arXiv subjects

Cong Liu

Publications and source records attributed to Cong Liu.

At least 55 records · Page 3Linked to original sources

arXiv2025

TempoMaster: Efficient Long Video Generation via Next-Frame-Rate Prediction

We present TempoMaster, a novel framework that formulates long video generation as next-frame-rate prediction. Specifically, we first generate a low-frame-rate clip that serves as a coarse blueprint of the entire video sequence, and then progressively increase the frame rate to refine visual details and motion continuity. During generation, TempoMaster employs bidirectional attention within each frame-rate level while performing autoregression across frame rates, thus achieving long-range temporal coherence while enabling efficient and parallel synthesis. Extensive experiments demonstrate that TempoMaster establishes a new state-of-the-art in long video generation, excelling in both visual and temporal quality.

cs.CV↗

arXiv2025

Spark-Prover-X1: Formal Theorem Proving Through Diverse Data Training

Large Language Models (LLMs) have shown significant promise in automated theorem proving, yet progress is often constrained by the scarcity of diverse and high-quality formal language data. To address this issue, we introduce Spark-Prover-X1, a 7B parameter model trained via an three-stage framework designed to unlock the reasoning potential of more accessible and moderately-sized LLMs. The first stage infuses deep knowledge through continuous pre-training on a broad mathematical corpus, enhanced by a suite of novel data tasks. Key innovation is a "CoT-augmented state prediction" task to achieve fine-grained reasoning. The second stage employs Supervised Fine-tuning (SFT) within an expert iteration loop to specialize both the Spark-Prover-X1-7B and Spark-Formalizer-X1-7B models. Finally, a targeted round of Group Relative Policy Optimization (GRPO) is applied to sharpen the prover's capabilities on the most challenging problems. To facilitate robust evaluation, particularly on problems from real-world examinations, we also introduce ExamFormal-Bench, a new benchmark dataset of 402 formal problems. Experimental results demonstrate that Spark-Prover achieves state-of-the-art performance among similarly-sized open-source models within the "Whole-Proof Generation" paradigm. It shows exceptional performance on difficult competition benchmarks, notably solving 27 problems on PutnamBench (pass@32) and achieving 24.0\% on CombiBench (pass@32). Our work validates that this diverse training data and progressively refined training pipeline provides an effective path for enhancing the formal reasoning capabilities of lightweight LLMs. We will release both Spark-Prover-X1-7B and Spark-Formalizer-X1-7B, along with the ExamFormal-Bench dataset, in the near future.

cs.CL↗

arXiv2025

Performance evaluation of compact plastic scintillating fiber modules for muon tomography applications

Muon tomography is a non-destructive imaging technique that exploits cosmic-ray muons from multiple directions. Its performance critically depends on the stability, active-area coverage, and spatial resolution of position-sensitive detectors. In this work, we report on the development of four compact scintillating fiber modules, each 100 cm long and composed of two staggered layers of 1 mm diameter fibers. The fibers are read out at one end by one-dimensional silicon photomultiplier arrays with a 2 mm pitch, coupled to Citiroc 1A-based front-end electronics. The modules were characterized with cosmic-ray muons, yielding a detection efficiency above 97% and a mean spatial resolution of about 0.56 mm, with uniform response over different distances from the readout end. An imaging test of a lead block was also performed, and the reconstructed results are consistent with the blocks profile. These results demonstrate the suitability of this detector design for compact and large-area systems in muon tomography applications.

physics.ins-det↗

arXiv2025

Binary-Gaussian: Compact and Progressive Representation for 3D Gaussian Segmentation

3D Gaussian Splatting (3D-GS) has emerged as an efficient 3D representation and a promising foundation for semantic tasks like segmentation. However, existing 3D-GS-based segmentation methods typically rely on high-dimensional category features, which introduce substantial memory overhead. Moreover, fine-grained segmentation remains challenging due to label space congestion and the lack of stable multi-granularity control mechanisms. To address these limitations, we propose a coarse-to-fine binary encoding scheme for per-Gaussian category representation, which compresses each feature into a single integer via the binary-to-decimal mapping, drastically reducing memory usage. We further design a progressive training strategy that decomposes panoptic segmentation into a series of independent sub-tasks, reducing inter-class conflicts and thereby enhancing fine-grained segmentation capability. Additionally, we fine-tune opacity during segmentation training to address the incompatibility between photometric rendering and semantic segmentation, which often leads to foreground-background confusion. Extensive experiments on multiple benchmarks demonstrate that our method achieves state-of-the-art segmentation performance while significantly reducing memory consumption and accelerating inference.

