arXiv subjects

Bowen Zhang

Publications and source records attributed to Bowen Zhang.

At least 109 records · Page 6Linked to original sources

arXiv2025

The Mini-SiTian Array: Imaging Processing Pipeline

As a pathfinder of the SiTian project, the Mini-SiTian (MST) array, employed three commercial CMOS cameras, represents a next-generation, cost-effective optical time-domain survey project. This paper focuses primarily on the precise data processing pipeline designed for wide-field, CMOS-based devices, including the removal of instrumental effects, astrometry, photometry, and flux calibration. When applying this pipeline to approximately 3000 observations taken in the Field 02 (f02) region by MST, the results demonstrate a remarkable astrometric precision of approximately 70--80\,mas (about 0.1\,pixel), an impressive calibration accuracy of approximately 1\,mmag in the MST zero points, and a photometric accuracy of about 4\,mmag for bright stars. Our studies demonstrate that MST CMOS can achieve photometric accuracy comparable to that of CCDs, highlighting the feasibility of large-scale CMOS-based optical time-domain surveys and their potential applications for cost optimization in future large-scale time-domain surveys, like the SiTian project.

astro-ph.IM↗

arXiv2025

DiT-Air: Revisiting the Efficiency of Diffusion Model Architecture Design in Text to Image Generation

In this work, we empirically study Diffusion Transformers (DiTs) for text-to-image generation, focusing on architectural choices, text-conditioning strategies, and training protocols. We evaluate a range of DiT-based architectures--including PixArt-style and MMDiT variants--and compare them with a standard DiT variant which directly processes concatenated text and noise inputs. Surprisingly, our findings reveal that the performance of standard DiT is comparable with those specialized models, while demonstrating superior parameter-efficiency, especially when scaled up. Leveraging the layer-wise parameter sharing strategy, we achieve a further reduction of 66% in model size compared to an MMDiT architecture, with minimal performance impact. Building on an in-depth analysis of critical components such as text encoders and Variational Auto-Encoders (VAEs), we introduce DiT-Air and DiT-Air-Lite. With supervised and reward fine-tuning, DiT-Air achieves state-of-the-art performance on GenEval and T2I CompBench, while DiT-Air-Lite remains highly competitive, surpassing most existing models despite its compact size.

cs.CV↗

arXiv2025

PBR3DGen: A VLM-guided Mesh Generation with High-quality PBR Texture

Generating high-quality physically based rendering (PBR) materials is important to achieve realistic rendering in the downstream tasks, yet it remains challenging due to the intertwined effects of materials and lighting. While existing methods have made breakthroughs by incorporating material decomposition in the 3D generation pipeline, they tend to bake highlights into albedo and ignore spatially varying properties of metallicity and roughness. In this work, we present PBR3DGen, a two-stage mesh generation method with high-quality PBR materials that integrates the novel multi-view PBR material estimation model and a 3D PBR mesh reconstruction model. Specifically, PBR3DGen leverages vision language models (VLM) to guide multi-view diffusion, precisely capturing the spatial distribution and inherent attributes of reflective-metalness material. Additionally, we incorporate view-dependent illumination-aware conditions as pixel-aware priors to enhance spatially varying material properties. Furthermore, our reconstruction model reconstructs high-quality mesh with PBR materials. Experimental results demonstrate that PBR3DGen significantly outperforms existing methods, achieving new state-of-the-art results for PBR estimation and mesh generation. More results and visualization can be found on our project page: https://pbr3dgen1218.github.io/.

cs.CV↗

arXiv2025

EC-DIT: Scaling Diffusion Transformers with Adaptive Expert-Choice Routing

Diffusion transformers have been widely adopted for text-to-image synthesis. While scaling these models up to billions of parameters shows promise, the effectiveness of scaling beyond current sizes remains underexplored and challenging. By explicitly exploiting the computational heterogeneity of image generations, we develop a new family of Mixture-of-Experts (MoE) models (EC-DIT) for diffusion transformers with expert-choice routing. EC-DIT learns to adaptively optimize the compute allocated to understand the input texts and generate the respective image patches, enabling heterogeneous computation aligned with varying text-image complexities. This heterogeneity provides an efficient way of scaling EC-DIT up to 97 billion parameters and achieving significant improvements in training convergence, text-to-image alignment, and overall generation quality over dense models and conventional MoE models. Through extensive ablations, we show that EC-DIT demonstrates superior scalability and adaptive compute allocation by recognizing varying textual importance through end-to-end training. Notably, in text-to-image alignment evaluation, our largest models achieve a state-of-the-art GenEval score of 71.68% and still maintain competitive inference speed with intuitive interpretability.

