arXiv subjects

Le Wang

Publications and source records attributed to Le Wang.

At least 55 records · Page 3Linked to original sources

arXiv2025

BFA: Best-Feature-Aware Fusion for Multi-View Fine-grained Manipulation

In real-world scenarios, multi-view cameras are typically employed for fine-grained manipulation tasks. Existing approaches (e.g., ACT) tend to treat multi-view features equally and directly concatenate them for policy learning. However, it will introduce redundant visual information and bring higher computational costs, leading to ineffective manipulation. For a fine-grained manipulation task, it tends to involve multiple stages while the most contributed view for different stages is varied over time. In this paper, we propose a plug-and-play best-feature-aware (BFA) fusion strategy for multi-view manipulation tasks, which is adaptable to various policies. Built upon the visual backbone of the policy network, we design a lightweight network to predict the importance score of each view. Based on the predicted importance scores, the reweighted multi-view features are subsequently fused and input into the end-to-end policy network, enabling seamless integration. Notably, our method demonstrates outstanding performance in fine-grained manipulations. Experimental results show that our approach outperforms multiple baselines by 22-46% success rate on different tasks. Our work provides new insights and inspiration for tackling key challenges in fine-grained manipulations.

cs.RO↗

arXiv2025

Kling-Foley: Multimodal Diffusion Transformer for High-Quality Video-to-Audio Generation

We propose Kling-Foley, a large-scale multimodal Video-to-Audio generation model that synthesizes high-quality audio synchronized with video content. In Kling-Foley, we introduce multimodal diffusion transformers to model the interactions between video, audio, and text modalities, and combine it with a visual semantic representation module and an audio-visual synchronization module to enhance alignment capabilities. Specifically, these modules align video conditions with latent audio elements at the frame level, thereby improving semantic alignment and audio-visual synchronization. Together with text conditions, this integrated approach enables precise generation of video-matching sound effects. In addition, we propose a universal latent audio codec that can achieve high-quality modeling in various scenarios such as sound effects, speech, singing, and music. We employ a stereo rendering method that imbues synthesized audio with a spatial presence. At the same time, in order to make up for the incomplete types and annotations of the open-source benchmark, we also open-source an industrial-level benchmark Kling-Audio-Eval. Our experiments show that Kling-Foley trained with the flow matching objective achieves new audio-visual SOTA performance among public models in terms of distribution matching, semantic alignment, temporal alignment and audio quality.

eess.AS↗

arXiv2025

PR-DETR: Injecting Position and Relation Prior for Dense Video Captioning

Dense video captioning is a challenging task that aims to localize and caption multiple events in an untrimmed video. Recent studies mainly follow the transformer-based architecture to jointly perform the two sub-tasks, i.e., event localization and caption generation, in an end-to-end manner. Based on the general philosophy of detection transformer, these methods implicitly learn the event locations and event semantics, which requires a large amount of training data and limits the model's performance in practice. In this paper, we propose a novel dense video captioning framework, named PR-DETR, which injects the explicit position and relation prior into the detection transformer to improve the localization accuracy and caption quality, simultaneously. On the one hand, we first generate a set of position-anchored queries to provide the scene-specific position and semantic information about potential events as position prior, which serves as the initial event search regions to eliminate the implausible event proposals. On the other hand, we further design an event relation encoder to explicitly calculate the relationship between event boundaries as relation prior to guide the event interaction to improve the semantic coherence of the captions. Extensive ablation studies are conducted to verify the effectiveness of the position and relation prior. Experimental results also show the competitive performance of our method on ActivityNet Captions and YouCook2 datasets.

cs.CV↗

arXiv2025

FlowRAM: Grounding Flow Matching Policy with Region-Aware Mamba Framework for Robotic Manipulation

Robotic manipulation in high-precision tasks is essential for numerous industrial and real-world applications where accuracy and speed are required. Yet current diffusion-based policy learning methods generally suffer from low computational efficiency due to the iterative denoising process during inference. Moreover, these methods do not fully explore the potential of generative models for enhancing information exploration in 3D environments. In response, we propose FlowRAM, a novel framework that leverages generative models to achieve region-aware perception, enabling efficient multimodal information processing. Specifically, we devise a Dynamic Radius Schedule, which allows adaptive perception, facilitating transitions from global scene comprehension to fine-grained geometric details. Furthermore, we integrate state space models to integrate multimodal information, while preserving linear computational complexity. In addition, we employ conditional flow matching to learn action poses by regressing deterministic vector fields, simplifying the learning process while maintaining performance. We verify the effectiveness of the FlowRAM in the RLBench, an established manipulation benchmark, and achieve state-of-the-art performance. The results demonstrate that FlowRAM achieves a remarkable improvement, particularly in high-precision tasks, where it outperforms previous methods by 12.0% in average success rate. Additionally, FlowRAM is able to generate physically plausible actions for a variety of real-world tasks in less than 4 time steps, significantly increasing inference speed.

