arXiv subjects

Bing Wang

Publications and source records attributed to Bing Wang.

At least 91 records · Page 5Linked to original sources

arXiv2026

Robust quantized transport from topological quasienergy winding in long-range-coupling synthetic quantum walks

Quantized transport is a prominent feature in topological physics, with canonical examples being the quantum Hall effect and adiabatic Thouless pump, which are based on the Chern number, a topological invariant of 2D systems. Going beyond the Chern-number-based paradigms, quantized transports can also arise from k-direction quasienergy winding unique to periodically driven (Floquet) systems, which are free of dimensionality and adiabaticity limitations. However, lattices displaying winding of their quasienergy bands require asymmetric long-range couplings that are difficult to achieve in lattices of real-space coupled sites. Here, by leveraging photonic synthetic dimensions we construct asymmetric long-range-couplings in a one-dimensional temporal quantum walk based on three coupled fiber loops. We demonstrate quantized transport arising from the winding of quasienergy bands in k direction. We show that the average group velocity of an initial wave packet is proportional to the winding number, which leads to a quantized transport displacement. To better visualize this quantized displacement, we cascade two regions with flipped nearest/long-range couplings and observe a focusing effect with a quantized spatial shift in the focusing point. We also probe the robust properties of quantized transport against obstacles and disorders. The study initiates quasienergy-winding-based topological transports, which can feature applications in precise and robust imaging and information processing.

physics.optics↗

arXiv2026

UFO: Unifying Feed-Forward and Optimization-based Methods for Large Driving Scene Modeling

Dynamic driving scene reconstruction is critical for autonomous driving simulation and closed-loop learning. While recent feed-forward methods have shown promise for 3D reconstruction, they struggle with long-range driving sequences due to quadratic complexity in sequence length and challenges in modeling dynamic objects over extended durations. We propose UFO, a novel recurrent paradigm that combines the benefits of optimization-based and feed-forward methods for efficient long-range 4D reconstruction. Our approach maintains a 4D scene representation that is iteratively refined as new observations arrive, using a visibility-based filtering mechanism to select informative scene tokens and enable efficient processing of long sequences. For dynamic objects, we introduce an object pose-guided modeling approach that supports accurate long-range motion capture. Experiments on the Waymo Open Dataset demonstrate that our method significantly outperforms both per-scene optimization and existing feed-forward methods across various sequence lengths. Notably, our approach can reconstruct 16-second driving logs within 0.5 second while maintaining superior visual quality and geometric accuracy.

cs.CV↗

arXiv2026

Where Did This Sentence Come From? Tracing Provenance in LLM Reasoning Distillation

Reasoning distillation has attracted increasing attention. It typically leverages a large teacher model to generate reasoning paths, which are then used to fine-tune a student model so that it mimics the teacher's behavior in training contexts. However, previous approaches have lacked a detailed analysis of the origins of the distilled model's capabilities. It remains unclear whether the student can maintain consistent behaviors with the teacher in novel test-time contexts, or whether it regresses to its original output patterns, raising concerns about the generalization of distillation models. To analyse this question, we introduce a cross-model Reasoning Distillation Provenance Tracing framework. For each action (e.g., a sentence) produced by the distilled model, we obtain the predictive probabilities assigned by the teacher, the original student, and the distilled model under the same context. By comparing these probabilities, we classify each action into different categories. By systematically disentangling the provenance of each action, we experimentally demonstrate that, in test-time contexts, the distilled model can indeed generate teacher-originated actions, which correlate with and plausibly explain observed performance on distilled model. Building on this analysis, we further propose a teacher-guided data selection method. Unlike prior approach that rely on heuristics, our method directly compares teacher-student divergences on the training data, providing a principled selection criterion. We validate the effectiveness of our approach across multiple representative teacher models and diverse student models. The results highlight the utility of our provenance-tracing framework and underscore its promise for reasoning distillation. We hope to share Reasoning Distillation Provenance Tracing and our insights into reasoning distillation with the community.

