Searcharxiv⌕ Search

arXiv subjects

Peng He

Publications and source records attributed to Peng He.

At least 37 records · Page 2Linked to original sources

HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds

We introduce HY-World 2.0, a multi-modal world model framework that advances our prior project HY-World 1.0. HY-World 2.0 accommodates diverse input modalities, including text prompts, single-view images, multi-view images, and videos, and produces 3D world representations. With text or single-view image inputs, the model performs world generation, synthesizing high-fidelity, navigable 3D Gaussian Splatting (3DGS) scenes. This is achieved through a four-stage method: a) Panorama Generation with HY-Pano 2.0, b) Trajectory Planning with WorldNav, c) World Expansion with WorldStereo 2.0, and d) World Composition with WorldMirror 2.0. Specifically, we introduce key innovations to enhance panorama fidelity, enable 3D scene understanding and planning, and upgrade WorldStereo, our keyframe-based view generation model with consistent memory. We also upgrade WorldMirror, a feed-forward model for universal 3D prediction, by refining model architecture and learning strategy, enabling world reconstruction from multi-view images or videos. Also, we introduce WorldLens, a high-performance 3DGS rendering platform featuring a flexible engine-agnostic architecture, automatic IBL lighting, efficient collision detection, and training-rendering co-design, enabling interactive exploration of 3D worlds with character support. Extensive experiments demonstrate that HY-World 2.0 achieves state-of-the-art performance on several benchmarks among open-source approaches, delivering results comparable to the closed-source model Marble. We release all model weights, code, and technical details to facilitate reproducibility and support further research on 3D world models.

cs.CV↗

Comparative Analysis of EMCEE, Gaussian Process, and Masked Autoregressive Flow in Constraining the Hubble Constant Using Cosmic Chronometers Dataset

The Hubble constant ($H_0$) is essential for understanding the universe's evolution. Different methods, such as Affine Invariant Markov chain Monte Carlo Ensemble sampler (EMCEE), Gaussian Process (GP), and Masked Autoregressive Flow (MAF), are used to constrain $H_0$ using $H(z)$ data. However, these methods produce varying $H_0$ values when applied to the same dataset. To investigate these differences, we compare the methods based on their sensitivity to individual data points and their performance in constraining $H_0$. We apply Monte Carlo delete-$d$ jackknife (MCDJ) to assess their sensitivity to individual data points. Our findings reveal that GP is more sensitive to individual data points than both MAF and EMCEE, with MAF being more sensitive than EMCEE. Sensitivity also depends on redshift: EMCEE and GP are more sensitive to $H(z)$ at higher redshifts, while MAF is more sensitive at lower redshifts. In simulation-based performance tests, we generate an ensemble of mock CC datasets with a fixed input truth $H_{0,\mathrm{true}}$, apply each method to recover $H_0$ posteriors, and summarise performance by comparing the recovered posterior to $H_{0,\mathrm{true}}$: (i) posterior central value accuracy (bias and RMSE), (ii) credible-interval calibration (68\% and 95\% coverage), and (iii) overall posterior quality (log score), under two simulation prescriptions ($Λ$CDM-based and GP-based). Overall, EMCEE performs best, GP is intermediate, and MAF performs worst across the performance metrics.

astro-ph.CO↗

Can Multimodal LLMs See Science Instruction? Benchmarking Pedagogical Reasoning in K-12 Classroom Videos

K-12 science classrooms are rich sites of inquiry where students coordinate phenomena, evidence, and explanatory models through discourse; yet, the multimodal complexity of these interactions has made automated analysis elusive. Existing benchmarks for classroom discourse focus primarily on mathematics and rely solely on transcripts, overlooking the visual artifacts and model-based reasoning emphasized by the Next Generation Science Standards (NGSS). We address this gap with SciIBI, the first video benchmark for analyzing science classroom discourse, featuring 113 NGSS-aligned clips annotated with Core Instructional Practices (CIP) and sophistication levels. By evaluating eight state-of-the-art LLMs and Multimodal LLMs, we reveal fundamental limitations: current models struggle to distinguish pedagogically similar practices, suggesting that CIP coding requires instructional reasoning beyond surface pattern matching. Furthermore, adding video input yields inconsistent gains across architectures. Crucially, our evidence-based evaluation reveals that models often succeed through surface shortcuts rather than genuine pedagogical understanding. These findings establish science classroom discourse as a challenging frontier for multimodal AI and point toward human-AI collaboration, where models retrieve evidence to accelerate expert review rather than replace it.