cs.RO↗

arXiv2025

Time-Unified Diffusion Policy with Action Discrimination for Robotic Manipulation

In many complex scenarios, robotic manipulation relies on generative models to estimate the distribution of multiple successful actions. As the diffusion model has better training robustness than other generative models, it performs well in imitation learning through successful robot demonstrations. However, the diffusion-based policy methods typically require significant time to iteratively denoise robot actions, which hinders real-time responses in robotic manipulation. Moreover, existing diffusion policies model a time-varying action denoising process, whose temporal complexity increases the difficulty of model training and leads to suboptimal action accuracy. To generate robot actions efficiently and accurately, we present the Time-Unified Diffusion Policy (TUDP), which utilizes action recognition capabilities to build a time-unified denoising process. On the one hand, we build a time-unified velocity field in action space with additional action discrimination information. By unifying all timesteps of action denoising, our velocity field reduces the difficulty of policy learning and speeds up action generation. On the other hand, we propose an action-wise training method, which introduces an action discrimination branch to supply additional action discrimination information. Through action-wise training, the TUDP implicitly learns the ability to discern successful actions to better denoising accuracy. Our method achieves state-of-the-art performance on RLBench with the highest success rate of 82.6% on a multi-view setup and 83.8% on a single-view setup. In particular, when using fewer denoising iterations, TUDP achieves a more significant improvement in success rate. Additionally, TUDP can produce accurate actions for a wide range of real-world tasks.

cs.RO↗

arXiv2025

LayoutRAG: Retrieval-Augmented Model for Content-agnostic Conditional Layout Generation

Controllable layout generation aims to create plausible visual arrangements of element bounding boxes within a graphic design according to certain optional constraints, such as the type or position of a specific component. While recent diffusion or flow-matching models have achieved considerable advances in multifarious conditional generation tasks, there remains considerable room for generating optimal arrangements under given conditions. In this work, we propose to carry out layout generation through retrieving by conditions and reference-guided generation. Specifically, we retrieve appropriate layout templates according to given conditions as references. The references are then utilized to guide the denoising or flow-based transport process. By retrieving layouts compatible with the given conditions, we can uncover the potential information not explicitly provided in the given condition. Such an approach offers more effective guidance to the model during the generation process, in contrast to previous models that feed the condition to the model and let the model infer the unprovided layout attributes directly. Meanwhile, we design a condition-modulated attention that selectively absorbs retrieval knowledge, adapting to the difference between retrieved templates and given conditions. Extensive experiment results show that our method successfully produces high-quality layouts that meet the given conditions and outperforms existing state-of-the-art models. Code will be released upon acceptance.

cs.CV↗

arXiv2025

From Mapping to Composing: A Two-Stage Framework for Zero-shot Composed Image Retrieval

Composed Image Retrieval (CIR) is a challenging multimodal task that retrieves a target image based on a reference image and accompanying modification text. Due to the high cost of annotating CIR triplet datasets, zero-shot (ZS) CIR has gained traction as a promising alternative. Existing studies mainly focus on projection-based methods, which map an image to a single pseudo-word token. However, these methods face three critical challenges: (1) insufficient pseudo-word token representation capacity, (2) discrepancies between training and inference phases, and (3) reliance on large-scale synthetic data. To address these issues, we propose a two-stage framework where the training is accomplished from mapping to composing. In the first stage, we enhance image-to-pseudo-word token learning by introducing a visual semantic injection module and a soft text alignment objective, enabling the token to capture richer and fine-grained image information. In the second stage, we optimize the text encoder using a small amount of synthetic triplet data, enabling it to effectively extract compositional semantics by combining pseudo-word tokens with modification text for accurate target image retrieval. The strong visual-to-pseudo mapping established in the first stage provides a solid foundation for the second stage, making our approach compatible with both high- and low-quality synthetic data, and capable of achieving significant performance gains with only a small amount of synthetic data. Extensive experiments were conducted on three public datasets, achieving superior performance compared to existing approaches.

cs.CV↗

arXiv2025

Geometric Asymmetry-Enhanced Nonreciprocal Supercurrent Transport Revealed by Second-Harmonic Response