cs.CL↗

arXiv2026

Efficient Scene Modeling via Structure-Aware and Region-Prioritized 3D Gaussians

Reconstructing 3D scenes with high fidelity and efficiency remains a central pursuit in computer vision and graphics. Recent advances in 3D Gaussian Splatting (3DGS) enable photorealistic rendering with Gaussian primitives, yet the modeling process remains governed predominantly by photometric supervision. This reliance often leads to irregular spatial distribution and indiscriminate primitive adjustments that largely ignore underlying geometric context. In this work, we rethink Gaussian modeling from a geometric standpoint and introduce Mini-Splatting2, an efficient scene modeling framework that couples structure-aware distribution and region-prioritized optimization, driving 3DGS into a geometry-regulated paradigm. The structure-aware distribution enforces spatial regularity through structured reorganization and representation sparsity, ensuring balanced structural coverage for compact organization. The region-prioritized optimization improves training discrimination through geometric saliency and computational selectivity, fostering appropriate structural emergence for fast convergence. These mechanisms alleviate the long-standing tension among representation compactness, convergence acceleration, and rendering fidelity. Extensive experiments demonstrate that Mini-Splatting2 achieves up to 4$\times$ fewer Gaussians and 3$\times$ faster optimization while maintaining state-of-the-art visual quality, paving the way towards structured and efficient 3D Gaussian modeling.

cs.CV↗

arXiv2026

VILTA: A VLM-in-the-Loop Adversary for Enhancing Driving Policy Robustness

The safe deployment of autonomous driving (AD) systems is fundamentally hindered by the long-tail problem, where rare yet critical driving scenarios are severely underrepresented in real-world data. Existing solutions including safety-critical scenario generation and closed-loop learning often rely on rule-based heuristics, resampling methods and generative models learned from offline datasets, limiting their ability to produce diverse and novel challenges. While recent works leverage Vision Language Models (VLMs) to produce scene descriptions that guide a separate, downstream model in generating hazardous trajectories for agents, such two-stage framework constrains the generative potential of VLMs, as the diversity of the final trajectories is ultimately limited by the generalization ceiling of the downstream algorithm. To overcome these limitations, we introduce VILTA (VLM-In-the-Loop Trajectory Adversary), a novel framework that integrates a VLM into the closed-loop training of AD agents. Unlike prior works, VILTA actively participates in the training loop by comprehending the dynamic driving environment and strategically generating challenging scenarios through direct, fine-grained editing of surrounding agents' future trajectories. This direct-editing approach fully leverages the VLM's powerful generalization capabilities to create a diverse curriculum of plausible yet challenging scenarios that extend beyond the scope of traditional methods. We demonstrate that our approach substantially enhances the safety and robustness of the resulting AD policy, particularly in its ability to navigate critical long-tail events.

cs.CV↗

arXiv2026

Distribution-Aligned Sequence Distillation for Superior Long-CoT Reasoning

In this report, we introduce DASD-4B-Thinking, a lightweight yet highly capable, fully open-source reasoning model. It achieves SOTA performance among open-source models of comparable scale across challenging benchmarks in mathematics, scientific reasoning, and code generation -- even outperforming several larger models. We begin by critically reexamining a widely adopted distillation paradigm in the community: SFT on teacher-generated responses, also known as sequence-level distillation. Although a series of recent works following this scheme have demonstrated remarkable efficiency and strong empirical performance, they are primarily grounded in the SFT perspective. Consequently, these approaches focus predominantly on designing heuristic rules for SFT data filtering, while largely overlooking the core principle of distillation itself -- enabling the student model to learn the teacher's full output distribution so as to inherit its generalization capability. Specifically, we identify three critical limitations in current practice: i) Inadequate representation of the teacher's sequence-level distribution; ii) Misalignment between the teacher's output distribution and the student's learning capacity; and iii) Exposure bias arising from teacher-forced training versus autoregressive inference. In summary, these shortcomings reflect a systemic absence of explicit teacher-student interaction throughout the distillation process, leaving the essence of distillation underexploited. To address these issues, we propose several methodological innovations that collectively form an enhanced sequence-level distillation training pipeline. Remarkably, DASD-4B-Thinking obtains competitive results using only 448K training samples -- an order of magnitude fewer than those employed by most existing open-source efforts. To support community research, we publicly release our models and the training dataset.

