induction in monolayer MoS2 by molecular functionalization and realise ultra-sensitive detectors for circularly polarized photons.

cond-mat.mtrl-sci↗

arXiv2024

On optimality of Mallows model averaging

In the past decades, model averaging (MA) has attracted much attention as it has emerged as an alternative tool to the model selection (MS) statistical approach. Hansen [Econometrica 75 (2007) 1175--1189] introduced a Mallows model averaging (MMA) method with model weights selected by minimizing a Mallows' $C_p$ criterion. The main theoretical justification for MMA is an asymptotic optimality (AOP), which states that the risk/loss of the resulting MA estimator is asymptotically equivalent to that of the best but infeasible averaged model. MMA's AOP is proved in the literature by either constraining weights in a special discrete weight set or limiting the number of candidate models. In this work, it is first shown that under these restrictions, however, the optimal risk of MA becomes an unreachable target, and MMA may converge more slowly than MS. In this background, a foundational issue that has not been addressed is: When a suitably large set of candidate models is considered, and the model weights are not harmfully constrained, can the MMA estimator perform asymptotically as well as the optimal convex combination of the candidate models? We answer this question in both nested and non-nested settings. In the nested setting, we provide finite sample inequalities for the risk of MMA and show that without unnatural restrictions on the candidate models, MMA's AOP holds in a general continuous weight set under certain mild conditions. In the non-nested setting, a sufficient condition and a negative result are established for the achievability of the optimal MA risk. Implications on minimax adaptivity are given as well. The results from simulations back up our theoretical findings.

math.ST↗

arXiv2024

Energetic particle modes in burning plasmas

In this work, we present a novel kind of energetic particle modes with frequencies in the range of thermal ion diamagnetic and/or transit frequencies in burning plasmas. It is shown that the continuum structure can be broken by the energetic particles. In addition, the mode destabilization does not require the energetic particle drive to overcome the continuum damping, which indicates that they are much easier to be excited and thus manifest themselves as wide-band modes. Based on the analysis, a switch or even an oscillation between phases of discrete eigenmodes and wide-band modes can be predicted.

physics.plasm-ph↗

arXiv2024

Microscopic Insights into Fatigue Mechanism in Wurtzite Ferroelectric Al$_{0.65}$Sc$_{0.35}$N: Oxygen Infiltration Enabled Grain Amorphization Spanning Boundary to Bulk

For the first time, the fatigue behavior involving external oxygen in highly Sc-doped AlN ferroelectric film was observed using transmission electron microscope techniques. Despite increasing the Sc composition in AlScN film contributes to reducing the device operation voltage, the inherent affinity of Sc for oxygen introduces instability in device performance. In this study, oxygen incorporation at top electrode edges and grain boundaries accompanied with an increase in current leakage and the disappearance of ferroelectric properties, was observed in nanoscale after long-term field cycling. This observation indicates the emergence of non-ferroelectric and even amorphous states. This presented work revealed solid experimental evidence of an oxygen-involved fatigue mechanism, providing valuable insights into the physical nature of the ferroelectric properties of AlScN films.

cond-mat.mtrl-sci↗

arXiv2024

Matrix-Transformation Based Low-Rank Adaptation (MTLoRA): A Brain-Inspired Method for Parameter-Efficient Fine-Tuning

Fine-tuning techniques based on Large Pretrained Language Models (LPLMs) have been proven to significantly enhance model performance on a variety of downstream tasks and effectively control the output behaviors of LPLMs. Recent studies have proposed numerous methods for fine-tuning a small number of parameters based on open-source LPLMs, reducing the demand for computational and storage resources. Among these, reparameterization fine-tuning methods represented by LoRA (Low-Rank Adaptation) have gained popularity. We find that although these methods perform well in many aspects, there is still considerable room for improvement in terms of complex task adaptability, performance, stability, and algorithm complexity. In response to this, inspired by the idea that the functions of the brain are shaped by its geometric structure, this paper integrates this idea into LoRA technology and proposes a new matrix transformation-based reparameterization method for efficient fine-tuning, named Matrix-Transformation based Low-Rank Adaptation (MTLoRA). MTLoRA aims to dynamically alter its spatial geometric structure by applying a transformation-matrix T to perform linear transformations, such as rotation, scaling, and translation, on the task-specific parameter matrix, generating new matrix feature patterns (eigenvectors) to mimic the fundamental influence of complex geometric structure feature patterns in the brain on functions, thereby enhancing the model's performance in downstream tasks. In Natural Language Understanding (NLU) tasks, it is evaluated using the GLUE benchmark test, and the results reveal that MTLoRA achieves an overall performance increase of about 1.0% across eight tasks; in Natural Language Generation (NLG) tasks, MTLoRA improves performance by an average of 0.95% and 0.56% in the DART and WebNLG tasks, respectively.