Nonreciprocal transport in superconducting systems serves as a powerful probe of symmetry-breaking mechanisms, with the superconducting diode effect emerging as a key manifestation enabling cryogenic rectification. While theoretical models have extensively explored superconducting nonreciprocity, experimental verification remains challenging, as conventional transport measurements struggle to disentangle intrinsic and extrinsic contributions. Nonlinear transport analysis, particularly second-harmonic response, offers an alternative approach by providing a sensitive probe for detecting spatial inversion symmetry breaking in the presence of time-reversal symmetry violation. Here, we systematically investigate the influence of geometric symmetry on nonreciprocal transport by comparing two triangular-extended Hall bar configurations with a symmetric Hall bar control. Second-harmonic nonlinear transport measurements reveal that the triangular extension significantly enhances nonreciprocal response, exhibiting a clear dependence on the base angle of the extension. These findings establish a direct connection between mesoscopic geometry and macroscopic nonreciprocity, demonstrating how spatial symmetry and vortex dynamics govern nonlinear transport. This insight offers a guiding principle for designing superconducting rectification architectures.

cond-mat.supr-con↗

arXiv2025

Moment Quantization for Video Temporal Grounding

Video temporal grounding is a critical video understanding task, which aims to localize moments relevant to a language description. The challenge of this task lies in distinguishing relevant and irrelevant moments. Previous methods focused on learning continuous features exhibit weak differentiation between foreground and background features. In this paper, we propose a novel Moment-Quantization based Video Temporal Grounding method (MQVTG), which quantizes the input video into various discrete vectors to enhance the discrimination between relevant and irrelevant moments. Specifically, MQVTG maintains a learnable moment codebook, where each video moment matches a codeword. Considering the visual diversity, i.e., various visual expressions for the same moment, MQVTG treats moment-codeword matching as a clustering process without using discrete vectors, avoiding the loss of useful information from direct hard quantization. Additionally, we employ effective prior-initialization and joint-projection strategies to enhance the maintained moment codebook. With its simple implementation, the proposed method can be integrated into existing temporal grounding models as a plug-and-play component. Extensive experiments on six popular benchmarks demonstrate the effectiveness and generalizability of MQVTG, significantly outperforming state-of-the-art methods. Further qualitative analysis shows that our method effectively groups relevant features and separates irrelevant ones, aligning with our goal of enhancing discrimination.

cs.CV↗

arXiv2025

Selective Oxidation and Cr Segregation in High-Entropy Oxide Thin Films

High-entropy oxides (HEOs) offer exceptional compositional flexibility and structural stability, making them promising materials for energy and catalytic applications. Here, we investigate Sr doping effects on B-site cation oxidation states, local composition, and structure in epitaxial La1-xSrx(Cr0.2Mn0.2Fe0.2Co0.2Ni0.2)O3 thin films. X-ray spectroscopies reveal that Sr doping preferentially promotes Cr oxidation from Cr3+ to Cr6+, partially oxidizes Co and Ni, while leaving Mn4+ and Fe3+ unchanged. Atomic-resolution scanning transmission electron microscopy with energy-dispersive X-ray spectroscopy shows pronounced Cr segregation, with Cr exhibiting depletion at the film-substrate interface and enrichment at the film surface, along with the formation of a partially amorphous phase in heavily Sr-doped samples. This segregation is likely driven by oxidation-induced migration of smaller, high-valence Cr cations during the growth. These findings underscore the critical interplay between charge transfer, local strain, and compositional fluctuations, providing strategies to control surface composition and electronic structure in HEOs for more robust electrocatalyst design.

cond-mat.mtrl-sci↗

arXiv2025

Berezinskii-Kosterlitz-Thouless region and magnetization plateaus in easy-axis triangular weak-dimer antiferromagnet K$_2$Co$_2$(SeO$_3$)$_3$

We investigate the magnetic phase diagram of the bilayer triangular antiferromagnet K$_2$Co$_2$(SeO$_3$)$_3$, revealing a rich interplay among geometric frustration, bilayer coupling, and symmetry-driven phenomena. High-field magnetization measurements show fractional magnetization plateaus at 1/3, 1/2, 2/3, and 5/6 of the saturation magnetization. To elucidate the experimental magnetic phase diagram at low fields, we propose that K$_2$Co$_2$(SeO$_3$)$_3$ can be described as an easy-axis triangular weak-dimer antiferromagnet. We emphasize the critical role of the emergent $U(1) \otimes S_3$ symmetry, where $S_3 = \mathbb{Z}_3 \otimes \mathbb{Z}_2^d$, in determining the magnetic phases at low fields. The remarkable agreement between the experimental and theoretical phase diagrams suggests that the phase transitions are governed by this symmetry. Notably, our combined experimental and theoretical results identify a Berezinskii-Kosterlitz-Thouless (BKT) phase region at finite fields. These findings provide new insights into the phase structure of frustrated magnets and establish K$_2$Co$_2$(SeO$_3$)$_3$ as a compelling platform for exploring unconventional quantum phenomena in $U(1) \otimes S_3$ systems.

