arXiv subjects

Dongliang Wang

Publications and source records attributed to Dongliang Wang.

At least 19 recordsLinked to original sources

arXiv2026

Real-Time Dynamic Crosstalk Tracking and Compensation via Photonic Blind Source Separation

Space-division multiplexing in few-mode fibers can substantially increase optical-link capacity, but its practical deployment is hindered by dynamically varying inter-modal crosstalk induced by environmental perturbations. Although silicon photonic reconfigurable mode processors have been widely demonstrated, continuous adaptation during high-speed intensity-modulation direct-detection (IM/DD) transmission remains challenging. Here, we experimentally demonstrate real-time tracking and compensation of dynamically varying inter-modal crosstalk using a hybrid photonic--electronic framework that combines an integrated silicon photonic processor with an FPGA-based control backend. The photonic processor performs signal separation in the optical domain, while the FPGA extracts signal statistics and implements a blind source separation (BSS)-based feedback algorithm without requiring dedicated training sequences. A two-stage optimization strategy combines rapid crosstalk suppression with stable continuous tracking under dynamic channel variations. We demonstrate photonic blind source separation for signals up to 100 GBaud and FPGA-enabled continuous adaptation for two 64 GBaud data channels in a few-mode-fiber transmission system. The system maintains bit-error rates below $10^{-4}$ under dynamic crosstalk, with a per-update control latency of 4 ms. These results establish a practical route toward low-latency, hardware-efficient adaptive photonic front ends for dynamic high-speed IM/DD space-division-multiplexed links.

physics.optics↗

arXiv2026

Synthetic-to-Real Translation for Class-Agnostic Motion Prediction

Motion understanding is critical for ensuring safety and robustness in autonomous driving systems, driving increasing interest in motion prediction. A key challenge in this domain is the high cost associated with acquiring real-world motion labels. It is therefore ideal if we could transfer motion knowledge from synthetic data to real data. In this context, we explore the potential of synthetic-to-real translation for motion prediction (SRMP). However, the most used naive motion regression methods are notably sensitive to the synthetic-to-real domain shift, resulting in unreliable knowledge translation. To address this, we propose a novel approach integrating a motion knowledge translation framework with two key components: (1) objectness-aware motion prediction, which explicitly models the joint distribution of motion patterns and objectness priors to improve domain-invariant feature learning, and (2) objectness-aided motion enhancement, a motion label refinement mechanism that leverages learned objectness priors to filter motion noise. Furthermore, we present a physically-based pipeline for generating Motion4D, the first synthetic 4D LiDAR dataset tailored for SRMP research, addressing the lack of synthetic motion datasets. Experimental results demonstrate that our approach effectively bridges the domain gaps and yields superior performance on real scenes.

cs.CV↗

arXiv2026

Seedance 2.0: Advancing Video Generation for World Complexity

Seedance 2.0 is a new native multi-modal audio-video generation model, officially released in China in early February 2026. Compared with its predecessors, Seedance 1.0 and 1.5 Pro, Seedance 2.0 adopts a unified, highly efficient, and large-scale architecture for multi-modal audio-video joint generation. This allows it to support four input modalities: text, image, audio, and video, by integrating one of the most comprehensive suites of multi-modal content reference and editing capabilities available in the industry to date. It delivers substantial, well-rounded improvements across all key sub-dimensions of video and audio generation. In both expert evaluations and public user tests, the model has demonstrated performance on par with the leading levels in the field. Seedance 2.0 supports direct generation of audio-video content with durations ranging from 4 to 15 seconds, with native output resolutions of 480p and 720p. For multi-modal inputs as reference, its current open platform supports up to 3 video clips, 9 images, and 3 audio clips. In addition, we provide Seedance 2.0 Fast version, an accelerated variant of Seedance 2.0 designed to boost generation speed for low-latency scenarios. Seedance 2.0 has delivered significant improvements to its foundational generation capabilities and multi-modal generation performance, bringing an enhanced creative experience for end users.

cs.CV↗

arXiv2025

Asymmetric stress engineering of dense dislocations in brittle superconductors for strong vortex pinning