cs.CL↗

arXiv2024

On Galois self-orthogonal algebraic geometry codes

Galois self-orthogonal (SO) codes are generalizations of Euclidean and Hermitian SO codes. Algebraic geometry (AG) codes are the first known class of linear codes exceeding the Gilbert-Varshamov bound. Both of them have attracted much attention for their rich algebraic structures and wide applications in these years. In this paper, we consider them together and study Galois SO AG codes. A criterion for an AG code being Galois SO is presented. Based on this criterion, we construct several new classes of maximum distance separable (MDS) Galois SO AG codes from projective lines and several new classes of Galois SO AG codes from projective elliptic curves, hyper-elliptic curves and hermitian curves. In addition, we give an embedding method that allows us to obtain more MDS Galois SO codes from known MDS Galois SO AG codes.

cs.IT↗

arXiv2024

Enhancing Cross-Dataset EEG Emotion Recognition: A Novel Approach with Emotional EEG Style Transfer Network

Recognizing the pivotal role of EEG emotion recognition in the development of affective Brain-Computer Interfaces (aBCIs), considerable research efforts have been dedicated to this field. While prior methods have demonstrated success in intra-subject EEG emotion recognition, a critical challenge persists in addressing the style mismatch between EEG signals from the source domain (training data) and the target domain (test data). To tackle the significant inter-domain differences in cross-dataset EEG emotion recognition, this paper introduces an innovative solution known as the Emotional EEG Style Transfer Network (E$^2$STN). The primary objective of this network is to effectively capture content information from the source domain and the style characteristics from the target domain, enabling the reconstruction of stylized EEG emotion representations. These representations prove highly beneficial in enhancing cross-dataset discriminative prediction. Concretely, E$^2$STN consists of three key modules\textemdash transfer module, transfer evaluation module, and discriminative prediction module\textemdash which address the domain style transfer, transfer quality evaluation, and discriminative prediction, respectively. Extensive experiments demonstrate that E$^2$STN achieves state-of-the-art performance in cross-dataset EEG emotion recognition tasks.

cs.HC↗

arXiv2024

Generalizing to Unseen Domains with Wasserstein Distributional Robustness under Limited Source Knowledge

Domain generalization aims at learning a universal model that performs well on unseen target domains, incorporating knowledge from multiple source domains. In this research, we consider the scenario where different domain shifts occur among conditional distributions of different classes across domains. When labeled samples in the source domains are limited, existing approaches are not sufficiently robust. To address this problem, we propose a novel domain generalization framework called {Wasserstein Distributionally Robust Domain Generalization} (WDRDG), inspired by the concept of distributionally robust optimization. We encourage robustness over conditional distributions within class-specific Wasserstein uncertainty sets and optimize the worst-case performance of a classifier over these uncertainty sets. We further develop a test-time adaptation module leveraging optimal transport to quantify the relationship between the unseen target domain and source domains to make adaptive inference for target data. Experiments on the Rotated MNIST, PACS and the VLCS datasets demonstrate that our method could effectively balance the robustness and discriminability in challenging generalization scenarios.

cs.LG↗

arXiv2024

Open-sourced Data Ecosystem in Autonomous Driving: the Present and Future

With the continuous maturation and application of autonomous driving technology, a systematic examination of open-source autonomous driving datasets becomes instrumental in fostering the robust evolution of the industry ecosystem. Current autonomous driving datasets can broadly be categorized into two generations. The first-generation autonomous driving datasets are characterized by relatively simpler sensor modalities, smaller data scale, and is limited to perception-level tasks. KITTI, introduced in 2012, serves as a prominent representative of this initial wave. In contrast, the second-generation datasets exhibit heightened complexity in sensor modalities, greater data scale and diversity, and an expansion of tasks from perception to encompass prediction and control. Leading examples of the second generation include nuScenes and Waymo, introduced around 2019. This comprehensive review, conducted in collaboration with esteemed colleagues from both academia and industry, systematically assesses over seventy open-source autonomous driving datasets from domestic and international sources. It offers insights into various aspects, such as the principles underlying the creation of high-quality datasets, the pivotal role of data engine systems, and the utilization of generative foundation models to facilitate scalable data generation. Furthermore, this review undertakes an exhaustive analysis and discourse regarding the characteristics and data scales that future third-generation autonomous driving datasets should possess. It also delves into the scientific and technical challenges that warrant resolution. These endeavors are pivotal in advancing autonomous innovation and fostering technological enhancement in critical domains. For further details, please refer to https://github.com/OpenDriveLab/DriveAGI.