cs.CV↗

arXiv2025

Contrastive Localized Language-Image Pre-Training

Contrastive Language-Image Pre-training (CLIP) has been a celebrated method for training vision encoders to generate image/text representations facilitating various applications. Recently, CLIP has been widely adopted as the vision backbone of multimodal large language models (MLLMs) to connect image inputs for language interactions. The success of CLIP as a vision-language foundation model relies on aligning web-crawled noisy text annotations at image levels. Nevertheless, such criteria may become insufficient for downstream tasks in need of fine-grained vision representations, especially when region-level understanding is demanding for MLLMs. In this paper, we improve the localization capability of CLIP with several advances. We propose a pre-training method called Contrastive Localized Language-Image Pre-training (CLOC) by complementing CLIP with region-text contrastive loss and modules. We formulate a new concept, promptable embeddings, of which the encoder produces image embeddings easy to transform into region representations given spatial hints. To support large-scale pre-training, we design a visually-enriched and spatially-localized captioning framework to effectively generate region-text pseudo-labels at scale. By scaling up to billions of annotated images, CLOC enables high-quality regional embeddings for image region recognition and retrieval tasks, and can be a drop-in replacement of CLIP to enhance MLLMs, especially on referring and grounding tasks.

cs.CV↗

arXiv2025

High Quality Single Crystal of Kitaev Spin Liquid Candidate Material RuBr3 Synthesized under High Pressure

Kitaev quantum spin liquids have attracted significant attention in condensed matter physics over the past decade. To understand their emergent quantum phenomena, high-quality single crystals of substantial size are essential. Here, we report the synthesis of single crystals of the Kitaev quantum spin liquid candidate RuBr3, achieving millimeter-sized crystals through a self-flux method under high pressure and high temperature conditions. The crystals exhibit well-defined cleavage planes with a lustrous appearance. Transport characterizations exhibit a narrow band-gap semiconducting behavior with 0.13 eV and 0.11 eV band-gap in ab plane and along c axis, respectively. Magnetic measurement shows a transition to antiferromagnetic (AFM) state at approximately 29 K both in ab plane and along c axis. Notably, the Néel temperature increases to 34 K with an applied magnetic field of up to 7 T in the ab plane, but without any change along c axis. The large size and high quality of RuBr3 single crystals provide a valuable platform for investigating various interactions, particularly the Kitaev interaction, and for elucidating the intrinsic physical properties of Kitaev quantum spin liquids.

cond-mat.str-el↗

arXiv2025

Object kinetic Monte Carlo simulations on the difference between fission neutron and heavy ion irradiation induced void evolution in Fe-Cr alloys

Experimental results show significant difference between neutrons and ions irradiation of alloys, while the underlying reasons remain unclear. Herein, we performed object kinetic Monte Carlo (OKMC) simulations on void evolution in Fe-Cr alloys under neutron and ion irradiations, focusing on the effects of dose rate, irradiation particle type and temperature. Binary Collision Approximation and Molecular Dynamics are applied to obtain the cascade morphology of ion irradiation in order to study the effect of spatial correlation of cascades along the ion track, which is considered as a significant difference between the neutron and ion irradiations. Systematic OKMC simulations were performed at a wide range of dose rate from $10^{-7}$ to $10^{-3}$ dpa/s and temperature from 300 to 500$^\circ C$. Simulation results show that both a higher dose rate and a lower temperature can lead to a higher density and a smaller average size of voids. High dose rate greatly promotes the interaction frequency between small defects and inhibit the absorption of vacancies by one vacancy cluster, thus enhancing the nucleation of vacancy clusters. This dose rate effect explains the major difference of microstructure between fission neutron and heavy ion irradiation. High temperature enhances the migration of small defects and the absorption of vacancies by vacancy clusters, and thus enlarge the vacancy clusters. The impact of irradiation particle types that has influence on the primary knock-on atom spectrum and cascade morphology is less important to void evolution compared with dose rate and irradiation temperature. This work provides fundamental insights into the difference in void evolution between fission neutron and heavy ion irradiations that are important to the application of ion irradiations in study irradiation effects of nuclear materials.

