arXiv subjects

Bo Zhang

Publications and source records attributed to Bo Zhang.

At least 217 records · Page 12Linked to original sources

arXiv2025

Elastic scattering problems by penetrable obstacles with embedded objects

This paper considers 3-D elastic scattering problems by penetrable obstacles with embedded objects. The well-posedness of transmission problem is proved by employing integral equation method. Then the Inverse Problems , which is to recover the obstacle by the far-field pattern measurement, is considered. It is shown that the inhomogeneous penetrable obstacle can be uniquely determined from the far-field pattern at a fixed frequency.

math.AP↗

arXiv2025

LongCat-Flash-Omni Technical Report

We introduce LongCat-Flash-Omni, a state-of-the-art open-source omni-modal model with 560 billion parameters, excelling at real-time audio-visual interaction. By adopting a curriculum-inspired progressive training strategy that transitions from simpler to increasingly complex modality sequence modeling tasks, LongCat-Flash-Omni attains comprehensive multimodal capabilities while maintaining strong unimodal capability. Building upon LongCat-Flash, which adopts a high-performance Shortcut-connected Mixture-of-Experts (MoE) architecture with zero-computation experts, LongCat-Flash-Omni integrates efficient multimodal perception and speech reconstruction modules. Despite its immense size of 560B parameters (with 27B activated), LongCat-Flash-Omni achieves low-latency real-time audio-visual interaction. For training infrastructure, we developed a modality-decoupled parallelism scheme specifically designed to manage the data and model heterogeneity inherent in large-scale multimodal training. This innovative approach demonstrates exceptional efficiency by sustaining over 90% of the throughput achieved by text-only training. Extensive evaluations show that LongCat-Flash-Omni achieves state-of-the-art performance on omni-modal benchmarks among open-source models. Furthermore, it delivers highly competitive results across a wide range of modality-specific tasks, including text, image, and video understanding, as well as audio understanding and generation. We provide a comprehensive overview of the model architecture design, training procedures, and data strategies, and open-source the model to foster future research and development in the community.

cs.MM↗

arXiv2025

Banach neural operator for Navier-Stokes equations

Classical neural networks are known for their ability to approximate mappings between finite-dimensional spaces, but they fall short in capturing complex operator dynamics across infinite-dimensional function spaces. Neural operators, in contrast, have emerged as powerful tools in scientific machine learning for learning such mappings. However, standard neural operators typically lack mechanisms for mixing or attending to input information across space and time. In this work, we introduce the Banach neural operator (BNO) -- a novel framework that integrates Koopman operator theory with deep neural networks to predict nonlinear, spatiotemporal dynamics from partial observations. The BNO approximates a nonlinear operator between Banach spaces by combining spectral linearization (via Koopman theory) with deep feature learning (via convolutional neural networks and nonlinear activations). This sequence-to-sequence model captures dominant dynamic modes and allows for mesh-independent prediction. Numerical experiments on the Navier-Stokes equations demonstrate the method's accuracy and generalization capabilities. In particular, BNO achieves robust zero-shot super-resolution in unsteady flow prediction and consistently outperforms conventional Koopman-based methods and deep learning models.

cs.NE↗

arXiv2025

ConceptGuard: Proactive Safety in Text-and-Image-to-Video Generation through Multimodal Risk Detection

Recent progress in video generative models has enabled the creation of high-quality videos from multimodal prompts that combine text and images. While these systems offer enhanced controllability, they also introduce new safety risks, as harmful content can emerge from individual modalities or their interaction. Existing safety methods are often text-only, require prior knowledge of the risk category, or operate as post-generation auditors, struggling to proactively mitigate such compositional, multimodal risks. To address this challenge, we present ConceptGuard, a unified safeguard framework for proactively detecting and mitigating unsafe semantics in multimodal video generation. ConceptGuard operates in two stages: First, a contrastive detection module identifies latent safety risks by projecting fused image-text inputs into a structured concept space; Second, a semantic suppression mechanism steers the generative process away from unsafe concepts by intervening in the prompt's multimodal conditioning. To support the development and rigorous evaluation of this framework, we introduce two novel benchmarks: ConceptRisk, a large-scale dataset for training on multimodal risks, and T2VSafetyBench-TI2V, the first benchmark adapted from T2VSafetyBench for the Text-and-Image-to-Video (TI2V) safety setting. Comprehensive experiments on both benchmarks show that ConceptGuard consistently outperforms existing baselines, achieving state-of-the-art results in both risk detection and safe video generation. Our code is available at https://github.com/Ruize-Ma/ConceptGuard.