cs.LG↗

arXiv2026

TiInsight: A SQL-based Automated Exploratory Data Analysis System through Large Language Models

The SQL-based exploratory data analysis has garnered significant attention within the data analysis community. The emergence of large language models (LLMs) has facilitated the paradigm shift from manual to automated data exploration. However, existing methods generally lack the ability for cross-domain analysis, and the exploration of LLMs capabilities remains insufficient. This paper presents TiInsight, an SQL-based automated cross-domain exploratory data analysis system. First, TiInsight offers a user-friendly GUI enabling users to explore data using natural language queries. Second, TiInsight offers a robust cross-domain exploratory data analysis pipeline: hierarchical data context (i.e., HDC) generation, question clarification and decomposition, text-to-SQL (i.e., TiSQL), and data visualization (i.e., TiChart). Third, we have implemented and deployed TiInsight in the production environment of PingCAP and demonstrated its capabilities using representative datasets. The demo video is available at https://youtu.be/JzYFyYd-emI.

cs.DB↗

arXiv2026

Pixel-Perfect Visual Geometry Estimation

Recovering clean and accurate geometry from images is essential for robotics and augmented reality. However, existing geometry foundation models still suffer severely from flying pixels and the loss of fine details. In this paper, we present pixel-perfect visual geometry models that can predict high-quality, flying-pixel-free point clouds by leveraging generative modeling in the pixel space. We first introduce Pixel-Perfect Depth (PPD), a monocular depth foundation model built upon pixel-space diffusion transformers (DiT). To address the high computational complexity associated with pixel-space diffusion, we propose two key designs: 1) Semantics-Prompted DiT, which incorporates semantic representations from vision foundation models to prompt the diffusion process, preserving global semantics while enhancing fine-grained visual details; and 2) Cascade DiT architecture that progressively increases the number of image tokens, improving both efficiency and accuracy. To further extend PPD to video (PPVD), we introduce a new Semantics-Consistent DiT, which extracts temporally consistent semantics from a multi-view geometry foundation model. We then perform reference-guided token propagation within the DiT to maintain temporal coherence with minimal computational and memory overhead. Our models achieve the best performance among all generative monocular and video depth estimation models and produce significantly cleaner point clouds than all other models.

cs.CV↗

arXiv2026

ParkGaussian: Surround-view 3D Gaussian Splatting for Autonomous Parking

Parking is a critical task for autonomous driving systems (ADS), with unique challenges in crowded parking slots and GPS-denied environments. However, existing works focus on 2D parking slot perception, mapping, and localization, 3D reconstruction remains underexplored, which is crucial for capturing complex spatial geometry in parking scenarios. Naively improving the visual quality of reconstructed parking scenes does not directly benefit autonomous parking, as the key entry point for parking is the slots perception module. To address these limitations, we curate the first benchmark named ParkRecon3D, specifically designed for parking scene reconstruction. It includes sensor data from four surround-view fisheye cameras with calibrated extrinsics and dense parking slot annotations. We then propose ParkGaussian, the first framework that integrates 3D Gaussian Splatting (3DGS) for parking scene reconstruction. To further improve the alignment between reconstruction and downstream parking slot detection, we introduce a slot-aware reconstruction strategy that leverages existing parking perception methods to enhance the synthesis quality of slot regions. Experiments on ParkRecon3D demonstrate that ParkGaussian achieves state-of-the-art reconstruction quality and better preserves perception consistency for downstream tasks. The code and dataset will be released at: https://github.com/wm-research/ParkGaussian

cs.CV↗

arXiv2025

Mirage: One-Step Video Diffusion for Photorealistic and Coherent Asset Editing in Driving Scenes