Large lossless currents in high-temperature superconductors (HTS) critically rely on dense defects with suitable size and dimensionality to pin vortices, with dislocations being particularly effective due to their one-dimensional geometry to interact extensively with vortex lines. However, in non-metallic compounds such as HTS with rigid lattices, conventional deformation methods typically lead to catastrophic fracture rather than dislocation-mediated plasticity, making it a persistent challenge to introduce dislocations at high density. Here, we propose an asymmetric stress field strategy using extrusion to directly nucleate a high-density of dislocations in HTS by activating shear-driven lattice slip and twisting under superimposed hydrostatic compression. As demonstrated in iron-based superconductors (IBS), atomic displacements of nearly one angstrom trigger the formation of tilted dislocation lines with a density approaching that of metals. With further structural refinement, these dislocations serve as strong pinning centers that lead to a fivefold enhancement in the current-carrying capacity of IBS at 33 T, along with low anisotropy and a large irreversibility field. This work not only establishes a scalable route to engineer pinning landscapes in HTS, but also offers a generalizable framework for manipulating dislocation structures in rigid crystalline systems.

cond-mat.supr-con↗

arXiv2025

Perceptual Ratings Predict Speech Inversion Articulatory Kinematics in Childhood Speech Sound Disorders

Purpose: This study evaluated whether articulatory kinematics, inferred by Articulatory Phonology speech inversion neural networks, aligned with perceptual ratings of /r/ and /s/ in the speech of children with speech sound disorders. Methods: Articulatory Phonology vocal tract variables were inferred for 5,961 utterances from 118 children and 3 adults, aged 2.25-45 years. Perceptual ratings were standardized using the novel 5-point PERCEPT Rating Scale and training protocol. Two research questions examined if the articulatory patterns of inferred vocal tract variables aligned with the perceptual error category for the phones investigated (e.g., tongue tip is more anterior in dentalized /s/ productions than in correct /s/). A third research question examined if gradient PERCEPT Rating Scale scores predicted articulatory proximity to correct productions. Results: Estimated marginal means from linear mixed models supported 17 of 18 /r/ hypotheses, involving tongue tip and tongue body constrictions. For /s/, estimated marginal means from a second linear mixed model supported 7 of 15 hypotheses, particularly those related to the tongue tip. A third linear mixed model revealed that PERCEPT Rating Scale scores significantly predicted articulatory proximity of errored phones to correct productions. Conclusion: Inferred vocal tract variables differentiated category and magnitude of articulatory errors for /r/, and to a lesser extent for /s/, aligning with perceptual judgments. These findings support the clinical interpretability of speech inversion vocal tract variables and the PERCEPT Rating Scale in quantifying articulatory proximity to the target sound, particularly for /r/.

eess.AS↗

arXiv2025

Kimi-VL Technical Report

We present Kimi-VL, an efficient open-source Mixture-of-Experts (MoE) vision-language model (VLM) that offers advanced multimodal reasoning, long-context understanding, and strong agent capabilities - all while activating only 2.8B parameters in its language decoder (Kimi-VL-A3B). Kimi-VL demonstrates strong performance across challenging domains: as a general-purpose VLM, Kimi-VL excels in multi-turn agent tasks (e.g., OSWorld), matching flagship models. Furthermore, it exhibits remarkable capabilities across diverse challenging vision language tasks, including college-level image and video comprehension, OCR, mathematical reasoning, and multi-image understanding. In comparative evaluations, it effectively competes with cutting-edge efficient VLMs such as GPT-4o-mini, Qwen2.5-VL-7B, and Gemma-3-12B-IT, while surpassing GPT-4o in several key domains. Kimi-VL also advances in processing long contexts and perceiving clearly. With a 128K extended context window, Kimi-VL can process diverse long inputs, achieving impressive scores of 64.5 on LongVideoBench and 35.1 on MMLongBench-Doc. Its native-resolution vision encoder, MoonViT, further allows it to see and understand ultra-high-resolution visual inputs, achieving 83.2 on InfoVQA and 34.5 on ScreenSpot-Pro, while maintaining lower computational cost for common tasks. Building upon Kimi-VL, we introduce an advanced long-thinking variant: Kimi-VL-Thinking-2506. Developed through long chain-of-thought (CoT) supervised fine-tuning (SFT) and reinforcement learning (RL), the latest model exhibits strong long-horizon reasoning capabilities (64.0 on MMMU, 46.3 on MMMU-Pro, 56.9 on MathVision, 80.1 on MathVista, 65.2 on VideoMMMU) while obtaining robust general abilities. Code and models are publicly accessible at https://github.com/MoonshotAI/Kimi-VL.

cs.CV↗

arXiv2025

Large-scale artificial intelligence with 41 million nanophotonic neurons on a metasurface

