arXiv subjects

Shuran Ma

Publications and source records attributed to Shuran Ma.

8 recordsLinked to original sources

arXiv2026

FIRM-Video: Check Before You Score for Reliable Text-to-Video Reward Modeling

Reliable reward models are essential for text-to-video evaluation and alignment. However, the trade-off between evaluation accuracy and inference efficiency places high demands on the quality of training supervision. Existing approaches often rely on holistic judges with fixed rubrics or open-ended reasoning, leading to incomplete inspection, unfaithful justification, and entangled attribution. We introduce FIRM-Video, a unified checklist-driven data construction framework based on a check-before-score principle: construct dimension-specific checklists, verify each criterion against temporal visual evidence, and aggregate only verified decisions. For Instruction Following, FIRM-Video decomposes prompts into weighted atomic requirements; for World Coherence, it constructs prompt-calibrated, target-specific checks grounded in visible entities and actions; and for Perceptual Quality, it applies a generic taxonomy of visual defects. The verified criteria and scores are further transformed into natural-language analyses for end-to-end reward modeling. Subsequently, we construct FIRM-Video-90K with 88,044 dimension-specific instances from 29,348 videos, and introduce FIRM-Video-Bench with 750 point-wise human annotations across 250 videos. The Qwen3-VL-based FIRM-Video-8B achieves the best overall MAE on FIRM-Video-Bench while consistently delivering the highest VBench Total, Quality, and Semantic Scores in Best-of-8 sampling across three video generators.

cs.CV↗

arXiv2026

Pressure-Driven Activation of Semi-core p-Orbitals in Rb and Cs via Crystal-Field Splitting

High-pressure unconventional oxidation states are attributed to exceptional charge transfer, which is itself induced by the differential pressure response of atomic orbital energy levels. The high oxidation states observed in heavy alkali metals (Cs, Ba, Ra) exemplify this behavior, as their semi-core p-states surpass the valence orbital levels of oxidants, e.g., the 2p-orbital of F, at high pressure. However, semi-core p-electron activation in lighter alkali metals, such as Rb, is hindered because the relative orbitals lie at intrinsically lower energies due to their smaller radii, making pressure-induced upshift challenging. We demonstrate that crystal-field splitting of alkali-metal semi-core p-orbitals selectively elevates a portion of these states, substantially lowering the pressure threshold for their chemical activation. Here, our computations reveal that the semi-core 4p-electrons of Rb form weak metallic bonds with F in $P2_1/c$-RbBF5 at around 250 GPa, a pressure accessible in modern high-pressure experiments. Extending to Cs-B-F systems, the crystal-field splitting drives 5p participation in Cs-F bond formation in CsBF5. These findings unveil a new paradigm for semi-core or inner-shell chemistry, providing a unifying framework for semi-core electron activation and bonding. Crucially, they establish that semi-core electrons of light main-group elements, including Rb, are accessible at experimentally feasible pressures.

cond-mat.mtrl-sci↗

arXiv2026

RISE-Video: Can Video Generators Decode Implicit World Rules?

While generative video models have achieved remarkable visual fidelity, their capacity to internalize and reason over implicit world rules remains a critical yet under-explored frontier. To bridge this gap, we present RISE-Video, a pioneering reasoning-oriented benchmark for Text-Image-to-Video (TI2V) synthesis that shifts the evaluative focus from surface-level aesthetics to deep cognitive reasoning. RISE-Video comprises 467 meticulously human-annotated samples spanning eight rigorous categories, providing a structured testbed for probing model intelligence across diverse dimensions, ranging from commonsense and spatial dynamics to specialized subject domains. Our framework introduces a multi-dimensional evaluation protocol consisting of four metrics: \textit{Reasoning Alignment}, \textit{Temporal Consistency}, \textit{Physical Rationality}, and \textit{Visual Quality}. To further support scalable evaluation, we propose an automated pipeline leveraging Large Multimodal Models (LMMs) to emulate human-centric assessment. Extensive experiments on 11 state-of-the-art TI2V models reveal pervasive deficiencies in simulating complex scenarios under implicit constraints, offering critical insights for the advancement of future world-simulating generative models.

cs.CV↗

arXiv2025

Non-local Chemistry Driven by Cation-Anion Size Disparity in Helium Inserted Compounds under High Pressure

Opposing the theory that Helium (He) cannot be inserted into AB-type ionic compounds due to the Madelung energy increase, our crystal structure search and first-principles calculations found that He can form stable compounds with sodium halides (NaX, X=Cl, Br, I) under high-pressure. These reactions are driven by the non-local chemistry arising from the cation-anion size disparity, distinctly different from the He insertion reaction with A2B-type compounds. The large size differences between Na+ and X- enable structures that can effectively host He insertions through volume and inter-atomic distance disproportionation. Furthermore, the insertion of He atoms can significantly relieve the elevated Madelung energy that builds up in NaX under high pressure. This energy increase arises from structural transitions driven by cation-anion size disparity, which are necessary for reducing volume under pressure. The insertion of He allows the reduction of the total volume under high pressure without increasing the Madelung energy. Our predicted compounds and stability analysis reveal a new example of He reactivity governed not by local chemical bond formation, but by long-range electrostatic interactions.