physics.app-ph↗

arXiv2025

Hunyuan3D 1.0: A Unified Framework for Text-to-3D and Image-to-3D Generation

While 3D generative models have greatly improved artists' workflows, the existing diffusion models for 3D generation suffer from slow generation and poor generalization. To address this issue, we propose a two-stage approach named Hunyuan3D 1.0 including a lite version and a standard version, that both support text- and image-conditioned generation. In the first stage, we employ a multi-view diffusion model that efficiently generates multi-view RGB in approximately 4 seconds. These multi-view images capture rich details of the 3D asset from different viewpoints, relaxing the tasks from single-view to multi-view reconstruction. In the second stage, we introduce a feed-forward reconstruction model that rapidly and faithfully reconstructs the 3D asset given the generated multi-view images in approximately 7 seconds. The reconstruction network learns to handle noises and in-consistency introduced by the multi-view diffusion and leverages the available information from the condition image to efficiently recover the 3D structure. Our framework involves the text-to-image model, i.e., Hunyuan-DiT, making it a unified framework to support both text- and image-conditioned 3D generation. Our standard version has 3x more parameters than our lite and other existing model. Our Hunyuan3D 1.0 achieves an impressive balance between speed and quality, significantly reducing generation time while maintaining the quality and diversity of the produced assets.

cs.CV↗

arXiv2024

Photometric Stellar Parameters for 195,478 Kepler Input Catalog (KIC) Stars

The stellar atmospheric parameters and physical properties of stars in the Kepler Input Catalog (KIC) are of great significance for the study of exoplanets, stellar activity, and asteroseismology. However, despite extensive effort over the past decades, accurate spectroscopic estimates of these parameters are available for only about half of the stars in the full KIC catalog. In our work, by training relationships between photometric colors and spectroscopic stellar parameters from Gaia DR3, the Kepler Issac-Newton Survey, LAMOST DR10, and APOGEE DR17, we have obtained atmospheric-parameter estimates for over 195,000 stars, accounting for 97$\%$ of the total sample of KIC stars. We obtain 1$σ$ uncertainties of 0.1 dex on metallicity [Fe/H], 100 K on effective temperature $T_{\rm eff}$, and 0.2 dex on surface gravity log $g$. In addition, based on these atmospheric parameters, we estimated the ages, masses, radii, and surface gravities of these stars using the commonly adopted isochrone-fitting approach. External comparisons indicate that the resulting precision for turn-off stars is 20$\%$ in age; for dwarf stars, it is 0.07 $M_{\odot}$ in mass, 0.05 $R_{\odot}$ in radius, and 0.12 dex in surface gravity; and for giant stars, it is 0.14 $M_{\odot}$ in mass, 0.73 $R_{\odot}$ in radius, and 0.11 dex in surface gravity.

astro-ph.SR↗

arXiv2024

A Survey of Stance Detection on Social Media: New Directions and Perspectives

In modern digital environments, users frequently express opinions on contentious topics, providing a wealth of information on prevailing attitudes. The systematic analysis of these opinions offers valuable insights for decision-making in various sectors, including marketing and politics. As a result, stance detection has emerged as a crucial subfield within affective computing, enabling the automatic detection of user stances in social media conversations and providing a nuanced understanding of public sentiment on complex issues. Recent years have seen a surge of research interest in developing effective stance detection methods, with contributions from multiple communities, including natural language processing, web science, and social computing. This paper provides a comprehensive survey of stance detection techniques on social media, covering task definitions, datasets, approaches, and future works. We review traditional stance detection models, as well as state-of-the-art methods based on large language models, and discuss their strengths and limitations. Our survey highlights the importance of stance detection in understanding public opinion and sentiment, and identifies gaps in current research. We conclude by outlining potential future directions for stance detection on social media, including the need for more robust and generalizable models, and the importance of addressing emerging challenges such as multi-modal stance detection and stance detection in low-resource languages.

cs.CL↗

arXiv2024

Learning from Different Samples: A Source-free Framework for Semi-supervised Domain Adaptation