cs.CV↗

arXiv2025

Order-Disorder in Fe-Si Alloys: Implications for Seismic Anisotropy and Thermal Evolution of Earth's Inner Core

Understanding the structure and dynamics of Earth's inner core is essential for constraining its composition, thermal evolution, and seismic properties. Silicon is a probable major component of Earth's core. Using first-principles molecular dynamics and thermodynamic modeling, we investigate the structural, elastic, and transport properties of Fe-Si alloys at high pressures and temperatures. By computing the Gibbs free energies of B2, hcp, fcc, and bcc solid solutions, we construct the Fe-Si phase diagram applicable to the Earth's inner core. Our results reveal a pronounced miscibility gap between hcp and B2 Fe-Si, with the two phases coexisting over the compositional range of 6-11 wt% Si at 6000 K. The B2 Fe-Si alloy exhibits strong single-crystal shear anisotropy (22.9% at 6000 K) compared to the nearly isotropic hcp phase (0.6%), and yields a shear wave velocity (3.73 km/s) and Poisson's ratio consistent with seismological observations. Moreover, the computed transport properties reveal substantially lower thermal conductivity of B2 Fe-Si relative to pure iron or hcp Fe-Si under inner-core conditions. These results imply that Earth's inner core likely comprises multiple phases, whose distribution and crystallographic texture critically influence its seismic and thermal properties.

cond-mat.mtrl-sci↗

arXiv2025

MSP-MVS: Multi-Granularity Segmentation Prior Guided Multi-View Stereo

Recently, patch deformation-based methods have demonstrated significant strength in multi-view stereo by adaptively expanding the reception field of patches to help reconstruct textureless areas. However, such methods mainly concentrate on searching for pixels without matching ambiguity (i.e., reliable pixels) when constructing deformed patches, while neglecting the deformation instability caused by unexpected edge-skipping, resulting in potential matching distortions. Addressing this, we propose MSP-MVS, a method introducing multi-granularity segmentation prior for edge-confined patch deformation. Specifically, to avoid unexpected edge-skipping, we first aggregate and further refine multi-granularity depth edges gained from Semantic-SAM as prior to guide patch deformation within depth-continuous (i.e., homogeneous) areas. Moreover, to address attention imbalance caused by edge-confined patch deformation, we implement adaptive equidistribution and disassemble-clustering of correlative reliable pixels (i.e., anchors), thereby promoting attention-consistent patch deformation. Finally, to prevent deformed patches from falling into local-minimum matching costs caused by the fixed sampling pattern, we introduce disparity-sampling synergistic 3D optimization to help identify global-minimum matching costs. Evaluations on ETH3D and Tanks & Temples benchmarks prove our method obtains state-of-the-art performance with remarkable generalization.

cs.CV↗

arXiv2025

DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo

Patch deformation-based methods have recently exhibited substantial effectiveness in multi-view stereo, due to the incorporation of deformable and expandable perception to reconstruct textureless areas. However, such approaches typically focus on exploring correlative reliable pixels to alleviate match ambiguity during patch deformation, but ignore the deformation instability caused by mistaken edge-skipping and visibility occlusion, leading to potential estimation deviation. To remedy the above issues, we propose DVP-MVS, which innovatively synergizes depth-edge aligned and cross-view prior for robust and visibility-aware patch deformation. Specifically, to avoid unexpected edge-skipping, we first utilize Depth Anything V2 followed by the Roberts operator to initialize coarse depth and edge maps respectively, both of which are further aligned through an erosion-dilation strategy to generate fine-grained homogeneous boundaries for guiding patch deformation. In addition, we reform view selection weights as visibility maps and restore visible areas by cross-view depth reprojection, then regard them as cross-view prior to facilitate visibility-aware patch deformation. Finally, we improve propagation and refinement with multi-view geometry consistency by introducing aggregated visible hemispherical normals based on view selection and local projection depth differences based on epipolar lines, respectively. Extensive evaluations on ETH3D and Tanks & Temples benchmarks demonstrate that our method can achieve state-of-the-art performance with excellent robustness and generalization.

cs.CV↗

arXiv2025

Policy Search, Retrieval, and Composition via Task Similarity in Collaborative Agentic Systems

