arXiv subjects

Jiawei Yang

Publications and source records attributed to Jiawei Yang.

At least 55 records · Page 3Linked to original sources

arXiv2024

DistillNeRF: Perceiving 3D Scenes from Single-Glance Images by Distilling Neural Fields and Foundation Model Features

We propose DistillNeRF, a self-supervised learning framework addressing the challenge of understanding 3D environments from limited 2D observations in outdoor autonomous driving scenes. Our method is a generalizable feedforward model that predicts a rich neural scene representation from sparse, single-frame multi-view camera inputs with limited view overlap, and is trained self-supervised with differentiable rendering to reconstruct RGB, depth, or feature images. Our first insight is to exploit per-scene optimized Neural Radiance Fields (NeRFs) by generating dense depth and virtual camera targets from them, which helps our model to learn enhanced 3D geometry from sparse non-overlapping image inputs. Second, to learn a semantically rich 3D representation, we propose distilling features from pre-trained 2D foundation models, such as CLIP or DINOv2, thereby enabling various downstream tasks without the need for costly 3D human annotations. To leverage these two insights, we introduce a novel model architecture with a two-stage lift-splat-shoot encoder and a parameterized sparse hierarchical voxel representation. Experimental results on the NuScenes and Waymo NOTR datasets demonstrate that DistillNeRF significantly outperforms existing comparable state-of-the-art self-supervised methods for scene reconstruction, novel view synthesis, and depth estimation; and it allows for competitive zero-shot 3D semantic occupancy prediction, as well as open-world scene understanding through distilled foundation model features. Demos and code will be available at https://distillnerf.github.io/.

cs.CV↗

arXiv2024

Controllable Text Generation for Large Language Models: A Survey

In Natural Language Processing (NLP), Large Language Models (LLMs) have demonstrated high text generation quality. However, in real-world applications, LLMs must meet increasingly complex requirements. Beyond avoiding misleading or inappropriate content, LLMs are also expected to cater to specific user needs, such as imitating particular writing styles or generating text with poetic richness. These varied demands have driven the development of Controllable Text Generation (CTG) techniques, which ensure that outputs adhere to predefined control conditions--such as safety, sentiment, thematic consistency, and linguistic style--while maintaining high standards of helpfulness, fluency, and diversity. This paper systematically reviews the latest advancements in CTG for LLMs, offering a comprehensive definition of its core concepts and clarifying the requirements for control conditions and text quality. We categorize CTG tasks into two primary types: content control and attribute control. The key methods are discussed, including model retraining, fine-tuning, reinforcement learning, prompt engineering, latent space manipulation, and decoding-time intervention. We analyze each method's characteristics, advantages, and limitations, providing nuanced insights for achieving generation control. Additionally, we review CTG evaluation methods, summarize its applications across domains, and address key challenges in current research, including reduced fluency and practicality. We also propose several appeals, such as placing greater emphasis on real-world applications in future research. This paper aims to offer valuable guidance to researchers and developers in the field. Our reference list and Chinese version are open-sourced at https://github.com/IAAR-Shanghai/CTGSurvey.

cs.CL↗

arXiv2024

Joint Selective State Space Model and Detrending for Robust Time Series Anomaly Detection

Deep learning-based sequence models are extensively employed in Time Series Anomaly Detection (TSAD) tasks due to their effective sequential modeling capabilities. However, the ability of TSAD is limited by two key challenges: (i) the ability to model long-range dependency and (ii) the generalization issue in the presence of non-stationary data. To tackle these challenges, an anomaly detector that leverages the selective state space model known for its proficiency in capturing long-term dependencies across various domains is proposed. Additionally, a multi-stage detrending mechanism is introduced to mitigate the prominent trend component in non-stationary data to address the generalization issue. Extensive experiments conducted on realworld public datasets demonstrate that the proposed methods surpass all 12 compared baseline methods.