cs.CY↗

Bridging Discrete Marks and Continuous Dynamics: Dual-Path Cross-Interaction for Marked Temporal Point Processes

Predicting irregularly spaced event sequences with discrete marks poses significant challenges due to the complex, asynchronous dependencies embedded within continuous-time data streams.Existing sequential approaches capture dependencies among event tokens but ignore the continuous evolution between events, while Neural Ordinary Differential Equation (Neural ODE) methods model smooth dynamics yet fail to account for how event types influence future timing.To overcome these limitations, we propose NEXTPP, a dual-channel framework that unifies discrete and continuous representations via Event-granular Neural Evolution with Cross-Interaction for Marked Temporal Point Processes. Specifically, NEXTPP encodes discrete event marks via a self-attention mechanism, simultaneously evolving a latent continuous-time state using a Neural ODE. These parallel streams are then fused through a crossattention module to enable explicit bidirectional interaction between continuous and discrete representations. The fused representations drive the conditional intensity function of the neural Hawkes process, while an iterative thinning sampler is employed to generate future events. Extensive evaluations on five real-world datasets demonstrate that NEXTPP consistently outperforms state-of-the-art models. The source code can be found at https://github.com/AONE-NLP/NEXTPP.

cs.LG↗

How Uncertain Is the Grade? A Benchmark of Uncertainty Metrics for LLM-Based Automatic Assessment

The rapid rise of large language models (LLMs) is reshaping the landscape of automatic assessment in education. While these systems demonstrate substantial advantages in adaptability to diverse question types and flexibility in output formats, they also introduce new challenges related to output uncertainty, stemming from the inherently probabilistic nature of LLMs. Output uncertainty is an inescapable challenge in automatic assessment, as assessment results often play a critical role in informing subsequent pedagogical actions, such as providing feedback to students or guiding instructional decisions. Unreliable or poorly calibrated uncertainty estimates can lead to unstable downstream interventions, potentially disrupting students' learning processes and resulting in unintended negative consequences. To systematically understand this challenge and inform future research, we benchmark a broad range of uncertainty quantification methods in the context of LLM-based automatic assessment. Although the effectiveness of these methods has been demonstrated in many tasks across other domains, their applicability and reliability in educational settings, particularly for automatic grading, remain underexplored. Through comprehensive analyses of uncertainty behaviors across multiple assessment datasets, LLM families, and generation control settings, we characterize the uncertainty patterns exhibited by LLMs in grading scenarios. Based on these findings, we evaluate the strengths and limitations of different uncertainty metrics and analyze the influence of key factors, including model families, assessment tasks, and decoding strategies, on uncertainty estimates. Our study provides actionable insights into the characteristics of uncertainty in LLM-based automatic assessment and lays the groundwork for developing more reliable and effective uncertainty-aware grading systems in the future.

cs.AI↗

Negative-Aware Diffusion Process for Temporal Knowledge Graph Extrapolation

Temporal Knowledge Graph (TKG) reasoning seeks to predict future missing facts from historical evidence. While diffusion models (DM) have recently gained attention for their ability to capture complex predictive distributions, two gaps remain: (i) the generative path is conditioned only on positive evidence, overlooking informative negative context, and (ii) training objectives are dominated by cross-entropy ranking, which improves candidate ordering but provides little supervision over the calibration of the denoised embedding. To bridge this gap, we introduce Negative-Aware Diffusion model for TKG Extrapolation (NADEx). Specifically, NADEx encodes subject-centric histories of entities, relations and temporal intervals into sequential embeddings. NADEx perturbs the query object in the forward process and reconstructs it in reverse with a Transformer denoiser conditioned on the temporal-relational context. We further derive a cosine-alignment regularizer derived from batch-wise negative prototypes, which tightens the decision boundary against implausible candidates. Comprehensive experiments on four public TKG benchmarks demonstrate that NADEx delivers state-of-the-art performance.

cs.AI↗

Multi-View Adaptive Contrastive Learning for Information Retrieval Based Fault Localization