cond-mat.str-el↗

arXiv2025

CogMorph: Cognitive Morphing Attacks for Text-to-Image Models

The development of text-to-image (T2I) generative models, that enable the creation of high-quality synthetic images from textual prompts, has opened new frontiers in creative design and content generation. However, this paper reveals a significant and previously unrecognized ethical risk inherent in this technology and introduces a novel method, termed the Cognitive Morphing Attack (CogMorph), which manipulates T2I models to generate images that retain the original core subjects but embeds toxic or harmful contextual elements. This nuanced manipulation exploits the cognitive principle that human perception of concepts is shaped by the entire visual scene and its context, producing images that amplify emotional harm far beyond attacks that merely preserve the original semantics. To address this, we first construct an imagery toxicity taxonomy spanning 10 major and 48 sub-categories, aligned with human cognitive-perceptual dimensions, and further build a toxicity risk matrix resulting in 1,176 high-quality T2I toxic prompts. Based on this, our CogMorph first introduces Cognitive Toxicity Augmentation, which develops a cognitive toxicity knowledge base with rich external toxic representations for humans (e.g., fine-grained visual features) that can be utilized to further guide the optimization of adversarial prompts. In addition, we present Contextual Hierarchical Morphing, which hierarchically extracts critical parts of the original prompt (e.g., scenes, subjects, and body parts), and then iteratively retrieves and fuses toxic features to inject harmful contexts. Extensive experiments on multiple open-sourced T2I models and black-box commercial APIs (e.g., DALLE-3) demonstrate the efficacy of CogMorph which significantly outperforms other baselines by large margins (+20.62% on average).

cs.CV↗

arXiv2024

Referencing Where to Focus: Improving VisualGrounding with Referential Query

Visual Grounding aims to localize the referring object in an image given a natural language expression. Recent advancements in DETR-based visual grounding methods have attracted considerable attention, as they directly predict the coordinates of the target object without relying on additional efforts, such as pre-generated proposal candidates or pre-defined anchor boxes. However, existing research primarily focuses on designing stronger multi-modal decoder, which typically generates learnable queries by random initialization or by using linguistic embeddings. This vanilla query generation approach inevitably increases the learning difficulty for the model, as it does not involve any target-related information at the beginning of decoding. Furthermore, they only use the deepest image feature during the query learning process, overlooking the importance of features from other levels. To address these issues, we propose a novel approach, called RefFormer. It consists of the query adaption module that can be seamlessly integrated into CLIP and generate the referential query to provide the prior context for decoder, along with a task-specific decoder. By incorporating the referential query into the decoder, we can effectively mitigate the learning difficulty of the decoder, and accurately concentrate on the target object. Additionally, our proposed query adaption module can also act as an adapter, preserving the rich knowledge within CLIP without the need to tune the parameters of the backbone network. Extensive experiments demonstrate the effectiveness and efficiency of our proposed method, outperforming state-of-the-art approaches on five visual grounding benchmarks.

cs.CV↗

arXiv2024

Recurrent Aligned Network for Generalized Pedestrian Trajectory Prediction

Pedestrian trajectory prediction is a crucial component in computer vision and robotics, but remains challenging due to the domain shift problem. Previous studies have tried to tackle this problem by leveraging a portion of the trajectory data from the target domain to adapt the model. However, such domain adaptation methods are impractical in real-world scenarios, as it is infeasible to collect trajectory data from all potential target domains. In this paper, we study a task named generalized pedestrian trajectory prediction, with the aim of generalizing the model to unseen domains without accessing their trajectories. To tackle this task, we introduce a Recurrent Aligned Network~(RAN) to minimize the domain gap through domain alignment. Specifically, we devise a recurrent alignment module to effectively align the trajectory feature spaces at both time-state and time-sequence levels by the recurrent alignment strategy.Furthermore, we introduce a pre-aligned representation module to combine social interactions with the recurrent alignment strategy, which aims to consider social interactions during the alignment process instead of just target trajectories. We extensively evaluate our method and compare it with state-of-the-art methods on three widely used benchmarks. The experimental results demonstrate the superior generalization capability of our method. Our work not only fills the gap in the generalization setting for practical pedestrian trajectory prediction but also sets strong baselines in this field.