cs.LG↗

arXiv2024

Denoising Vision Transformers

We study a crucial yet often overlooked issue inherent to Vision Transformers (ViTs): feature maps of these models exhibit grid-like artifacts, which hurt the performance of ViTs in downstream dense prediction tasks such as semantic segmentation, depth prediction, and object discovery. We trace this issue down to the positional embeddings at the input stage. To mitigate this, we propose a two-stage denoising approach, termed Denoising Vision Transformers (DVT). In the first stage, we separate the clean features from those contaminated by positional artifacts by enforcing cross-view feature consistency with neural fields on a per-image basis. This per-image optimization process extracts artifact-free features from raw ViT outputs, providing clean feature estimates for offline applications. In the second stage, we train a lightweight transformer block to predict clean features from raw ViT outputs, leveraging the derived estimates of the clean features as supervision. Our method, DVT, does not require re-training the existing pre-trained ViTs, and is immediately applicable to any Vision Transformer architecture. We evaluate our method on a variety of representative ViTs (DINO, DeiT-III, EVA02, CLIP, DINOv2, DINOv2-reg) and demonstrate that DVT consistently improves existing state-of-the-art general-purpose models in semantic and geometric tasks across multiple datasets. We hope our study will encourage a re-evaluation of ViT design, especially regarding the naive use of positional embeddings. Our code and checkpoints are publicly available.

cs.CV↗

arXiv2024

PreSight: Enhancing Autonomous Vehicle Perception with City-Scale NeRF Priors

Autonomous vehicles rely extensively on perception systems to navigate and interpret their surroundings. Despite significant advancements in these systems recently, challenges persist under conditions like occlusion, extreme lighting, or in unfamiliar urban areas. Unlike these systems, humans do not solely depend on immediate observations to perceive the environment. In navigating new cities, humans gradually develop a preliminary mental map to supplement real-time perception during subsequent visits. Inspired by this human approach, we introduce a novel framework, PreSight, that leverages past traversals to construct static prior memories, enhancing online perception in later navigations. Our method involves optimizing a city-scale neural radiance field with data from previous journeys to generate neural priors. These priors, rich in semantic and geometric details, are derived without manual annotations and can seamlessly augment various state-of-the-art perception models, improving their efficacy with minimal additional computational cost. Experimental results on the nuScenes dataset demonstrate the framework's high compatibility with diverse online perception models. Specifically, it shows remarkable improvements in HD-map construction and occupancy prediction tasks, highlighting its potential as a new perception framework for autonomous driving systems. Our code will be released at https://github.com/yuantianyuan01/PreSight.

cs.CV↗

arXiv2024

MSS-PAE: Saving Autoencoder-based Outlier Detection from Unexpected Reconstruction

AutoEncoders (AEs) are commonly used for machine learning tasks due to their intrinsic learning ability. This unique characteristic can be capitalized for Outlier Detection (OD). However conventional AE-based methods face the issue of overconfident decisions and unexpected reconstruction results of outliers, limiting their performance in OD. To mitigate these issues, the Mean Squared Error (MSE) and Negative Logarithmic Likelihood (NLL) were firstly analyzed, and the importance of incorporating aleatoric uncertainty to AE-based OD was elucidated. Then the Weighted Negative Logarithmic Likelihood (WNLL) was proposed to adjust for the effect of uncertainty for different OD scenarios. Moreover, the Mean-Shift Scoring (MSS) method was proposed to utilize the local relationship of data to reduce the issue of false inliers caused by AE. Experiments on 32 real-world OD datasets proved the effectiveness of the proposed methods. The combination of WNLL and MSS achieved 41% relative performance improvement compared to the best baseline. In addition, MSS improved the detection performance of multiple AE-based outlier detectors by an average of 20%. The proposed methods have the potential to advance AE's development in OD.

cs.LG↗

arXiv2024

DDLNet: Boosting Remote Sensing Change Detection with Dual-Domain Learning

Remote sensing change detection (RSCD) aims to identify the changes of interest in a region by analyzing multi-temporal remote sensing images, and has an outstanding value for local development monitoring. Existing RSCD methods are devoted to contextual modeling in the spatial domain to enhance the changes of interest. Despite the satisfactory performance achieved, the lack of knowledge in the frequency domain limits the further improvement of model performance. In this paper, we propose DDLNet, a RSCD network based on dual-domain learning (i.e., frequency and spatial domains). In particular, we design a Frequency-domain Enhancement Module (FEM) to capture frequency components from the input bi-temporal images using Discrete Cosine Transform (DCT) and thus enhance the changes of interest. Besides, we devise a Spatial-domain Recovery Module (SRM) to fuse spatiotemporal features for reconstructing spatial details of change representations. Extensive experiments on three benchmark RSCD datasets demonstrate that the proposed method achieves state-of-the-art performance and reaches a more satisfactory accuracy-efficiency trade-off. Our code is publicly available at https://github.com/xwmaxwma/rschange.