Most studies focused on information retrieval-based techniques for fault localization, which built representations for bug reports and source code files and matched their semantic vectors through similarity measurement. However, such approaches often ignore some useful information that might help improve localization performance, such as 1) the interaction relationship between bug reports and source code files; 2) the similarity relationship between bug reports; and 3) the co-citation relationship between source code files. In this paper, we propose a novel approach named Multi-View Adaptive Contrastive Learning for Information Retrieval Fault Localization (MACL-IRFL) to learn the above-mentioned relationships for software fault localization. Specifically, we first generate data augmentations from report-code interaction view, report-report similarity view and code-code co-citation view separately, and adopt graph neural network to aggregate the information of bug reports or source code files from the three views in the embedding process. Moreover, we perform contrastive learning across these views. Our design of contrastive learning task will force the bug report representations to encode information shared by report-report and report-code views,and the source code file representations shared by code-code and report-code views, thereby alleviating the noise from auxiliary information. Finally, to evaluate the performance of our approach, we conduct extensive experiments on five open-source Java projects. The results show that our model can improve over the best baseline up to 28.93%, 25.57% and 20.35% on Accuracy@1, MAP and MRR, respectively.

cs.SE↗

DrawSim-PD: Simulating Student Science Drawings to Support NGSS-Aligned Teacher Diagnostic Reasoning

Developing expertise in diagnostic reasoning requires practice with diverse student artifacts, yet privacy regulations prohibit sharing authentic student work for teacher professional development (PD) at scale. We present DrawSim-PD, the first generative framework that simulates NGSS-aligned, student-like science drawings exhibiting controllable pedagogical imperfections to support teacher training. Central to our approach are apability profiles--structured cognitive states encoding what students at each performance level can and cannot yet demonstrate. These profiles ensure cross-modal coherence across generated outputs: (i) a student-like drawing, (ii) a first-person reasoning narrative, and (iii) a teacher-facing diagnostic concept map. Using 100 curated NGSS topics spanning K-12, we construct a corpus of 10,000 systematically structured artifacts. Through an expert-based feasibility evaluation, K--12 science educators verified the artifacts' alignment with NGSS expectations (>84% positive on core items) and utility for interpreting student thinking, while identifying refinement opportunities for grade-band extremes. We release this open infrastructure to overcome data scarcity barriers in visual assessment research.

cs.CY↗

Floquet quantum geometry in periodically driven topological insulators

Quantum geometry plays a fundamental role across many branches of modern physics, yet its full characterization in nonequilibrium systems remains a challenge. Here, we propose a framework for quantum geometry in Floquet topological insulators by introducing a time-resolved quantum metric tensor, defined via the trace distance between micromotion operators in momentum-time space. For class A in two spatial dimensions, we find a general inequality linking the Floquet quantum metric tensor and the Floquet topology: the associated quantum volume is bounded below by the Floquet topological invariant. This relation is found to also hold in class AIII in one dimension, where the Floquet geometric tensor may be notably reduced due to time-reflection symmetry. This work will be useful in digesting the general aspects of quantum geometry in periodically driven systems in connection with their topological characterization.

cond-mat.mes-hall↗

Judging the Judges: Human Validation of Multi-LLM Evaluation for High-Quality K--12 Science Instructional Materials

Designing high-quality, standards-aligned instructional materials for K--12 science is time-consuming and expertise-intensive. This study examines what human experts notice when reviewing AI-generated evaluations of such materials, aiming to translate their insights into design principles for a future GenAI-based instructional material design agent. We intentionally selected 12 high-quality curriculum units across life, physical, and earth sciences from validated programs such as OpenSciEd and Multiple Literacies in Project-based Learning. Using the EQuIP rubric with 9 evaluation items, we prompted GPT-4o, Claude, and Gemini to produce numerical ratings and written rationales for each unit, generating 648 evaluation outputs. Two science education experts independently reviewed all outputs, marking agreement (1) or disagreement (0) for both scores and rationales, and offering qualitative reflections on AI reasoning. This process surfaces patterns in where LLM judgments align with or diverge from expert perspectives, revealing reasoning strengths, gaps, and contextual nuances. These insights will directly inform the development of a domain-specific GenAI agent to support the design of high-quality instructional materials in K--12 science education.

cs.CY↗

Constructing left-continuous triangular norms on complete lattices

This article focuses on the construction of left-continuous t-norms on complete lattices. The concepts of $\mathfrak{f}$-mappings and weak $\mathfrak{f}$-mappings on complete lattices are first introduced, respectively. They are then applied to establish the following key results: weak $\mathfrak{f}$-mappings are used to induce left-continuous t-subnorms; $\mathfrak{f}$-mappings are used to generate left-continuous t-norms whenever the top element $1$ of the complete lattice is a completely join-irreducible element. Finally, some necessary and sufficient conditions are provided for an operator constructed by the ordinal sum of a series of annihilating binary operators being a left-continuous t-norm on a complete lattice.