cs.CV↗

arXiv2024

Diversifying Query: Region-Guided Transformer for Temporal Sentence Grounding

Temporal sentence grounding is a challenging task that aims to localize the moment spans relevant to a language description. Although recent DETR-based models have achieved notable progress by leveraging multiple learnable moment queries, they suffer from overlapped and redundant proposals, leading to inaccurate predictions. We attribute this limitation to the lack of task-related guidance for the learnable queries to serve a specific mode. Furthermore, the complex solution space generated by variable and open-vocabulary language descriptions complicates optimization, making it harder for learnable queries to distinguish each other adaptively. To tackle this limitation, we present a Region-Guided TRansformer (RGTR) for temporal sentence grounding, which diversifies moment queries to eliminate overlapped and redundant predictions. Instead of using learnable queries, RGTR adopts a set of anchor pairs as moment queries to introduce explicit regional guidance. Each anchor pair takes charge of moment prediction for a specific temporal region, which reduces the optimization difficulty and ensures the diversity of the final predictions. In addition, we design an IoU-aware scoring head to improve proposal quality. Extensive experiments demonstrate the effectiveness of RGTR, outperforming state-of-the-art methods on QVHighlights, Charades-STA and TACoS datasets. Codes are available at https://github.com/TensorsSun/RGTR

cs.CV↗

arXiv2024

Neural-Network-Enhanced Metalens Camera for High-Definition, Dynamic Imaging in the Long-Wave Infrared Spectrum

To provide a lightweight and cost-effective solution for the long-wave infrared imaging using a singlet, we develop a camera by integrating a High-Frequency-Enhancing Cycle-GAN neural network into a metalens imaging system. The High-Frequency-Enhancing Cycle-GAN improves the quality of the original metalens images by addressing inherent frequency loss introduced by the metalens. In addition to the bidirectional cyclic generative adversarial network, it incorporates a high-frequency adversarial learning module. This module utilizes wavelet transform to extract high-frequency components, and then establishes a high-frequency feedback loop. It enables the generator to enhance the camera outputs by integrating adversarial feedback from the high-frequency discriminator. This ensures that the generator adheres to the constraints imposed by the high-frequency adversarial loss, thereby effectively recovering the camera's frequency loss. This recovery guarantees high-fidelity image output from the camera, facilitating smooth video production. Our camera is capable of achieving dynamic imaging at 125 frames per second with an End Point Error value of 12.58. We also achieve 0.42 for Fréchet Inception Distance, 30.62 for Peak Signal to Noise Ratio, and 0.69 for Structural Similarity in the recorded videos.

eess.IV↗

arXiv2024

Revealing the Evolution of Order in Materials Microstructures Using Multi-Modal Computer Vision

The development of high-performance materials for microelectronics, energy storage, and extreme environments depends on our ability to describe and direct property-defining microstructural order. Our present understanding is typically derived from laborious manual analysis of imaging and spectroscopy data, which is difficult to scale, challenging to reproduce, and lacks the ability to reveal latent associations needed for mechanistic models. Here, we demonstrate a multi-modal machine learning (ML) approach to describe order from electron microscopy analysis of the complex oxide La$_{1-x}$Sr$_x$FeO$_3$. We construct a hybrid pipeline based on fully and semi-supervised classification, allowing us to evaluate both the characteristics of each data modality and the value each modality adds to the ensemble. We observe distinct differences in the performance of uni- and multi-modal models, from which we draw general lessons in describing crystal order using computer vision.

cond-mat.mtrl-sci↗

arXiv2024

Bose-Einstein condensation of a two-magnon bound state in a spin-one triangular lattice

In ordered magnets, the elementary excitations are spin waves (magnons), which obey Bose-Einstein statistics. Similarly to Cooper pairs in superconductors, magnons can be paired into bound states under attractive interactions. The Zeeman coupling to a magnetic field is able to tune the particle density through a quantum critical point (QCP), beyond which a "hidden order" is predicted to exist. Here we report direct observation of the Bose-Einstein condensation (BEC) of the two-magnon bound state in Na$_2$BaNi(PO$_4$)$_2$. Comprehensive thermodynamic measurements confirmed the two-dimensional BEC-QCP at the saturation field. Inelastic neutron scattering experiments were performed to establish the microscopic model. An exact solution revealed stable 2-magnon bound states that were further confirmed by electron spin resonance and nuclear magnetic resonance experiments, demonstrating that the QCP is due to the pair condensation and the phase below saturation field is likely the long-sought-after spin nematic phase.

cond-mat.str-el↗