cs.CV↗

arXiv2024

Weakly-supervised anomaly detection for multimodal data distributions

Weakly-supervised anomaly detection can outperform existing unsupervised methods with the assistance of a very small number of labeled anomalies, which attracts increasing attention from researchers. However, existing weakly-supervised anomaly detection methods are limited as these methods do not factor in the multimodel nature of the real-world data distribution. To mitigate this, we propose the Weakly-supervised Variational-mixture-model-based Anomaly Detector (WVAD). WVAD excels in multimodal datasets. It consists of two components: a deep variational mixture model, and an anomaly score estimator. The deep variational mixture model captures various features of the data from different clusters, then these features are delivered to the anomaly score estimator to assess the anomaly levels. Experimental results on three real-world datasets demonstrate WVAD's superiority.

cs.LG↗

arXiv2024

Empowering Large Language Models to Set up a Knowledge Retrieval Indexer via Self-Learning

Retrieval-Augmented Generation (RAG) offers a cost-effective approach to injecting real-time knowledge into large language models (LLMs). Nevertheless, constructing and validating high-quality knowledge repositories require considerable effort. We propose a pre-retrieval framework named Pseudo-Graph Retrieval-Augmented Generation (PG-RAG), which conceptualizes LLMs as students by providing them with abundant raw reading materials and encouraging them to engage in autonomous reading to record factual information in their own words. The resulting concise, well-organized mental indices are interconnected through common topics or complementary facts to form a pseudo-graph database. During the retrieval phase, PG-RAG mimics the human behavior in flipping through notes, identifying fact paths and subsequently exploring the related contexts. Adhering to the principle of the path taken by many is the best, it integrates highly corroborated fact paths to provide a structured and refined sub-graph assisting LLMs. We validated PG-RAG on three specialized question-answering datasets. In single-document tasks, PG-RAG significantly outperformed the current best baseline, KGP-LLaMA, across all key evaluation metrics, with an average overall performance improvement of 11.6%. Specifically, its BLEU score increased by approximately 14.3%, and the QE-F1 metric improved by 23.7%. In multi-document scenarios, the average metrics of PG-RAG were at least 2.35% higher than the best baseline. Notably, the BLEU score and QE-F1 metric showed stable improvements of around 7.55% and 12.75%, respectively. Our code: https://github.com/IAAR-Shanghai/PGRAG.

cs.CL↗

arXiv2024

Filter-free high-performance single photon emission from a quantum dot in a Fabry-Perot microcavity

Combining resonant excitation with Purcell-enhanced single quantum dots (QDs) stands out as a prominent strategy for realizing high performance solid-state single photon sources. However, optimizing photon efficiency requires addressing challenges associated with effectively separating the excitation laser from QDs' emission. Traditionally, this involves polarization filtering, which limits the achievable polarization directions and the scalability of photonic states. In this study, we have successfully tackled this challenge by employing spatially-orthogonal resonant excitation of QDs, deterministically coupled to monolithic Fabry-Perot microcavities. Leveraging the membrane cavity structures, we have achieved filter-free single photon resonant fluorescence. The resulting source produces single photons with a simultaneous high extraction efficiency of 0.87, purity of 0.9045(4), and indistinguishability of 0.963(4).

quant-ph↗

arXiv2024

Parallelized Spatiotemporal Binding

While modern best practices advocate for scalable architectures that support long-range interactions, object-centric models are yet to fully embrace these architectures. In particular, existing object-centric models for handling sequential inputs, due to their reliance on RNN-based implementation, show poor stability and capacity and are slow to train on long sequences. We introduce Parallelizable Spatiotemporal Binder or PSB, the first temporally-parallelizable slot learning architecture for sequential inputs. Unlike conventional RNN-based approaches, PSB produces object-centric representations, known as slots, for all time-steps in parallel. This is achieved by refining the initial slots across all time-steps through a fixed number of layers equipped with causal attention. By capitalizing on the parallelism induced by our architecture, the proposed model exhibits a significant boost in efficiency. In experiments, we test PSB extensively as an encoder within an auto-encoding framework paired with a wide variety of decoder options. Compared to the state-of-the-art, our architecture demonstrates stable training on longer sequences, achieves parallelization that results in a 60% increase in training speed, and yields performance that is on par with or better on unsupervised 2D and 3D object-centric scene decomposition and understanding.