cs.CV↗

arXiv2025

MovieDreamer: Hierarchical Generation for Coherent Long Visual Sequence

Recent advancements in video generation have primarily leveraged diffusion models for short-duration content. However, these approaches often fall short in modeling complex narratives and maintaining character consistency over extended periods, which is essential for long-form video production like movies. We propose MovieDreamer, a novel hierarchical framework that integrates the strengths of autoregressive models with diffusion-based rendering to pioneer long-duration video generation with intricate plot progressions and high visual fidelity. Our approach utilizes autoregressive models for global narrative coherence, predicting sequences of visual tokens that are subsequently transformed into high-quality video frames through diffusion rendering. This method is akin to traditional movie production processes, where complex stories are factorized down into manageable scene capturing. Further, we employ a multimodal script that enriches scene descriptions with detailed character information and visual style, enhancing continuity and character identity across scenes. We present extensive experiments across various movie genres, demonstrating that our approach not only achieves superior visual and narrative quality but also effectively extends the duration of generated content significantly beyond current capabilities. Homepage: https://aim-uofa.github.io/MovieDreamer/.

cs.CV↗

arXiv2025

Stellar Parameters of BOSS M dwarfs in SDSS-V DR19

We utilized the Stellar LAbel Machine (SLAM), a data-driven model based on Support Vector Regression, to derive stellar parameters ([Fe/H], $T_{\rm eff}$, and $\log{g}$) for SDSS-V M dwarfs using low-resolution optical spectra (R$\sim$2000) obtained with the BOSS spectrographs. These parameters are calibrated using LAMOST F, G or K dwarf companions ([Fe/H]), and APOGEE Net ($T_{\rm eff}$ and $\log{g}$), respectively. Comparisons of SLAM predicted [Fe/H] values between two components of M+M dwarfs wide binaries show no bias but with a scatter of 0.11 dex. Further comparisons with two other works, which also calibrated the [Fe/H] of M dwarfs by using the F/G/K companions, reveal biases of -0.06$\pm$0.16 dex and 0.02$\pm$0.14 dex, respectively. The SLAM-derived effective temperatures agree well with the temperature which is calibrated by using interferometric angular diameters (bias: -27$\pm$92 K) and those of the LAMOST (bias: -34$\pm$65 K), but are systematically lower than those from an empirical relationship between the color index and $T_{\rm eff}$ by 146$\pm$45 K. The SLAM surface gravity aligns well with those of LAMOST (bias: -0.01$\pm$0.07 dex) and those derived from the stellar mass and radius (bias: -0.04$\pm$0.09 dex). Finally, we investigated a bias in [Fe/H] between SLAM and APOGEE ASPCAP. It depends on ASPCAP's [Fe/H] and $T_{\rm eff}$, we provide an equation to correct the ASPCAP metallicities.

astro-ph.SR↗

arXiv2025

Debiasing hazard-based, time-varying vaccine effects using vaccine-irrelevant infections: An observational extension of a pivotal Phase 3 COVID-19 vaccine efficacy trial

Understanding how vaccine effectiveness (VE) changes over time can provide evidence-based guidance for public health decision making. While commonly reported by practitioners, time-varying VE estimates obtained using Cox regression are vul- nerable to hidden biases. To address these limitations, we describe how to leverage vaccine-irrelevant infections to identify hazard-based, time-varying VE in the pres- ence of unmeasured confounding and selection bias. We articulate assumptions under which our approach identifies a causal effect of an intervention deferring vaccination and interaction with the community in which infections circulate. We develop sieve and efficient influence curve-based estimators and discuss imposing monotone shape constraints and estimating VE against multiple variants. As a case study, we examine the observational booster phase of the Coronavirus Vaccine Efficacy (COVE) trial of the Moderna mRNA-1273 COVID-19 vaccine which used symptom-triggered multi- plex PCR testing to identify acute respiratory illnesses (ARIs) caused by SARS-CoV-2 and 20 off-target pathogens previously identified as compelling negative controls for COVID-19. Accounting for vaccine-irrelevant ARIs supported that the mRNA-1273 booster was more effective and durable against Omicron COVID-19 than suggested by Cox regression. Our work offers an approach to mitigate bias in hazard-based, time- varying treatment effects in randomized and non-randomized studies using negative controls.