cond-mat.mtrl-sci↗

arXiv2025

Co-Training Vision Language Models for Remote Sensing Multi-task Learning

With Transformers achieving outstanding performance on individual remote sensing (RS) tasks, we are now approaching the realization of a unified model that excels across multiple tasks through multi-task learning (MTL). Compared to single-task approaches, MTL methods offer improved generalization, enhanced scalability, and greater practical applicability. Recently, vision language models (VLMs) have achieved promising results in RS image understanding, grounding, and ultra-high-resolution (UHR) image reasoning, respectively. Moreover, the unified text-based interface demonstrates significant potential for MTL. Hence, in this work, we present RSCoVLM, a simple yet flexible VLM baseline for RS MTL. Firstly, we create the data curation engine, including data acquisition, offline processing and integrating, as well as online loading and weighting. This data engine effectively addresses complex RS data enviroment and generates flexible vision-language conversations. Furthermore, we propose a unified dynamic-resolution strategy to address the diverse image scales inherent in RS imagery. For UHR images, we introduce the Zoom-in Chain mechanism together with its corresponding dataset, LRS-VQA-Zoom. The strategies are flexible and effectively mitigate the computational burdens. Additionally, we significantly enhance the model's object detection capability and propose a novel evaluation protocol that ensures fair comparison between VLMs and conventional detection models. Extensive experiments demonstrate that RSCoVLM achieves state-of-the-art performance across diverse tasks, outperforming existing RS VLMs and even rivaling specialized expert models. All the training and evaluating tools, model weights, and datasets have been fully open-sourced to support reproducibility. We expect that this baseline will promote further progress toward general-purpose RS models.

cs.CV↗

arXiv2025

Object Fidelity Diffusion for Remote Sensing Image Generation

High-precision controllable remote sensing image generation is both meaningful and challenging. Existing diffusion models often produce low-fidelity images due to their inability to adequately capture morphological details, which may affect the robustness and reliability of object detection models. To enhance the accuracy and fidelity of generated objects in remote sensing, this paper proposes Object Fidelity Diffusion (OF-Diff), which effectively improves the fidelity of generated objects. Specifically, we are the first to extract the prior shapes of objects based on the layout for diffusion models in remote sensing. Then, we introduce a dual-branch diffusion model with diffusion consistency loss, which can generate high-fidelity remote sensing images without providing real images during the sampling phase. Furthermore, we introduce DDPO to fine-tune the diffusion process, making the generated remote sensing images more diverse and semantically consistent. Comprehensive experiments demonstrate that OF-Diff outperforms state-of-the-art methods in the remote sensing across key quality metrics. Notably, the performance of several polymorphic and small object classes shows significant improvement. For instance, the mAP increases by 8.3%, 7.7%, and 4.0% for airplanes, ships, and vehicles, respectively.

cs.CV↗

arXiv2024

FedFQ: Federated Learning with Fine-Grained Quantization

Federated learning (FL) is a decentralized approach, enabling multiple participants to collaboratively train a model while ensuring the protection of data privacy. The transmission of updates from numerous edge clusters to the server creates a significant communication bottleneck in FL. Quantization is an effective compression technology, showcasing immense potential in addressing this bottleneck problem. The Non-IID nature of FL renders it sensitive to quantization. Existing quantized FL frameworks inadequately balance high compression ratios and superior convergence performance by roughly employing a uniform quantization bit-width on the client-side. In this work, we propose a communication-efficient FL algorithm with a fine-grained adaptive quantization strategy (FedFQ). FedFQ addresses the trade-off between achieving high communication compression ratios and maintaining superior convergence performance by introducing parameter-level quantization. Specifically, we have designed a Constraint-Guided Simulated Annealing algorithm to determine specific quantization schemes. We derive the convergence of FedFQ, demonstrating its superior convergence performance compared to existing quantized FL algorithms. We conducted extensive experiments on multiple benchmarks and demonstrated that, while maintaining lossless performance, FedFQ achieves a compression ratio of 27 times to 63 times compared to the baseline experiment.

cs.DC↗

arXiv2024

Reducing Spurious Correlation for Federated Domain Generalization

The rapid development of multimedia has provided a large amount of data with different distributions for visual tasks, forming different domains. Federated Learning (FL) can efficiently use this diverse data distributed on different client media in a decentralized manner through model sharing. However, in open-world scenarios, there is a challenge: global models may struggle to predict well on entirely new domain data captured by certain media, which were not encountered during training. Existing methods still rely on strong statistical correlations between samples and labels to address this issue, which can be misleading, as some features may establish spurious short-cut correlations with the predictions. To comprehensively address this challenge, we introduce FedCD (Cross-Domain Invariant Federated Learning), an overall optimization framework at both the local and global levels. We introduce the Spurious Correlation Intervener (SCI), which employs invariance theory to locally generate interventers for features in a self-supervised manner to reduce the model's susceptibility to spurious correlated features. Our approach requires no sharing of data or features, only the gradients related to the model. Additionally, we develop the simple yet effective Risk Extrapolation Aggregation strategy (REA), determining aggregation coefficients through mathematical optimization to facilitate global causal invariant predictions. Extensive experiments and ablation studies highlight the effectiveness of our approach. In both classification and object detection generalization tasks, our method outperforms the baselines by an average of at least 1.45% in Acc, 4.8% and 1.27% in mAP50.

cs.CV↗