Conventional integrated circuits (ICs) struggle to meet the escalating demands of artificial intelligence (AI). This has sparked a renewed interest in an unconventional computing paradigm: neuromorphic (brain-inspired) computing. However, current neuromorphic systems face significant challenges in delivering a large number of parameters (i.e., weights) required for large-scale AI models. As a result, most neuromorphic hardware is limited to basic benchmark demonstrations, hindering its application to real-world AI challenges. Here, we present a large-scale optical neural network (ONN) for machine learning acceleration, featuring over 41 million photonic neurons. This system not only surpasses digital electronics in speed and energy efficiency but more importantly, closes the performance gap with large-scale AI models. Our ONN leverages an innovative optical metasurface device featuring numerous spatial modes. This device integrates over 41 million meta-atoms on a 10 mm$^2$ metasurface chip, enabling the processing of tens of millions of weights in a single operation. For the first time, we demonstrate that an ONN, utilizing a single-layer metasurface, can match the performance of deep and large-scale deep learning models, such as ResNet and Vision Transformer, across various benchmark tasks. Additionally, we show that our system can deliver high-performance solutions to real-world AI challenges through its unprecedented scale, such as accelerating the analysis of multi-gigapixel whole slide images (WSIs) for cancer detection by processing the million-pixel sub-image in a single shot. Our system reduces computing time and energy consumption by over 1,000 times compared to state-of-the-art graphic processing units (GPUs). This work presents a large-scale, low-power, and high-performance neuromorphic computing system, paving the way for future disruptive AI technologies.

physics.optics↗

arXiv2024

Perfecting Imperfect Physical Neural Networks with Transferable Robustness using Sharpness-Aware Training

AI models are essential in science and engineering, but recent advances are pushing the limits of traditional digital hardware. To address these limitations, physical neural networks (PNNs), which use physical substrates for computation, have gained increasing attention. However, developing effective training methods for PNNs remains a significant challenge. Current approaches, regardless of offline and online training, suffer from significant accuracy loss. Offline training is hindered by imprecise modeling, while online training yields device-specific models that can't be transferred to other devices due to manufacturing variances. Both methods face challenges from perturbations after deployment, such as thermal drift or alignment errors, which make trained models invalid and require retraining. Here, we address the challenges with both offline and online training through a novel technique called Sharpness-Aware Training (SAT), where we innovatively leverage the geometry of the loss landscape to tackle the problems in training physical systems. SAT enables accurate training using efficient backpropagation algorithms, even with imprecise models. PNNs trained by SAT offline even outperform those trained online, despite modeling and fabrication errors. SAT also overcomes online training limitations by enabling reliable transfer of models between devices. Finally, SAT is highly resilient to perturbations after deployment, allowing PNNs to continuously operate accurately under perturbations without retraining. We demonstrate SAT across three types of PNNs, showing it is universally applicable, regardless of whether the models are explicitly known. This work offers a transformative, efficient approach to training PNNs, addressing critical challenges in analog computing and enabling real-world deployment.

physics.optics↗

arXiv2024

High-precision programming of large-scale ring resonator circuits with minimal pre-calibration

Microring resonators (MRRs) are essential components in large-scale photonic integrated circuits (PICs), but programming these circuits with high precision and efficiency remains an unsolved challenge. Conventional methods rely on complex calibration processes that are both time-consuming and often inaccurate, limiting the scalability of PICs. This work introduces an innovative control method called chip-in-the-loop optimization (ChiL) that addresses this challenge by offering high scalability, precision, fast convergence, and robustness. ChiL reduces the calibration complexity for an $N$ devices system from $O(k^N)$ to a single-shot measurement, while maintaining a record-high precision over 9-bit in the presence of system imperfections, including fabrication variances, thermal crosstalk, and temperature drift. Using ChiL, we experimentally demonstrate a photonic solver for computing matrix eigenvalues and eigenvectors with errors on the order of $10^{-4}$. Additionally, we achieve a photonic neural network (PNN) with accuracy and a confusion matrix identical to those of digital computers. ChiL offers a practical approach for programming large-scale PICs and bridges the gap between analog photonic and digital electronic computing and signal processing in both scale and precision.

physics.optics↗

arXiv2024

Improving Typhoon Predictions by Integrating Data-Driven Machine Learning Models with Physics Models Based on the Spectral Nudging and Data Assimilation

With the rapid development of data-driven machine learning (ML) models in meteorology, typhoon track forecasts have become increasingly accurate. However, current ML models still face challenges, such as underestimating typhoon intensity and lacking interpretability. To address these issues, this study establishes an ML-driven hybrid typhoon model, where forecast fields from the Pangu-Weather model are used to constrain the large-scale forecasts of the Weather Research and Forecasting model based on the spectral nudging method (Pangu_SP). The results show that forecasts from the Pangu_SP experiment obviously outperform those by using the Global Forecast System as the initial field (GFS_INIT) and from the Integrated Forecasting System of the European Centre for Medium-Range Weather Forecasts (ECMWF IFS) for the track forecast of Typhoon Doksuri (2023). The predicted typhoon cloud patterns from Pangu_SP are also more consistent with satellite observations. Additionally, the typhoon intensity forecasts from Pangu_SP are notably more accurate than those from the ECMWF IFS, demonstrating that the hybrid model effectively leverages the strengths of both ML and physical models. Furthermore, this study is the first to explore the significance of data assimilation in ML-driven hybrid dynamical systems. The findings reveal that after assimilating water vapor channels from the Advanced Geostationary Radiation Imager onboard Fengyun-4B, the errors in typhoon intensity forecasts are reduced.