Vision-centric autonomous driving systems rely on diverse and scalable training data to achieve robust performance. While video object editing offers a promising path for data augmentation, existing methods often struggle to maintain both high visual fidelity and temporal coherence. In this work, we propose \textbf{Mirage}, a one-step video diffusion model for photorealistic and coherent asset editing in driving scenes. Mirage builds upon a text-to-video diffusion prior to ensure temporal consistency across frames. However, 3D causal variational autoencoders often suffer from degraded spatial fidelity due to compression, and directly passing 3D encoder features to decoder layers breaks temporal causality. To address this, we inject temporally agnostic latents from a pretrained 2D encoder into the 3D decoder to restore detail while preserving causal structures. Furthermore, because scene objects and inserted assets are optimized under different objectives, their Gaussians exhibit a distribution mismatch that leads to pose misalignment. To mitigate this, we introduce a two-stage data alignment strategy combining coarse 3D alignment and fine 2D refinement, thereby improving alignment and providing cleaner supervision. Extensive experiments demonstrate that Mirage achieves high realism and temporal consistency across diverse editing scenarios. Beyond asset editing, Mirage can also generalize to other video-to-video translation tasks, serving as a reliable baseline for future research. Our code is available at https://github.com/wm-research/mirage.

cs.CV↗

arXiv2025

Solar jet-induced perturbation propagating through coronal loops and in-loop electron beam transport indicated by type II and type N radio bursts

Solar type II radio bursts are commonly attributed to coronal shocks driven by coronal mass ejections (CMEs). However, some metric type II bursts have occasionally been reported to occur in the absence of a CME and to be associated with weak solar activities. This study aims to identify the driver of the coronal shock in this kind of type II event. We investigate a high-frequency metric type II burst with clear band splitting, observed simultaneously by the Chashan Broadband Solar radio spectrograph and the Nançay Radioheliograph. It is associated with a C3.1-class flare and a small-scale jet, but without a detectable CME in the coronagraphs. The type II burst is preceded by multiple type III bursts, one of which exhibits characteristics of a type N burst. The type II burst source is associated with the jet-induced perturbation front propagating through nearby closed loops at a speed of $\sim$880 km s$^{-1}$, rather than the much slower jet front. This suggests that the disturbance initiated by the jet can convert to a shock wave within low Alfvénic coronal loops, providing the necessary conditions for electron acceleration and subsequent radio emission. Our findings offer new insights into the formation mechanism of high-frequency type II bursts associated with weak flares and jets.

astro-ph.SR↗

arXiv2025

Opportunistic Scheduling for Single-downlink Satellite-based Quantum Key Distribution

Satellite-based quantum key distribution (QKD), leveraging low photon loss in free-space quantum communication, is widely regarded as one of the most promising directions to achieve global-scale QKD. With a constellation of satellites and a set of ground stations in a satellite-based QKD system, how to schedule satellites to achieve efficient QKD is an important problem. This problem has been studied in the dual-downlink architecture, where each satellite distributes pairs of entanglements to two ground stations simultaneously. However, it has not been studied in the single downlink architecture, where satellites create keys with each individual ground station, and then serve as trusted nodes to create keys between pairs of ground stations. While the single downlink architecture provides weaker security in that the satellites need to be trusted, it has many advantages, including the potential of achieving significantly higher key rates, and generating keys between pairs of ground stations that are far away from each other and cannot be served using the dual-downlink architecture. In this paper, we propose a novel opportunistic approach for satellite scheduling that accounts for fairness among the ground station pairs, while taking advantage of the dynamic satellite channels to maximize the system performance. We evaluate this approach in a wide range of settings and demonstrate that it provides the best tradeoffs in terms of total and minimum key rates across the ground station pairs. Our evaluation also highlights the importance of considering seasonal effects and cloud coverage in evaluating satellite-based QKD systems. In addition, we show different tradeoffs in global and regional QKD systems.