cs.CV↗

arXiv2024

Beyond Inserting: Learning Identity Embedding for Semantic-Fidelity Personalized Diffusion Generation

Advanced diffusion-based Text-to-Image (T2I) models, such as the Stable Diffusion Model, have made significant progress in generating diverse and high-quality images using text prompts alone. However, when non-famous users require personalized image generation for their identities (IDs), the T2I models fail to accurately generate their ID-related images. The main problem is that pre-trained T2I models do not learn the mapping between the new ID prompts and their corresponding visual content. The previous methods either failed to accurately fit the face region or lost the interactive generative ability with other existing concepts in T2I models. In other words, they are unable to generate T2I-aligned and semantic-fidelity images for the given prompts with other concepts such as scenes (``Eiffel Tower''), actions (``holding a basketball''), and facial attributes (``eyes closed''). In this paper, we focus on inserting accurate and interactive ID embedding into the Stable Diffusion Model for semantic-fidelity personalized generation. We address this challenge from two perspectives: face-wise region fitting and semantic-fidelity token optimization. Specifically, we first visualize the attention overfit problem and propose a face-wise attention loss to fit the face region instead of entangling ID-unrelated information, such as face layout and background. This key trick significantly enhances the ID accuracy and interactive generative ability with other existing concepts. Then, we optimize one ID representation as multiple per-stage tokens where each token contains two disentangled features. This expansion of the textual conditioning space improves semantic-fidelity control. Extensive experiments validate that our results exhibit superior ID accuracy, text-based manipulation ability, and generalization compared to previous methods.

cs.CV↗

arXiv2024

Generating Automatic Feedback on UI Mockups with Large Language Models

Feedback on user interface (UI) mockups is crucial in design. However, human feedback is not always readily available. We explore the potential of using large language models for automatic feedback. Specifically, we focus on applying GPT-4 to automate heuristic evaluation, which currently entails a human expert assessing a UI's compliance with a set of design guidelines. We implemented a Figma plugin that takes in a UI design and a set of written heuristics, and renders automatically-generated feedback as constructive suggestions. We assessed performance on 51 UIs using three sets of guidelines, compared GPT-4-generated design suggestions with those from human experts, and conducted a study with 12 expert designers to understand fit with existing practice. We found that GPT-4-based feedback is useful for catching subtle errors, improving text, and considering UI semantics, but feedback also decreased in utility over iterations. Participants described several uses for this plugin despite its imperfect suggestions.

cs.HC↗

arXiv2024

Enhancing Continuous Domain Adaptation with Multi-Path Transfer Curriculum

Addressing the large distribution gap between training and testing data has long been a challenge in machine learning, giving rise to fields such as transfer learning and domain adaptation. Recently, Continuous Domain Adaptation (CDA) has emerged as an effective technique, closing this gap by utilizing a series of intermediate domains. This paper contributes a novel CDA method, W-MPOT, which rigorously addresses the domain ordering and error accumulation problems overlooked by previous studies. Specifically, we construct a transfer curriculum over the source and intermediate domains based on Wasserstein distance, motivated by theoretical analysis of CDA. Then we transfer the source model to the target domain through multiple valid paths in the curriculum using a modified version of continuous optimal transport. A bidirectional path consistency constraint is introduced to mitigate the impact of accumulated mapping errors during continuous transfer. We extensively evaluate W-MPOT on multiple datasets, achieving up to 54.1\% accuracy improvement on multi-session Alzheimer MR image classification and 94.7\% MSE reduction on battery capacity estimation.

cs.LG↗

arXiv2024

OUCopula: Bi-Channel Multi-Label Copula-Enhanced Adapter-Based CNN for Myopia Screening Based on OU-UWF Images