physics.ao-ph↗

arXiv2024

Robust Policy Learning for Multi-UAV Collision Avoidance with Causal Feature Selection

In unseen and complex outdoor environments, collision avoidance navigation for unmanned aerial vehicle (UAV) swarms presents a challenging problem. It requires UAVs to navigate through various obstacles and complex backgrounds. Existing collision avoidance navigation methods based on deep reinforcement learning show promising performance but suffer from poor generalization abilities, resulting in performance degradation in unseen environments. To address this issue, we investigate the cause of weak generalization ability in DRL and propose a novel causal feature selection module. This module can be integrated into the policy network and effectively filters out non-causal factors in representations, thereby reducing the influence of spurious correlations between non-causal factors and action predictions. Experimental results demonstrate that our proposed method can achieve robust navigation performance and effective collision avoidance especially in scenarios with unseen backgrounds and obstacles, which significantly outperforms existing state-of-the-art algorithms.

cs.RO↗

arXiv2024

Collision Avoidance for Multiple UAVs in Unknown Scenarios with Causal Representation Disentanglement

Deep reinforcement learning (DRL) has achieved remarkable progress in online path planning tasks for multi-UAV systems. However, existing DRL-based methods often suffer from performance degradation when tackling unseen scenarios, since the non-causal factors in visual representations adversely affect policy learning. To address this issue, we propose a novel representation learning approach, \ie, causal representation disentanglement, which can identify the causal and non-causal factors in representations. After that, we only pass causal factors for subsequent policy learning and thus explicitly eliminate the influence of non-causal factors, which effectively improves the generalization ability of DRL models. Experimental results show that our proposed method can achieve robust navigation performance and effective collision avoidance especially in unseen scenarios, which significantly outperforms existing SOTA algorithms.

cs.RO↗

arXiv2024

A 103-TOPS/mm$^2$ Integrated Photonic Computing Engine Enabling Next-Generation Reservoir Computing

Reservoir computing (RC) is a leading machine learning algorithm for information processing due to its rich expressiveness. A new RC paradigm has recently emerged, showcasing superior performance and delivering more interpretable results with shorter training data sets and training times, representing the next generation of RC computing. This work presents the first realization of a high-speed next-generation RC system on an integrated photonic chip. Our experimental results demonstrate state-of-the-art forecasting and classification performances under various machine learning tasks and achieve the fastest speeds of 60 Gbaud and a computing density of 103 tera operations/second/mm$^2$ (TOPS/mm$^2$). The passive system, composed of a simple star coupler with on-chip delay lines, offers several advantages over traditional RC systems, including no speed limitations, compact footprint, extremely high fabrication error tolerance, fewer metaparameters, and greater interpretability. This work lays the foundation for ultrafast on-chip photonic RC, representing significant progress toward developing next-generation high-speed photonic computing and signal processing.

cs.ET↗

arXiv2023

StreetSurf: Extending Multi-view Implicit Surface Reconstruction to Street Views

We present a novel multi-view implicit surface reconstruction technique, termed StreetSurf, that is readily applicable to street view images in widely-used autonomous driving datasets, such as Waymo-perception sequences, without necessarily requiring LiDAR data. As neural rendering research expands rapidly, its integration into street views has started to draw interests. Existing approaches on street views either mainly focus on novel view synthesis with little exploration of the scene geometry, or rely heavily on dense LiDAR data when investigating reconstruction. Neither of them investigates multi-view implicit surface reconstruction, especially under settings without LiDAR data. Our method extends prior object-centric neural surface reconstruction techniques to address the unique challenges posed by the unbounded street views that are captured with non-object-centric, long and narrow camera trajectories. We delimit the unbounded space into three parts, close-range, distant-view and sky, with aligned cuboid boundaries, and adapt cuboid/hyper-cuboid hash-grids along with road-surface initialization scheme for finer and disentangled representation. To further address the geometric errors arising from textureless regions and insufficient viewing angles, we adopt geometric priors that are estimated using general purpose monocular models. Coupled with our implementation of efficient and fine-grained multi-stage ray marching strategy, we achieve state of the art reconstruction quality in both geometry and appearance within only one to two hours of training time with a single RTX3090 GPU for each street view sequence. Furthermore, we demonstrate that the reconstructed implicit surfaces have rich potential for various downstream tasks, including ray tracing and LiDAR simulation.