cs.LG↗

arXiv2024

CodeFuse-13B: A Pretrained Multi-lingual Code Large Language Model

Code Large Language Models (Code LLMs) have gained significant attention in the industry due to their wide applications in the full lifecycle of software engineering. However, the effectiveness of existing models in understanding non-English inputs for multi-lingual code-related tasks is still far from well studied. This paper introduces CodeFuse-13B, an open-sourced pre-trained code LLM. It is specifically designed for code-related tasks with both English and Chinese prompts and supports over 40 programming languages. CodeFuse achieves its effectiveness by utilizing a high quality pre-training dataset that is carefully filtered by program analyzers and optimized during the training process. Extensive experiments are conducted using real-world usage scenarios, the industry-standard benchmark HumanEval-x, and the specially designed CodeFuseEval for Chinese prompts. To assess the effectiveness of CodeFuse, we actively collected valuable human feedback from the AntGroup's software development process where CodeFuse has been successfully deployed. The results demonstrate that CodeFuse-13B achieves a HumanEval pass@1 score of 37.10%, positioning it as one of the top multi-lingual code LLMs with similar parameter sizes. In practical scenarios, such as code generation, code translation, code comments, and testcase generation, CodeFuse performs better than other models when confronted with Chinese prompts.

cs.SE↗

arXiv2023

Electroluminescence as a probe of strong exciton-plasmon coupling in few-layer WSe2

The manipulation of coupled quantum excitations is of fundamental importance in realizing novel photonic and optoelectronic devices. We use electroluminescence to probe plasmon-exciton coupling in hybrid structures consisting of a nanoscale plasmonic tunnel junction and few-layer two-dimensional transition-metal dichalcogenide transferred onto the junction. The resulting hybrid states act as a novel dielectric environment that affects the radiative recombination of hot carriers in the plasmonic nanostructure. We determine the plexcitonic spectrum from the electroluminescence and find Rabi splittings exceeding 50 meV in strong coupling regime. Our experimental findings are supported by electromagnetic simulations that enable us to explore systematically, and in detail, the emergence of plexciton polaritons as well as the polarization characteristics of their far-field emission. Electroluminescence modulated by plexciton coupling provides potential applications for engineering compact photonic devices with tunable optical and electrical properties.

cond-mat.mes-hall↗

arXiv2023

Rethinking Directional Integration in Neural Radiance Fields

Recent works use the Neural radiance field (NeRF) to perform multi-view 3D reconstruction, providing a significant leap in rendering photorealistic scenes. However, despite its efficacy, NeRF exhibits limited capability of learning view-dependent effects compared to light field rendering or image-based view synthesis. To that end, we introduce a modification to the NeRF rendering equation which is as simple as a few lines of code change for any NeRF variations, while greatly improving the rendering quality of view-dependent effects. By swapping the integration operator and the direction decoder network, we only integrate the positional features along the ray and move the directional terms out of the integration, resulting in a disentanglement of the view-dependent and independent components. The modified equation is equivalent to the classical volumetric rendering in ideal cases on object surfaces with Dirac densities. Furthermore, we prove that with the errors caused by network approximation and numerical integration, our rendering equation exhibits better convergence properties with lower error accumulations compared to the classical NeRF. We also show that the modified equation can be interpreted as light field rendering with learned ray embeddings. Experiments on different NeRF variations show consistent improvements in the quality of view-dependent effects with our simple modification.