Agentic AI aims to create systems that set their own goals, adapt proactively to change, and refine behavior through continuous experience. Recent advances suggest that, when facing multiple and unforeseen tasks, agents could benefit from sharing machine-learned knowledge and reusing policies that have already been fully or partially learned by other agents. However, how to query, select, and retrieve policies from a pool of agents, and how to integrate such policies remains a largely unexplored area. This study explores how an agent decides what knowledge to select, from whom, and when and how to integrate it in its own policy in order to accelerate its own learning. The proposed algorithm, \emph{Modular Sharing and Composition in Collective Learning} (MOSAIC), improves learning in agentic collectives by combining (1) knowledge selection using performance signals and cosine similarity on Wasserstein task embeddings, (2) modular and transferable neural representations via masks, and (3) policy integration, composition and fine-tuning. MOSAIC outperforms isolated learners and global sharing approaches in both learning speed and overall performance, and in some cases solves tasks that isolated agents cannot. The results also demonstrate that selective, goal-driven reuse leads to less susceptibility to task interference. We also observe the emergence of self-organization, where agents solving simpler tasks accelerate the learning of harder ones through shared knowledge.

cs.LG↗

arXiv2025

READ: Real-time and Efficient Asynchronous Diffusion for Audio-driven Talking Head Generation

The introduction of diffusion models has brought significant advances to the field of audio-driven talking head generation. However, the extremely slow inference speed severely limits the practical implementation of diffusion-based talking head generation models. In this study, we propose READ, a real-time diffusion-transformer-based talking head generation framework. Our approach first learns a spatiotemporal highly compressed video latent space via a temporal VAE, significantly reducing the token count to accelerate generation. To achieve better audio-visual alignment within this compressed latent space, a pre-trained Speech Autoencoder (SpeechAE) is proposed to generate temporally compressed speech latent codes corresponding to the video latent space. These latent representations are then modeled by a carefully designed Audio-to-Video Diffusion Transformer (A2V-DiT) backbone for efficient talking head synthesis. Furthermore, to ensure temporal consistency and accelerated inference in extended generation, we propose a novel asynchronous noise scheduler (ANS) for both the training and inference processes of our framework. The ANS leverages asynchronous add-noise and asynchronous motion-guided generation in the latent space, ensuring consistency in generated video clips. Experimental results demonstrate that READ outperforms state-of-the-art methods by generating competitive talking head videos with significantly reduced runtime, achieving an optimal balance between quality and speed while maintaining robust metric stability in long-time generation.

cs.GR↗

arXiv2025

Constraining $σ_8$ with Lensing Statistics in Low and High Density Regions

Lensing studies are typically carried out around high density regions, such as groups and clusters, where the lensing signals are significant and indicative of rich density structures. However, a more comprehensive test of the cosmological model should also include the lensing effect in low density regions. In this work, we incorporate the stacked weak lensing signals around the low density positions, alongside galaxy-galaxy lensing and galaxy-galaxy two point correlation function to perform a joint cosmological analysis on $σ_8$. The low density positions are constructed from the DR9 data release of the DESI legacy imaging survey, using galaxies with r-band absolute magnitude cut M$<$-21.5 and in the redshift range of 0.18$<$z$<$0.28. In doing so, we simultaneously parameterize photometric redshift errors and halo mass uncertainties while building mock catalogs from simulations using the method of SubHalo Abundance Matching (SHAM). For the weak lensing measurements, we use the shear estimators derived from the DECaLS DR8 imaging data, processed by the Fourier_Quad pipeline. The survey boundaries and masks are fully taken into account. Our analysis achieves a total significance of $31.1σ$ detection for lensing in the low density positions, which significantly improve the $σ_8$ constraint compared to galaxy-galaxy lensing and galaxy-galaxy two point correlation function by 14$\%$. For flat $Λ$CDM model, we constrain $σ_8$ =$0.824^{+0.015}_{-0.015}$, which shows a good agreement with the PLANCK result. Additionally, the halo mass uncertainty $σ_{\lg M}$ and photometric redshift error $σ_z$ are constrained to be $0.565^{+0.086}_{-0.070}$ and $0.004^{+0.004}_{-0.003}$ respectively, which are somewhat different from our expectations due to the significant degeneracy of the two parameters.

astro-ph.CO↗

arXiv2025

Stabilization of Metallic, Excitonic Insulator, and Superionic Phases in Helium-Rare Gas Compounds at Sub-Terapascal Pressures