quant-ph↗

arXiv2025

DGGT: Feedforward 4D Reconstruction of Dynamic Driving Scenes using Unposed Images

Autonomous driving needs fast, scalable 4D reconstruction and re-simulation for training and evaluation, yet most methods for dynamic driving scenes still rely on per-scene optimization, known camera calibration, or short frame windows, making them slow and impractical. We revisit this problem from a feedforward perspective and introduce \textbf{Driving Gaussian Grounded Transformer (DGGT)}, a unified framework for pose-free dynamic scene reconstruction. We note that the existing formulations, treating camera pose as a required input, limit flexibility and scalability. Instead, we reformulate pose as an output of the model, enabling reconstruction directly from sparse, unposed images and supporting an arbitrary number of views for long sequences. Our approach jointly predicts per-frame 3D Gaussian maps and camera parameters, disentangles dynamics with a lightweight dynamic head, and preserves temporal consistency with a lifespan head that modulates visibility over time. A diffusion-based rendering refinement further reduces motion/interpolation artifacts and improves novel-view quality under sparse inputs. The result is a single-pass, pose-free algorithm that achieves state-of-the-art performance and speed. Trained and evaluated on large-scale driving benchmarks (Waymo, nuScenes, Argoverse2), our method outperforms prior work both when trained on each dataset and in zero-shot transfer across datasets, and it scales well as the number of input frames increases.

cs.CV↗

arXiv2025

Universal convolution from wave dynamics: photonic processing and encryption in synthetic dimension

Convolution, a cornerstone of signal processing and optical neural networks, has traditionally been implemented by mapping mathematical operations onto complex hardware. Here, we overcome this challenge by revealing that wave dynamics in translation-symmetric lattices intrinsically performs convolution, with the dispersion relation uniquely defining the complex-valued kernel. Leveraging this universal principle, we develop a convolutional architecture of minimal complexity through wave evolution in programmable photonic synthetic lattices, delivering high-throughput, multifunctional capabilities at a rate of 13.5 tera-operations per second (TOPS) for image processing. Beyond convolution acceleration, the kernel's complex nature facilitates the photonic simulation of both irreversible diffusion and reversible unitary quantum dynamics under classical incoherent excitation. Capitalizing on the physics-based reversibility and undetectable phase information, we demonstrate a novel convolution-driven optical encryption strategy. This work establishes a unified framework for photonic computing by grounding convolution in wave dynamics, opening avenues toward scalable, multifunctional photonic processors with high integration potential.

physics.optics↗

arXiv2025

Application of the microscopic optical potential of chiral effective field theory in astrophysical neutron-capture reactions

A state-of-the-art microscopic global nucleon-nucleus optical potential has been developed by Whitehead, Lim, and Holt (WLH) within the framework of many-body perturbation theory, incorporating realistic nuclear interactions derived from chiral effective field theory. Given its potentially greater predictive power for reactions involving exotic isotopes, we apply it to the calculations of astrophysical neutron-capture reactions for the first time, which are particularly important to the nucleosynthesis of elements heavier than iron. It is found that this potential provides a good description of experimental known neutron-capture cross sections and Maxwellian-averaged cross sections. For unstable neutron-rich nuclei, we comprehensively calculate the neutron-capture reaction rates for all nuclei with $26\leq Z\leq84$, located between the valley of stability and the neutron drip line, using the backward-forward Monte Carlo method with the $f_{rms}$ deviation as the $χ^2$ estimator. The results reveal a noticeable separation in the uncertainty of rates around an isospin asymmetry of 0.28 under the constraint $f_{rms} \leq 1.56$. This highlights the critical role of isospin dependence in optical potentials and suggests that future developments of the WLH potential may pay special attention to the isospin dependence.