cs.CV↗

arXiv2022

ActFormer: A GAN-based Transformer towards General Action-Conditioned 3D Human Motion Generation

We present a GAN-based Transformer for general action-conditioned 3D human motion generation, including not only single-person actions but also multi-person interactive actions. Our approach consists of a powerful Action-conditioned motion TransFormer (ActFormer) under a GAN training scheme, equipped with a Gaussian Process latent prior. Such a design combines the strong spatio-temporal representation capacity of Transformer, superiority in generative modeling of GAN, and inherent temporal correlations from the latent prior. Furthermore, ActFormer can be naturally extended to multi-person motions by alternately modeling temporal correlations and human interactions with Transformer encoders. To further facilitate research on multi-person motion generation, we introduce a new synthetic dataset of complex multi-person combat behaviors. Extensive experiments on NTU-13, NTU RGB+D 120, BABEL and the proposed combat dataset show that our method can adapt to various human motion representations and achieve superior performance over the state-of-the-art methods on both single-person and multi-person motion generation tasks, demonstrating a promising step towards a general human motion generator.

cs.CV↗

arXiv2022

Discovering A Variety of Objects in Spatio-Temporal Human-Object Interactions

Spatio-temporal Human-Object Interaction (ST-HOI) detection aims at detecting HOIs from videos, which is crucial for activity understanding. In daily HOIs, humans often interact with a variety of objects, e.g., holding and touching dozens of household items in cleaning. However, existing whole body-object interaction video benchmarks usually provide limited object classes. Here, we introduce a new benchmark based on AVA: Discovering Interacted Objects (DIO) including 51 interactions and 1,000+ objects. Accordingly, an ST-HOI learning task is proposed expecting vision systems to track human actors, detect interactions and simultaneously discover interacted objects. Even though today's detectors/trackers excel in object detection/tracking tasks, they perform unsatisfied to localize diverse/unseen objects in DIO. This profoundly reveals the limitation of current vision systems and poses a great challenge. Thus, how to leverage spatio-temporal cues to address object discovery is explored, and a Hierarchical Probe Network (HPN) is devised to discover interacted objects utilizing hierarchical spatio-temporal human/context cues. In extensive experiments, HPN demonstrates impressive performance. Data and code are available at https://github.com/DirtyHarryLYL/HAKE-AVA.

cs.CV↗

arXiv2022

AGENT: An Adaptive Grouping Entrapping Method of Flocking Systems

This study proposes a distributed algorithm that makes agents' adaptive grouping entrap multiple targets via automatic decision making, smooth flocking, and well-distributed entrapping. Agents make their own decisions about which targets to surround based on environmental information. An improved artificial potential field method is proposed to enable agents to smoothly and naturally change the formation to adapt to the environment. The proposed strategies guarantee that the coordination of swarm agents develops the phenomenon of multiple targets entrapping at the swarm level. We validate the performance of the proposed method using simulation experiments and design indicators for the analysis of these simulation and physical experiments.

cs.MA↗

arXiv2021

TSI: Temporal Saliency Integration for Video Action Recognition

Efficient spatiotemporal modeling is an important yet challenging problem for video action recognition. Existing state-of-the-art methods exploit neighboring feature differences to obtain motion clues for short-term temporal modeling with a simple convolution. However, only one local convolution is incapable of handling various kinds of actions because of the limited receptive field. Besides, action-irrelated noises brought by camera movement will also harm the quality of extracted motion features. In this paper, we propose a Temporal Saliency Integration (TSI) block, which mainly contains a Salient Motion Excitation (SME) module and a Cross-perception Temporal Integration (CTI) module. Specifically, SME aims to highlight the motion-sensitive area through spatial-level local-global motion modeling, where the saliency alignment and pyramidal motion modeling are conducted successively between adjacent frames to capture motion dynamics with fewer noises caused by misaligned background. CTI is designed to perform multi-perception temporal modeling through a group of separate 1D convolutions respectively. Meanwhile, temporal interactions across different perceptions are integrated with the attention mechanism. Through these two modules, long short-term temporal relationships can be encoded efficiently by introducing limited additional parameters. Extensive experiments are conducted on several popular benchmarks (i.e., Something-Something V1 & V2, Kinetics-400, UCF-101, and HMDB-51), which demonstrate the effectiveness of our proposed method.

cs.CV↗