stat.ME↗

arXiv2025

CareCom: Generative Image Composition with Calibrated Reference Features

Image composition aims to seamlessly insert foreground object into background. Despite the huge progress in generative image composition, the existing methods are still struggling with simultaneous detail preservation and foreground pose/view adjustment. To address this issue, we extend the existing generative composition model to multi-reference version, which allows using arbitrary number of foreground reference images. Furthermore, we propose to calibrate the global and local features of foreground reference images to make them compatible with the background information. The calibrated reference features can supplement the original reference features with useful global and local information of proper pose/view. Extensive experiments on MVImgNet and MureCom demonstrate that the generative model can greatly benefit from the calibrated reference features.

cs.CV↗

arXiv2025

Agentar-DeepFinance-100K: A Large-Scale Financial Dataset via Systematic Chain-of-Thought Synthesis Optimization

Recent advancements in large language models (LLMs) have demonstrated remarkable general reasoning capabilities, holding significant potential for applications in the financial domain, a field that requires robust and reliable reasoning. It has been demonstrated that distilling high-quality chain-of-thought (CoT) rationales from advanced general reasoning models offers a promising and efficient path to the financial reasoning model. However, existing CoT synthesis methods suffer from shallow CoT sampling, leaving the question of how to construct a well-designed knowledge space for finance reasoning unexplored. In this paper, we present Agentar-DeepFinance-100K, a large-scale financial reasoning dataset characterized by its systematic CoT synthesis optimization. We first introduce a comprehensive CoT synthesis pipeline featuring Multi-perspective Knowledge Extraction (MKE) and Self-Corrective Rewriting (SCR) to generate exhaustive and deep financial reasoning trajectories. Furthermore, a systematic investigation, termed CoT Cube, is conducted to analyze critical factors that influence CoT effectiveness, such as necessity, length and synthesizer, yielding valuable insights for high-quality financial CoT construction. Experiments demonstrate that models trained on our Agentar-DeepFinance-100K achieve significant improvements on financial benchmarks. We publicly release Agentar-DeepFinance-100K , hoping to advance the research in financial reasoning models.

cs.CE↗

arXiv2025

High-Fidelity Controlled-Phase Gate for Binomial Codes via Geometric Phase Engineering

High-fidelity two-logical-qubit gates are essential for realizing fault-tolerant quantum computation with bosonic codes, yet experimentally reported fidelities have rarely exceeded 90\%. Here, we propose a geometric phase engineering approach for implementing controlled-phase gates for binomially encoded logical qubits. This method leverages the structural simplicity of geometric drives to reduce the numerical optimization dimensionality while fully incorporating system nonlinearities, enabling fast and high-fidelity logical operations. As an example, we experimentally demonstrate a process fidelity of 97.4$\pm$0.8\% for a controlled-Z gate between two binomial codes, surpassing all previously reported two-logical-qubit gates in bosonic codes. This work demonstrates that geometric phase engineering provides an effective and experimentally feasible route to fast, high-fidelity logical operations in bosonic quantum processors.

quant-ph↗

arXiv2025

The Initial mass function of field stars with mass $\leq$ 1 $M_{\odot}$ varies with metallicity

We investigated a volume-limited sample of LAMOST main-sequence stars with masses from 0.25 to 1 $M_{\odot}$ and distances of 150-350 pc to explore how the stellar initial mass function (IMF) varies with metallicity. We corrected the spectroscopic selection function by comparing the stellar number densities with the photometric ones at the same colour and magnitude. From these corrected number density distributions, we derived IMFs for each metallicity sub-samples. Fitting a broken power-law function in each IMF with a fixed break point at 0.525 $M_{\odot}$, we found the power-law indices increase with [Fe/H] for both mass regimes: $α_1$ (mass $\leq$ 0.525 $M_{\odot}$) rises from 0.54 $\pm$ 0.21 to 1.40 $\pm$ 0.07 and $α_2$ (mass>0.525 $M_{\odot}$) grows from 1.40 $\pm$ 0.16 to 1.86 $\pm$ 0.04 as [Fe/H] varies from -1 to +0.5 dex. It demonstrates that low-mass stars make up a larger fraction in metal-rich environments than in metal-poor ones. We performed simulations to assess the impact of unresolved binaries on the IMF power-law indices. After correction, the binary-adjusted $α$ values retained a similar metallicity-dependent trend. Furthermore, by examining the IMF of the aggregate sample, we found the corrected indices ($α_{\rm{1,corr}} = 1.48 \pm 0.03$ , $α_{\rm{2,corr}} = 2.17 \pm 0.03$) are consistent with Kroupa's IMF values ($α_1 = 1.3 \pm 0.5$ and $α_2 = 2.3 \pm 0.3$). Finally, we verified the robustness of our results by testing different break points and mass bin sizes, confirming that the IMF's dependence on [Fe/H] remains consistent.