nucl-th↗

arXiv2025

Enhancing Multimodal Misinformation Detection by Replaying the Whole Story from Image Modality Perspective

Multimodal Misinformation Detection (MMD) refers to the task of detecting social media posts involving misinformation, where the post often contains text and image modalities. However, by observing the MMD posts, we hold that the text modality may be much more informative than the image modality because the text generally describes the whole event/story of the current post but the image often presents partial scenes only. Our preliminary empirical results indicate that the image modality exactly contributes less to MMD. Upon this idea, we propose a new MMD method named RETSIMD. Specifically, we suppose that each text can be divided into several segments, and each text segment describes a partial scene that can be presented by an image. Accordingly, we split the text into a sequence of segments, and feed these segments into a pre-trained text-to-image generator to augment a sequence of images. We further incorporate two auxiliary objectives concerning text-image and image-label mutual information, and further post-train the generator over an auxiliary text-to-image generation benchmark dataset. Additionally, we propose a graph structure by defining three heuristic relationships between images, and use a graph neural network to generate the fused features. Extensive empirical results validate the effectiveness of RETSIMD.

cs.CV↗

arXiv2025

LiveStar: Live Streaming Assistant for Real-World Online Video Understanding

Despite significant progress in Video Large Language Models (Video-LLMs) for offline video understanding, existing online Video-LLMs typically struggle to simultaneously process continuous frame-by-frame inputs and determine optimal response timing, often compromising real-time responsiveness and narrative coherence. To address these limitations, we introduce LiveStar, a pioneering live streaming assistant that achieves always-on proactive responses through adaptive streaming decoding. Specifically, LiveStar incorporates: (1) a training strategy enabling incremental video-language alignment for variable-length video streams, preserving temporal consistency across dynamically evolving frame sequences; (2) a response-silence decoding framework that determines optimal proactive response timing via a single forward pass verification; (3) memory-aware acceleration via peak-end memory compression for online inference on 10+ minute videos, combined with streaming key-value cache to achieve 1.53x faster inference. We also construct an OmniStar dataset, a comprehensive dataset for training and benchmarking that encompasses 15 diverse real-world scenarios and 5 evaluation tasks for online video understanding. Extensive experiments across three benchmarks demonstrate LiveStar's state-of-the-art performance, achieving an average 19.5% improvement in semantic correctness with 18.1% reduced timing difference compared to existing online Video-LLMs, while improving FPS by 12.0% across all five OmniStar tasks. Our model and dataset can be accessed at https://github.com/yzy-bupt/LiveStar.

cs.CV↗

arXiv2025

Revealing the structure-property relationships of copper alloys with FAGC

Cu-Cr-Zr alloys play a crucial role in electronic devices and the electric power industry, where their electrical conductivity and hardness are of great importance. However, due to the scarcity of available samples, there has been a lack of effective studies exploring the relationship between the microstructural images of Cu-Cr-Zr alloys and their key properties. In this paper, the FAGC feature augmentation method is employed to enhance the microstructural images of Cu-Cr-Zr alloys within a feature space known as the pre-shape space. Pseudo-labels are then constructed to expand the number of training samples. These features are then input into various machine learning models to construct performance prediction models for the alloy. Finally, we validate the impact of different machine learning methods and the number of augmented features on prediction accuracy through experiments. Experimental results demonstrate that our method achieves superior performance in predicting electrical conductivity ($R^2=0.978$) and hardness ($R^2=0.998$) when using the decision tree classifier with 100 augmented samples. Further analysis reveals that regions with reduced image noise, such as fewer grain or phase boundaries, exhibit higher contributions to electrical conductivity. These findings highlight the potential of the FAGC method in overcoming the challenges of limited image data in materials science, offering a powerful tool for establishing detailed and quantitative relationships between complex microstructures and material properties.

cs.CV↗