Semi-supervised domain adaptation (SSDA) has been widely studied due to its ability to utilize a few labeled target data to improve the generalization ability of the model. However, existing methods only consider designing certain strategies for target samples to adapt, ignoring the exploration of customized learning for different target samples. When the model encounters complex target distribution, existing methods will perform limited due to the inability to clearly and comprehensively learn the knowledge of multiple types of target samples. To fill this gap, this paper focuses on designing a framework to use different strategies for comprehensively mining different target samples. We propose a novel source-free framework (SOUF) to achieve semi-supervised fine-tuning of the source pre-trained model on the target domain. Different from existing SSDA methods, SOUF decouples SSDA from the perspectives of different target samples, specifically designing robust learning techniques for unlabeled, reliably labeled, and noisy pseudo-labeled target samples. For unlabeled target samples, probability-based weighted contrastive learning (PWC) helps the model learn more discriminative feature representations. To mine the latent knowledge of labeled target samples, reliability-based mixup contrastive learning (RMC) learns complex knowledge from the constructed reliable sample set. Finally, predictive regularization learning (PR) further mitigates the misleading effect of noisy pseudo-labeled samples on the model. Extensive experiments on benchmark datasets demonstrate the superiority of our framework over state-of-the-art methods.

cs.CV↗

arXiv2024

CIT: Rethinking Class-incremental Semantic Segmentation with a Class Independent Transformation

Class-incremental semantic segmentation (CSS) requires that a model learn to segment new classes without forgetting how to segment previous ones: this is typically achieved by distilling the current knowledge and incorporating the latest data. However, bypassing iterative distillation by directly transferring outputs of initial classes to the current learning task is not supported in existing class-specific CSS methods. Via Softmax, they enforce dependency between classes and adjust the output distribution at each learning step, resulting in a large probability distribution gap between initial and current tasks. We introduce a simple, yet effective Class Independent Transformation (CIT) that converts the outputs of existing semantic segmentation models into class-independent forms with negligible cost or performance loss. By utilizing class-independent predictions facilitated by CIT, we establish an accumulative distillation framework, ensuring equitable incorporation of all class information. We conduct extensive experiments on various segmentation architectures, including DeepLabV3, Mask2Former, and SegViTv2. Results from these experiments show minimal task forgetting across different datasets, with less than 5% for ADE20K in the most challenging 11 task configurations and less than 1% across all configurations for the PASCAL VOC 2012 dataset.

cs.CV↗

arXiv2024

GaussianCube: A Structured and Explicit Radiance Representation for 3D Generative Modeling

We introduce a radiance representation that is both structured and fully explicit and thus greatly facilitates 3D generative modeling. Existing radiance representations either require an implicit feature decoder, which significantly degrades the modeling power of the representation, or are spatially unstructured, making them difficult to integrate with mainstream 3D diffusion methods. We derive GaussianCube by first using a novel densification-constrained Gaussian fitting algorithm, which yields high-accuracy fitting using a fixed number of free Gaussians, and then rearranging these Gaussians into a predefined voxel grid via Optimal Transport. Since GaussianCube is a structured grid representation, it allows us to use standard 3D U-Net as our backbone in diffusion modeling without elaborate designs. More importantly, the high-accuracy fitting of the Gaussians allows us to achieve a high-quality representation with orders of magnitude fewer parameters than previous structured representations for comparable quality, ranging from one to two orders of magnitude. The compactness of GaussianCube greatly eases the difficulty of 3D generative modeling. Extensive experiments conducted on unconditional and class-conditioned object generation, digital avatar creation, and text-to-3D synthesis all show that our model achieves state-of-the-art generation results both qualitatively and quantitatively, underscoring the potential of GaussianCube as a highly accurate and versatile radiance representation for 3D generative modeling. Project page: https://gaussiancube.github.io/.

cs.CV↗

arXiv2024

Improve Vision Language Model Chain-of-thought Reasoning

Chain-of-thought (CoT) reasoning in vision language models (VLMs) is crucial for improving interpretability and trustworthiness. However, current training recipes lack robust CoT reasoning data, relying on datasets dominated by short annotations with minimal rationales. In this work, we show that training VLM on short answers does not generalize well to reasoning tasks that require more detailed responses. To address this, we propose a two-fold approach. First, we distill rationales from GPT-4o model to enrich the training data and fine-tune VLMs, boosting their CoT performance. Second, we apply reinforcement learning to further calibrate reasoning quality. Specifically, we construct positive (correct) and negative (incorrect) pairs of model-generated reasoning chains, by comparing their predictions with annotated short answers. Using this pairwise data, we apply the Direct Preference Optimization algorithm to refine the model's reasoning abilities. Our experiments demonstrate significant improvements in CoT reasoning on benchmark datasets and better generalization to direct answer prediction as well. This work emphasizes the importance of incorporating detailed rationales in training and leveraging reinforcement learning to strengthen the reasoning capabilities of VLMs.