astro-ph.SR↗

arXiv2025

Compact and high-resolution spectrometer via Brillouin integrated circuits

Optical spectrometers are indispensable tools across various fields, from chemical and biological sensing to astronomical observations and quantum technologies. However, the integration of spectrometers onto photonic chips has been hindered by the low spectral resolution or large device footprint with complex multiple channel operations. Here, we introduce a novel chip-integrated spectrometer by leveraging the acoustically-stimulated Brillouin scattering in a hybrid photonic-phononic chip. The Brillouin interaction provides a dynamic reflection grating with a high reflectivity up to 50% and a fast switching time on the microsecond scale, achieving an unprecedented spectral resolution of 0.56 nm over a 110 nm bandwidth using just a single 1 mm-long straight waveguide. This remarkable performance approaches the fundamental limit of resolution for a given device size, validating the potential of the hybrid photonic-phononic device for efficient and dynamically-reconfigurable spectral analysis, and thus opens up new avenues for advanced optical signal processing and sensing applications.

physics.optics↗

arXiv2025

UniSplat: Unified Spatio-Temporal Fusion via 3D Latent Scaffolds for Dynamic Driving Scene Reconstruction

Feed-forward 3D reconstruction for autonomous driving has advanced rapidly, yet existing methods struggle with the joint challenges of sparse, non-overlapping camera views and complex scene dynamics. We present UniSplat, a general feed-forward framework that learns robust dynamic scene reconstruction through unified latent spatio-temporal fusion. UniSplat constructs a 3D latent scaffold, a structured representation that captures geometric and semantic scene context by leveraging pretrained foundation models. To effectively integrate information across spatial views and temporal frames, we introduce an efficient fusion mechanism that operates directly within the 3D scaffold, enabling consistent spatio-temporal alignment. To ensure complete and detailed reconstructions, we design a dual-branch decoder that generates dynamic-aware Gaussians from the fused scaffold by combining point-anchored refinement with voxel-based generation, and maintain a persistent memory of static Gaussians to enable streaming scene completion beyond current camera coverage. Extensive experiments on real-world datasets demonstrate that UniSplat achieves state-of-the-art performance in novel view synthesis, while providing robust and high-quality renderings even for viewpoints outside the original camera coverage.

cs.CV↗

arXiv2025

Diffusion-Based Image Editing: An Unforeseen Adversary to Robust Invisible Watermarks

Robust invisible watermarking aims to embed hidden messages into images such that they survive various manipulations while remaining imperceptible. However, powerful diffusion-based image generation and editing models now enable realistic content-preserving transformations that can inadvertently remove or distort embedded watermarks. In this paper, we present a theoretical and empirical analysis demonstrating that diffusion-based image editing can effectively break state-of-the-art robust watermarks designed to withstand conventional distortions. We analyze how the iterative noising and denoising process of diffusion models degrades embedded watermark signals, and provide formal proofs that under certain conditions a diffusion model's regenerated image retains virtually no detectable watermark information. Building on this insight, we propose a diffusion-driven attack that uses generative image regeneration to erase watermarks from a given image. Furthermore, we introduce an enhanced \emph{guided diffusion} attack that explicitly targets the watermark during generation by integrating the watermark decoder into the sampling loop. We evaluate our approaches on multiple recent deep learning watermarking schemes (e.g., StegaStamp, TrustMark, and VINE) and demonstrate that diffusion-based editing can reduce watermark decoding accuracy to near-zero levels while preserving high visual fidelity of the images. Our findings reveal a fundamental vulnerability in current robust watermarking techniques against generative model-based edits, underscoring the need for new watermarking strategies in the era of generative AI.

cs.CR↗

arXiv2025

Characterization of SiPMs at 40 K for neutrino coherent detection based on pure CsI

Silicon photomultiplier (SiPM), as the core photoelectric sensor for coherent neutrino detection in low-temperature pure CsI, its working performance directly determines the measurement accuracy of the scintillator light yield. Our previous research has fully demonstrated the performance of pure CsI at liquid nitrogen temperature. More intriguingly, its performance is expected to be even better at 40 K. However, the performance characteristics of SiPM in the 40 K temperature range still remain to be explored. In this study, a self-developed adjustable temperature control system ranging from 30 K to 293 K was built to investigate the key performance parameters of SiPM at different temperatures, such as single photoelectron spectrum, gain, breakdown voltage, dark count rate, after-pulse, internal crosstalk, and single photoelectron resolution. Special emphasis was placed on examining the key performance parameters of SiPM in the 40 K temperature range to evaluate its feasibility for light yield measurement in this temperature range. The results show that this study obtained the parameter variation trends and optimal working conditions of 3 types of SiPM at different temperatures, thereby improving the sensitivity of the detector. This research provides important technical support for low-temperature detection in neutrino physics experiments.