Helium and rare gases (RG: Ne, Ar, Kr, Xe) are typically considered chemically inert, yet under the extreme pressures of planetary interiors they may form compounds with unexpected properties. Using crystal structure prediction and first-principles calculations, we mapped the phase diagram of binary He-RG systems up to $1$ TPa. We identify several previously unknown stoichiometric compounds that are both thermodynamically and vibrationally stable at sub-terapascal pressures, within the reach of modern high-pressure experiments. In particular, AHe$_{2}$ and AHe (A: Ar, Kr, Xe) adopt previously unreported orthorhombic, hexagonal and cubic phases that remain stable over wide pressure ranges. We further find that He-Xe systems host metallic and excitonic insulator phases at pressures nearly an order of magnitude lower than those required for pure helium, offering a pathway to realize these exotic quantum states experimentally. Finite-temperature simulations also reveal superionic He-Xe phases, in which helium ions diffuse either anisotropically or isotropically depending on the host lattice. These findings constitute the first prediction of helium-based systems that combine metallicity and superionicity, with profound implications for energy transport and planetary dynamo processes. Overall, our results demonstrate that mixing helium with heavier rare gases provides an effective strategy to stabilize metallic, excitonic insulator, and superionic phases at experimentally accessible pressures, opening new research directions for condensed matter physics and planetary science.

cond-mat.mtrl-sci↗

arXiv2025

XDXD: End-to-end crystal structure determination with low resolution X-ray diffraction

Determining crystal structures from X-ray diffraction data is fundamental across diverse scientific fields, yet remains a significant challenge when data is limited to low resolution. While recent deep learning models have made breakthroughs in solving the crystallographic phase problem, the resulting low-resolution electron density maps are often ambiguous and difficult to interpret. To overcome this critical bottleneck, we introduce XDXD, to our knowledge, the first end-to-end deep learning framework to determine a complete atomic model directly from low-resolution single-crystal X-ray diffraction data. Our diffusion-based generative model bypasses the need for manual map interpretation, producing chemically plausible crystal structures conditioned on the diffraction pattern. We demonstrate that XDXD achieves a 70.4\% match rate for structures with data limited to 2.0~Å resolution, with a root-mean-square error (RMSE) below 0.05. Evaluated on a benchmark of 24,000 experimental structures, our model proves to be robust and accurate. Furthermore, a case study on small peptides highlights the model's potential for extension to more complex systems, paving the way for automated structure solution in previously intractable cases.

cond-mat.mtrl-sci↗

arXiv2025

TabAttackBench: A Benchmark for Adversarial Attacks on Tabular Data

Adversarial attacks pose a significant threat to machine learning models by inducing incorrect predictions through imperceptible perturbations to input data. While these attacks are well studied in unstructured domains such as images, their behaviour on tabular data remains underexplored due to mixed feature types and complex inter-feature dependencies. This study introduces a comprehensive benchmark that evaluates adversarial attacks on tabular datasets with respect to both effectiveness and imperceptibility. We assess five white-box attack algorithms (FGSM, BIM, PGD, DeepFool, and C\&W) across four representative models (LR, MLP, TabTransformer and FT-Transformer) using eleven datasets spanning finance, energy, and healthcare domains. The benchmark employs four quantitative imperceptibility metrics (proximity, sparsity, deviation, and sensitivity) to characterise perturbation realism. The analysis quantifies the trade-off between these two aspects and reveals consistent differences between attack types, with $\ell_\infty$-based attacks achieving higher success but lower subtlety, and $\ell_2$-based attacks offering more realistic perturbations. The benchmark findings offer actionable insights for designing more imperceptible adversarial attacks, advancing the understanding of adversarial vulnerability in tabular machine learning.

cs.LG↗

arXiv2025

Frame-based Equivariant Diffusion Models for 3D Molecular Generation

Recent methods for molecular generation face a trade-off: they either enforce strict equivariance with costly architectures or relax it to gain scalability and flexibility. We propose a frame-based diffusion paradigm that achieves deterministic E(3)-equivariance while decoupling symmetry handling from the backbone. Building on this paradigm, we investigate three variants: Global Frame Diffusion (GFD), which assigns a shared molecular frame; Local Frame Diffusion (LFD), which constructs node-specific frames and benefits from additional alignment constraints; and Invariant Frame Diffusion (IFD), which relies on pre-canonicalized invariant representations. To enhance expressivity, we further utilize EdgeDiT, a Diffusion Transformer with edge-aware attention. On the QM9 dataset, GFD with EdgeDiT achieves state-of-the-art performance, with a test NLL of -137.97 at standard scale and -141.85 at double scale, alongside atom stability of 98.98%, and molecular stability of 90.51%. These results surpass all equivariant baselines while maintaining high validity and uniqueness and nearly 2x faster sampling compared to EDM. Altogether, our study establishes frame-based diffusion as a scalable, flexible, and physically grounded paradigm for molecular generation, highlighting the critical role of global structure preservation.