cs.AI↗

arXiv2024

ReeFRAME: Reeb Graph based Trajectory Analysis Framework to Capture Top-Down and Bottom-Up Patterns of Life

In this paper, we present ReeFRAME, a scalable Reeb graph-based framework designed to analyze vast volumes of GPS-enabled human trajectory data generated at 1Hz frequency. ReeFRAME models Patterns-of-life (PoL) at both the population and individual levels, utilizing Multi-Agent Reeb Graphs (MARGs) for population-level patterns and Temporal Reeb Graphs (TERGs) for individual trajectories. The framework's linear algorithmic complexity relative to the number of time points ensures scalability for anomaly detection. We validate ReeFRAME on six large-scale anomaly detection datasets, simulating real-time patterns with up to 500,000 agents over two months.

cs.LG↗

arXiv2024

Investigating Chain-of-thought with ChatGPT for Stance Detection on Social Media

Stance detection predicts attitudes towards targets in texts and has gained attention with the rise of social media. Traditional approaches include conventional machine learning, early deep neural networks, and pre-trained fine-tuning models. However, with the evolution of very large pre-trained language models (VLPLMs) like ChatGPT (GPT-3.5), traditional methods face deployment challenges. The parameter-free Chain-of-Thought (CoT) approach, not requiring backpropagation training, has emerged as a promising alternative. This paper examines CoT's effectiveness in stance detection tasks, demonstrating its superior accuracy and discussing associated challenges.

cs.CL↗

arXiv2024

Toward Physics-guided Time Series Embedding

In various scientific and engineering fields, the primary research areas have revolved around physics-based dynamical systems modeling and data-driven time series analysis. According to the embedding theory, dynamical systems and time series can be mutually transformed using observation functions and physical reconstruction techniques. Based on this, we propose Embedding Duality Theory, where the parameterized embedding layer essentially provides a linear estimation of the non-linear time series dynamics. This theory enables us to bypass the parameterized embedding layer and directly employ physical reconstruction techniques to acquire a data embedding representation. Utilizing physical priors results in a 10X reduction in parameters, a 3X increase in speed, and maximum performance boosts of 18% in expert, 22% in few-shot, and 53\% in zero-shot tasks without any hyper-parameter tuning. All methods are encapsulated as a plug-and-play module

cs.LG↗

arXiv2024

Weak-eval-Strong: Evaluating and Eliciting Lateral Thinking of LLMs with Situation Puzzles

While advancements in NLP have significantly improved the performance of Large Language Models (LLMs) on tasks requiring vertical thinking, their lateral thinking capabilities remain under-explored and challenging to measure due to the complexity of assessing creative thought processes and the scarcity of relevant data. To address these challenges, we introduce SPLAT, a benchmark leveraging Situation Puzzles to evaluate and elicit LAteral Thinking of LLMs. This benchmark, containing 975 graded situation puzzles across three difficulty levels, employs a new multi-turn player-judge framework instead of the traditional model-based evaluation, which often necessitates a stronger evaluation model. This framework simulates an interactive game where the model (player) asks the evaluation model (judge) questions about an incomplete story to infer the full scenario. The judge answers based on a detailed reference scenario or evaluates if the player's predictions align with the reference one. This approach lessens dependence on more robust evaluation models, enabling the assessment of state-of-the-art LLMs. The experiments demonstrate that a robust evaluation model, such as WizardLM-2, closely matches human judgements in both intermediate question-answering and final scenario accuracy, achieving over 80% agreement-similar to the agreement levels among humans. Furthermore, applying data and reasoning processes from our benchmark to other lateral thinking-related benchmarks, e.g., RiddleSense and BrainTeaser, leads to performance enhancements. This suggests that our benchmark effectively evaluates and elicits the lateral thinking abilities of LLMs. Code is available at: https://github.com/chenqi008/LateralThinking.

cs.CL↗