physics.ins-det↗

arXiv2025

Online AUC Optimization Based on Second-order Surrogate Loss

The Area Under the Curve (AUC) is an important performance metric for classification tasks, particularly in class-imbalanced scenarios. However, minimizing the AUC presents significant challenges due to the non-convex and discontinuous nature of pairwise 0/1 losses, which are difficult to optimize, as well as the substantial memory cost of instance-wise storage, which creates bottlenecks in large-scale applications. To overcome these challenges, we propose a novel second-order surrogate loss based on the pairwise hinge loss, and develop an efficient online algorithm. Unlike conventional approaches that approximate each individual pairwise 0/1 loss term with an instance-wise surrogate function, our approach introduces a new paradigm that directly substitutes the entire aggregated pairwise loss with a surrogate loss function constructed from the first- and second-order statistics of the training data. Theoretically, while existing online AUC optimization algorithms typically achieve an $\mathcal{O}(\sqrt{T})$ regret bound, our method attains a tighter $\mathcal{O}(\ln T)$ bound. Furthermore, we extend the proposed framework to nonlinear settings through a kernel-based formulation. Extensive experiments on multiple benchmark datasets demonstrate the superior efficiency and effectiveness of the proposed second-order surrogate loss in optimizing online AUC performance.

cs.LG↗

arXiv2025

TempFlow-GRPO: When Timing Matters for GRPO in Flow Models

Recent flow matching models for text-to-image generation have achieved remarkable quality, yet their integration with reinforcement learning for human preference alignment remains suboptimal, hindering fine-grained reward-based optimization. We observe that the key impediment to effective GRPO training of flow models is the temporal uniformity assumption in existing approaches: sparse terminal rewards with uniform credit assignment fail to capture the varying criticality of decisions across generation timesteps, resulting in inefficient exploration and suboptimal convergence. To remedy this shortcoming, we introduce \textbf{TempFlow-GRPO} (Temporal Flow GRPO), a principled GRPO framework that captures and exploits the temporal structure inherent in flow-based generation. TempFlow-GRPO introduces three key innovations: (i) a trajectory branching mechanism that provides process rewards by concentrating stochasticity at designated branching points, enabling precise credit assignment without requiring specialized intermediate reward models; (ii) a noise-aware weighting scheme that modulates policy optimization according to the intrinsic exploration potential of each timestep, prioritizing learning during high-impact early stages while ensuring stable refinement in later phases; and (iii) a seed group strategy that controls for initialization effects to isolate exploration contributions. These innovations endow the model with temporally-aware optimization that respects the underlying generative dynamics, leading to state-of-the-art performance in human preference alignment and text-to-image benchmarks.

cs.CV↗

arXiv2025

Breaking the Compression Ceiling: Data-Free Pipeline for Ultra-Efficient Delta Compression

With the rise of the fine-tuned-pretrained paradigm, storing numerous fine-tuned models for multi-tasking creates significant storage overhead. Delta compression alleviates this by storing only the pretrained model and the highly compressed delta weights (the differences between fine-tuned and pretrained model weights). However, existing methods fail to maintain both high compression and performance, and often rely on data. To address these challenges, we propose UltraDelta, the first data-free delta compression pipeline that achieves both ultra-high compression and strong performance. UltraDelta is designed to minimize redundancy, maximize information, and stabilize performance across inter-layer, intra-layer, and global dimensions, using three key components: (1) Variance-Based Mixed Sparsity Allocation assigns sparsity based on variance, giving lower sparsity to high-variance layers to preserve inter-layer information. (2) Distribution-Aware Compression applies uniform quantization and then groups parameters by value, followed by group-wise pruning, to better preserve intra-layer distribution. (3) Trace-Norm-Guided Rescaling uses the trace norm of delta weights to estimate a global rescaling factor, improving model stability under higher compression. Extensive experiments across (a) large language models (fine-tuned on LLaMA-2 7B and 13B) with up to 50x compression, (b) general NLP models (RoBERTa-base, T5-base) with up to 224x compression, (c) vision models (ViT-B/32, ViT-L/14) with up to 132x compression, and (d) multi-modal models (BEiT-3) with 18x compression, demonstrate that UltraDelta consistently outperforms existing methods, especially under ultra-high compression. Code is available at https://github.com/xiaohuiwang000/UltraDelta.

cs.LG↗