cs.CV↗

arXiv2023

EmerNeRF: Emergent Spatial-Temporal Scene Decomposition via Self-Supervision

We present EmerNeRF, a simple yet powerful approach for learning spatial-temporal representations of dynamic driving scenes. Grounded in neural fields, EmerNeRF simultaneously captures scene geometry, appearance, motion, and semantics via self-bootstrapping. EmerNeRF hinges upon two core components: First, it stratifies scenes into static and dynamic fields. This decomposition emerges purely from self-supervision, enabling our model to learn from general, in-the-wild data sources. Second, EmerNeRF parameterizes an induced flow field from the dynamic field and uses this flow field to further aggregate multi-frame features, amplifying the rendering precision of dynamic objects. Coupling these three fields (static, dynamic, and flow) enables EmerNeRF to represent highly-dynamic scenes self-sufficiently, without relying on ground truth object annotations or pre-trained models for dynamic object segmentation or optical flow estimation. Our method achieves state-of-the-art performance in sensor simulation, significantly outperforming previous methods when reconstructing static (+2.93 PSNR) and dynamic (+3.70 PSNR) scenes. In addition, to bolster EmerNeRF's semantic generalization, we lift 2D visual foundation model features into 4D space-time and address a general positional bias in modern Transformers, significantly boosting 3D perception performance (e.g., 37.50% relative improvement in occupancy prediction accuracy on average). Finally, we construct a diverse and challenging 120-sequence dataset to benchmark neural fields under extreme and highly-dynamic settings.

cs.CV↗

arXiv2023

Tunable quantum dots in monolithic Fabry-Perot microcavities for high-performance single-photon sources

Cavity-enhanced single quantum dots (QDs) are the main approach towards ultra-high-performance solid-state quantum light sources for scalable photonic quantum technologies. Nevertheless, harnessing the Purcell effect requires precise spectral and spatial alignment of the QDs' emission with the cavity mode, which is challenging for most cavities. Here we have successfully integrated miniaturized Fabry-Perot microcavities with a piezoelectric actuator, and demonstrated a bright single photon source derived from a deterministically coupled QD within this microcavity. Leveraging the cavity-membrane structures, we have achieved large spectral-tunability via strain tuning. On resonance, we have obtained a high Purcell factor of approximately 9. The source delivers single photons with simultaneous high extraction efficiency of 0.58, high purity of 0.956(2) and high indistinguishability of 0.922(4). Together with a small footprint, our scheme facilitates the scalable integration of indistinguishable quantum light sources on-chip, and therefore removes a major barrier to the solid-state quantum information platforms based on QDs.

physics.optics↗

arXiv2023

Quantifying efficiency of remote excitation for surface enhanced Raman spectroscopy in molecular junctions

Surface-enhanced Raman spectroscopy (SERS) is enabled by local surface plasmon resonances (LSPRs) in metallic nanogaps. When SERS is excited by direct illumination of the nanogap, the background heating of lattice and electrons can prevent further manipulation of the molecules. To overcome this issue, we report SERS in electromigrated gold molecular junctions excited remotely: surface plasmon polaritons (SPPs) are excited at nearby gratings, propagate to the junction, and couple to the local nanogap plasmon modes. Like direct excitation, remote excitation of the nanogap can generate both SERS emission and an open-circuit photovoltage (OCPV). We compare SERS intensity and OCPV in both direct and remote illumination configurations. SERS spectra obtained by remote excitation are much more stable than those obtained through direct excitation when photon count rates are comparable. By statistical analysis of 33 devices, coupling efficiency of remote excitation is calculated to be around 10%, consistent with the simulated energy flow.

cond-mat.mes-hall↗

arXiv2023

STNet: Spatial and Temporal feature fusion network for change detection in remote sensing images

As an important task in remote sensing image analysis, remote sensing change detection (RSCD) aims to identify changes of interest in a region from spatially co-registered multi-temporal remote sensing images, so as to monitor the local development. Existing RSCD methods usually formulate RSCD as a binary classification task, representing changes of interest by merely feature concatenation or feature subtraction and recovering the spatial details via densely connected change representations, whose performances need further improvement. In this paper, we propose STNet, a RSCD network based on spatial and temporal feature fusions. Specifically, we design a temporal feature fusion (TFF) module to combine bi-temporal features using a cross-temporal gating mechanism for emphasizing changes of interest; a spatial feature fusion module is deployed to capture fine-grained information using a cross-scale attention mechanism for recovering the spatial details of change representations. Experimental results on three benchmark datasets for RSCD demonstrate that the proposed method achieves the state-of-the-art performance. Code is available at https://github.com/xwmaxwma/rschange.

cs.CV↗