cs.LG↗

arXiv2025

MACE: A Hybrid LLM Serving System with Colocated SLO-aware Continuous Retraining Alignment

Large language models (LLMs) deployed on edge servers are increasingly used in latency-sensitive applications such as personalized assistants, recommendation, and content moderation. However, the non-stationary nature of user data necessitates frequent retraining, which introduces a fundamental tension between inference latency and model accuracy under constrained GPU resources. Existing retraining strategies either delay model updates, over-commit resources to retraining, or overlook iteration-level retraining granularity. In this paper, we identify that iteration-level scheduling is crucial for adapting retraining frequency to model drift without violating service-level objectives (SLOs). We propose MACE, a hybrid LLM system that colocates concurrent inference (prefill, decode) and fine-tuning, with intelligent memory management to maximize task performance while promising inference throughput. MACE leverages the insight that not all model updates equally affect output alignment and allocates GPU cycles accordingly to balance throughput, latency, and update freshness. Our trace-driven evaluation shows that MACE matches or exceeds continuous retraining while reducing inference latency by up to 63% and maintaining throughput under resource constraints. Compared to periodic retraining, MACE improves latency breakdown across prefill, decode, and finetune stages, and sustains GPU utilization above 85% in NVIDIA AGX Orin. These results demonstrate that iteration-level hybrid scheduling is a promising direction for deploying LLMs with continual learning capabilities on edge platforms.

cs.LG↗

arXiv2025

Stabilization of Ferroelectric Hafnia and Zirconia through Y2O3 doping

We investigate the possible stabilization of ferroelectricity in bulk Y2O3-doped hafnia and zirconia. We use density functional theory (DFT) with large random supercells of hafnia and zirconia and study the relative phase stability of the centrosymmetric cubic and monoclinic phases compared with the polar orthorhombic phase. We find that Y2O3-doping stabilizes the polar ferroelectric phase over the monoclinic baddeleyite phase in both hafnia and zirconia.

cond-mat.mtrl-sci↗

arXiv2025

Thinking Before You Speak: A Proactive Test-time Scaling Approach

Large Language Models (LLMs) often exhibit deficiencies with complex reasoning tasks, such as maths, which we attribute to the discrepancy between human reasoning patterns and those presented in the LLMs' training data. When dealing with complex problems, humans tend to think carefully before expressing solutions. However, they often do not articulate their inner thoughts, including their intentions and chosen methodologies. Consequently, critical insights essential for bridging reasoning steps may be absent in training data collected from human sources. To bridge this gap, we proposes inserting \emph{insight}s between consecutive reasoning steps, which review the status and initiate the next reasoning steps. Unlike prior prompting strategies that rely on a single or a workflow of static prompts to facilitate reasoning, \emph{insight}s are \emph{proactively} generated to guide reasoning processes. We implement our idea as a reasoning framework, named \emph{Thinking Before You Speak} (TBYS), and design a pipeline for automatically collecting and filtering in-context examples for the generation of \emph{insight}s, which alleviates human labeling efforts and fine-tuning overheads. Experiments on challenging mathematical datasets verify the effectiveness of TBYS. Project website: https://gitee.com/jswrt/TBYS

cs.CL↗

arXiv2025

Collaborative Medical Triage under Uncertainty: A Multi-Agent Dynamic Matching Approach

The post-pandemic surge in healthcare demand, coupled with critical nursing shortages, has placed unprecedented pressure on medical triage systems, necessitating innovative AI-driven solutions. We present a multi-agent interactive intelligent system for medical triage that addresses three fundamental challenges in current AI-based triage systems: inadequate medical specialization leading to misclassification, heterogeneous department structures across healthcare institutions, and inefficient detail-oriented questioning that impedes rapid triage decisions. Our system employs three specialized agents--RecipientAgent, InquirerAgent, and DepartmentAgent--that collaborate through Inquiry Guidance mechanism and Classification Guidance Mechanism to transform unstructured patient symptoms into accurate department recommendations. To ensure robust evaluation, we constructed a comprehensive Chinese medical triage dataset from "Ai Ai Yi Medical Network", comprising 3,360 real-world cases spanning 9 primary departments and 62 secondary departments. Experimental results demonstrate that our multi-agent system achieves 89.6% accuracy in primary department classification and 74.3% accuracy in secondary department classification after four rounds of patient interaction. The system's dynamic matching based guidance mechanisms enable efficient adaptation to diverse hospital configurations while maintaining high triage accuracy. We successfully developed this multi-agent triage system that not only adapts to organizational heterogeneity across healthcare institutions but also ensures clinically sound decision-making.

cs.AI↗