Myopia screening using cutting-edge ultra-widefield (UWF) fundus imaging is potentially significant for ophthalmic outcomes. Current multidisciplinary research between ophthalmology and deep learning (DL) concentrates primarily on disease classification and diagnosis using single-eye images, largely ignoring joint modeling and prediction for Oculus Uterque (OU, both eyes). Inspired by the complex relationships between OU and the high correlation between the (continuous) outcome labels (Spherical Equivalent and Axial Length), we propose a framework of copula-enhanced adapter convolutional neural network (CNN) learning with OU UWF fundus images (OUCopula) for joint prediction of multiple clinical scores. We design a novel bi-channel multi-label CNN that can (1) take bi-channel image inputs subject to both high correlation and heterogeneity (by sharing the same backbone network and employing adapters to parameterize the channel-wise discrepancy), and (2) incorporate correlation information between continuous output labels (using a copula). Solid experiments show that OUCopula achieves satisfactory performance in myopia score prediction compared to backbone models. Moreover, OUCopula can far exceed the performance of models constructed for single-eye inputs. Importantly, our study also hints at the potential extension of the bi-channel model to a multi-channel paradigm and the generalizability of OUCopula across various backbone CNNs.

eess.IV↗

arXiv2024

Theoretical demonstration of mode transmission in ZGP-based micrometer waveguide platforms

Birefringence phase-matching based \c{hi}(2) ZnGeP2 (ZGP) waveguide platform has been recently reported for excellent mid-infrared laser generation. Here, a detailed theoretical characterization of mode transmission taking waveguide anisotropy and substrate material absorption into account in a micrometer ZGP waveguide platform (ZGP-on-SiO2) is conducted. Benefited from high-index contrast between ZGP and substrate (SiO2/Air), Transverse electric and magnetic (TM and TE) mode transmission loss at interested wavelengths range of 2 - 12 μm is calculated to be less than 4 dB/cm and 1.5 dB/cm, respectively, in the designed ZGP waveguide. Notably, non-obvious oscillation of mode transmission loss versus phase-matching angles is observed, which is different from that in the previously reported weakly guided anisotropic waveguide. A vital phenomenon named mode crossing at some wavelengths in TM polarization is also exhibited in our waveguide platforms, which jeopardizes waveguide performances and could be avoided by changing the phase-matching angle in practice. This work provides a significant indication of ZGP waveguide design optimization in future and also exhibits extendibility to other birefringent crystal waveguide platforms.

physics.optics↗

arXiv2024

Stress inside the pion in holographic light-front QCD

In this work, we propose a method to compute the gravitational form factor $D(Q^2)$ in holographic QCD by exploiting the remarkable correspondence between semi-classical light-front QCD and semi-classical field theories in wrapped spacetime in 5D. The use of light-front holography bridges physics at large $Q^2$ as attained in light-front QCD and physics at small $Q^2$ where the coupling to scalar and tensor fields, i.e. glueballs, are dominant. As an application, we compute the $D$-term for the pion, and compare the results with recent lattice simulations.

hep-th↗

arXiv2024

Highly stable power control for chip-based continuous-variable quantum key distribution system

Quantum key distribution allows secret key generation with information theoretical security. It can be realized with photonic integrated circuits to benefit the tiny footprints and the large-scale manufacturing capacity. Continuous-variable quantum key distribution is suitable for chip-based integration due to its compatibility with mature optical communication devices. However, the quantum signal power control compatible with the mature photonic integration process faces difficulties on stability, which limits the system performance and causes the overestimation of secret key rate that opens practical security loopholes. Here, a highly stable chip-based quantum signal power control scheme based on a biased Mach-Zehnder interferometer structure is proposed, theoretically analyzed and experimentally implemented with standard silicon photonic techniques. Simulations and experimental results show that the proposed scheme significantly improves the system stability, where the standard deviation of the secret key rate is suppressed by an order of magnitude compared with the system using traditional designs, showing a promising and practicable way to realize highly stable continuous-variable quantum key distribution system on chip.

quant-ph↗

arXiv2024

Contrastive Continual Learning with Importance Sampling and Prototype-Instance Relation Distillation

Recently, because of the high-quality representations of contrastive learning methods, rehearsal-based contrastive continual learning has been proposed to explore how to continually learn transferable representation embeddings to avoid the catastrophic forgetting issue in traditional continual settings. Based on this framework, we propose Contrastive Continual Learning via Importance Sampling (CCLIS) to preserve knowledge by recovering previous data distributions with a new strategy for Replay Buffer Selection (RBS), which minimize estimated variance to save hard negative samples for representation learning with high quality. Furthermore, we present the Prototype-instance Relation Distillation (PRD) loss, a technique designed to maintain the relationship between prototypes and sample representations using a self-distillation process. Experiments on standard continual learning benchmarks reveal that our method notably outperforms existing baselines in terms of knowledge preservation and thereby effectively counteracts catastrophic forgetting in online contexts. The code is available at https://github.com/lijy373/CCLIS.

cs.LG↗