math.GM↗

HY-Motion 1.0: Scaling Flow Matching Models for Text-To-Motion Generation

We present HY-Motion 1.0, a series of state-of-the-art, large-scale, motion generation models capable of generating 3D human motions from textual descriptions. HY-Motion 1.0 represents the first successful attempt to scale up Diffusion Transformer (DiT)-based flow matching models to the billion-parameter scale within the motion generation domain, delivering instruction-following capabilities that significantly outperform current open-source benchmarks. Uniquely, we introduce a comprehensive, full-stage training paradigm -- including large-scale pretraining on over 3,000 hours of motion data, high-quality fine-tuning on 400 hours of curated data, and reinforcement learning from both human feedback and reward models -- to ensure precise alignment with the text instruction and high motion quality. This framework is supported by our meticulous data processing pipeline, which performs rigorous motion cleaning and captioning. Consequently, our model achieves the most extensive coverage, spanning over 200 motion categories across 6 major classes. We release HY-Motion 1.0 to the open-source community to foster future research and accelerate the transition of 3D human motion generation models towards commercial maturity.

cs.CV↗

Constraining the Hubble Constant with a Simulated Full Covariance Matrix Using Neural Networks

The Hubble parameter, $H(z)$, plays a crucial role in understanding the expansion history of the universe and constraining the Hubble constant, $\mathrm{H}_0$. The Cosmic Chronometers (CC) method provides an independent approach to measuring $H(z)$, but existing studies either neglect off-diagonal elements in the covariance matrix or use an incomplete covariance matrix, limiting the accuracy of $\mathrm{H}_0$ constraints. To address this, we use a Positive-Definite Covariance Network (PD-CovNet) to simulate the full $33 \times 33$ covariance matrix based on a previously published $15 \times 15$ covariance matrix. Hyperparameters are chosen via leave-one-z-out validation, and performance is benchmarked against a Gaussian-process (GP) baseline. Under identical five-fold cross-validation over redshift groups, we prove that PD-CovNet is a reliable generator of the full covariance compared to the GP baseline. Using this full PD-CovNet-simulated covariance alongside three comparators with different covariance specifications, we constrain $\mathrm{H}_0$ with two independent methods (EMCEE and GP). Across all covariance specifications and both constraint methods, standardized differences and two-sided p-values show no statistically meaningful shift in the central value of the constrained $\mathrm{H}_0$. However, the precision of the constrained $\mathrm{H}_0$ depends on both covariance and method: EMCEE is uniformly more precise than GP once covariance is modeled; within a fixed method, incorporating more covariance reduces precision; and PD-CovNet hyperparameters have a modest effect on uncertainty. These results indicate the importance of accurate covariance modeling in CC-based $\mathrm{H}_0$ constraints.

astro-ph.CO↗

Exploiting Inter-Session Information with Frequency-enhanced Dual-Path Networks for Sequential Recommendation

Sequential recommendation (SR) aims to predict a user's next item preference by modeling historical interaction sequences. Recent advances often integrate frequency-domain modules to compensate for self-attention's low-pass nature by restoring the high-frequency signals critical for personalized recommendations. Nevertheless, existing frequency-aware solutions process each session in isolation and optimize exclusively with time-domain objectives. Consequently, they overlook cross-session spectral dependencies and fail to enforce alignment between predicted and actual spectral signatures, leaving valuable frequency information under-exploited. To this end, we propose FreqRec, a Frequency-Enhanced Dual-Path Network for sequential Recommendation that jointly captures inter-session and intra-session behaviors via a learnable Frequency-domain Multi-layer Perceptrons. Moreover, FreqRec is optimized under a composite objective that combines cross entropy with a frequency-domain consistency loss, explicitly aligning predicted and true spectral signatures. Extensive experiments on three benchmarks show that FreqRec surpasses strong baselines and remains robust under data sparsity and noisy-log conditions.

cs.IR↗

RECALL: REpresentation-aligned Catastrophic-forgetting ALLeviation via Hierarchical Model Merging

We unveil that internal representations in large language models (LLMs) serve as reliable proxies of learned knowledge, and propose RECALL, a novel representation-aware model merging framework for continual learning without access to historical data. RECALL computes inter-model similarity from layer-wise hidden representations over clustered typical samples, and performs adaptive, hierarchical parameter fusion to align knowledge across models. This design enables the preservation of domain-general features in shallow layers while allowing task-specific adaptation in deeper layers. Unlike prior methods that require task labels or incur performance trade-offs, RECALL achieves seamless multi-domain integration and strong resistance to catastrophic forgetting. Extensive experiments across five NLP tasks and multiple continual learning scenarios show that RECALL outperforms baselines in both knowledge retention and generalization, providing a scalable and data-free solution for evolving LLMs.

cs.CL↗

Hunyuan3D Studio: End-to-End AI Pipeline for Game-Ready 3D Asset Generation

The creation of high-quality 3D assets, a cornerstone of modern game development, has long been characterized by labor-intensive and specialized workflows. This paper presents Hunyuan3D Studio, an end-to-end AI-powered content creation platform designed to revolutionize the game production pipeline by automating and streamlining the generation of game-ready 3D assets. At its core, Hunyuan3D Studio integrates a suite of advanced neural modules (such as Part-level 3D Generation, Polygon Generation, Semantic UV, etc.) into a cohesive and user-friendly system. This unified framework allows for the rapid transformation of a single concept image or textual description into a fully-realized, production-quality 3D model complete with optimized geometry and high-fidelity PBR textures. We demonstrate that assets generated by Hunyuan3D Studio are not only visually compelling but also adhere to the stringent technical requirements of contemporary game engines, significantly reducing iteration time and lowering the barrier to entry for 3D content creation. By providing a seamless bridge from creative intent to technical asset, Hunyuan3D Studio represents a significant leap forward for AI-assisted workflows in game development and interactive media.

cs.CV↗

Theoretical Radio Signals from Radio-Band Gravitational Waves Converted from the Neutron Star Magnetic Field

Gravitational waves (GWs) can convert into electromagnetic waves in the presence of a magnetic field via the Gertsenshtein-Zeldovich (GZ) effect. The characteristics of the magnetic field substantially affect this conversion probability. This paper confirms that strong magnetic fields in neutron stars significantly enhance the conversion probability, facilitating detectable radio signatures of very high-frequency (VHF, $\left(10^6-10^{11}\mathrm{~Hz}\right)$) gravitational waves. We theoretically identify two distinct signatures using single-dish telescopes (FAST, TMRT, QTT, GBT) and interferometers (SKA1/2-MID): transient signals from burst-like gravitational wave sources and persistent signals from cosmological background gravitational wave sources. These signatures are mapped to graviton spectral lines derived from quantum field theory by incorporating spin-2 and mass constraints, resulting in smooth, featureless profiles that are critical for distinguishing gravitational wave signals from astrophysical foregrounds. FAST attains a characteristic strain bound of $h_c<10^{-23}$, approaching $10^{-24}$ in the frequency range of $1-3\mathrm{~GHz}$ with a 6-hour observation period. This performance exceeds the $5 σ$ detection thresholds for GWs originating from primordial black holes (PBHs) and nears the limits set by Big Bang nucleosynthesis. Additionally, projections for SKA2-MID indicate even greater sensitivity. Detecting such gravitational waves would improve our comprehension of cosmological models, refine the parameter spaces for primordial black holes, and function as a test for quantum field theory. This approach addresses significant deficiencies in VHF GW research, improving detection sensitivity and facilitating the advancement of next-generation radio telescopes such as FASTA and SKA, which feature larger fields of view and enhanced gain.

astro-ph.HE↗

Estimating Cosmological Parameters and Reconstructing Hubble Constant with Artificial Neural Networks: A Test with covariance matrix and mock H(z)

In this work, we reconstruct the H(z) based on observational Hubble data with Artificial Neural Network, then estimate the cosmological parameters and the Hubble constant. The training data we used are covariance matrix and mock H(z), which are generated based on the real OHD data and Gaussian Process(GP). The use of the covariance matrix propagates the correlated uncertainties and improves training efficiency. Using the reconstructed H(z) data, we first determine the Hubble constant and compare it with CMB-based measurements. To constrain cosmological parameters, we sample on the reconstructed data and calculate the corresponding posterior distributions with Markov Chain Monte Carlo (MCMC). Through comprehensive statistical comparisons, we demonstrate that the parameter estimation using reconstructed samples achieves comparable statistical accuracy to the result derived from real OHD data.

astro-ph.CO↗