arXiv subjects

Hao Yang

Publications and source records attributed to Hao Yang.

At least 109 records · Page 6Linked to original sources

arXiv2025

Operation Veja: Fixing Fundamental Concepts Missing from Modern Roleplaying Training Paradigms

Modern roleplaying models are increasingly sophisticated, yet they consistently struggle to capture the essence of believable, engaging characters. We argue this failure stems from training paradigms that overlook the dynamic interplay of a character's internal world. Current approaches, including Retrieval-Augmented Generation (RAG), fact-based priming, literature-based learning, and synthetic data generation, exhibit recurring limitations in modeling the deliberative, value-conflicted reasoning that defines human interaction. In this paper, we identify four core concepts essential for character authenticity: Values, Experiences, Judgments, and Abilities (VEJA). We propose the VEJA framework as a new paradigm for data curation that addresses these systemic limitations. To illustrate the qualitative ceiling enabled by our framework, we present a pilot study comparing a manually curated, VEJA-grounded dataset against a state-of-the-art synthetic baseline. Using an LLM-as-judge evaluation, our findings demonstrate a significant quality gap, suggesting that a shift toward conceptually grounded data curation, as embodied by VEJA, is necessary for creating roleplaying agents with genuine depth and narrative continuity. The full dataset is available at https://github.com/HyouinKyoumaIRL/Operation-Veja

cs.CL↗

arXiv2025

MAVERIX: Multimodal Audio-Visual Evaluation and Recognition IndeX

We introduce MAVERIX (Multimodal audiovisual Evaluation and Recognition IndeX), a unified benchmark to probe the video understanding in multimodal LLMs, encompassing video, audio, text inputs with human performance baselines. Although recent advancements in models with vision and audio understanding capabilities have shown substantial progress, the field lacks a standardized evaluation framework to thoroughly assess their cross-modality comprehension performance. MAVERIX curates 2,556 questions from 700 videos, in the form of both multiple-choice and open-ended formats, explicitly designed to evaluate multimodal models through questions that necessitate tight integration of video and audio information, spanning a broad spectrum of agentic scenarios. MAVERIX uniquely provides models with audiovisual questions, closely mimicking the multimodal perceptual experiences available to humans during inference and decision-making processes. To our knowledge, MAVERIX is the first benchmark aimed explicitly at assessing comprehensive audiovisual integration in such granularity. Experiments with state-of-the-art models, including Qwen 2.5 Omni and Gemini 2.5 Flash-Lite, show performance around 64% accuracy, while human experts reach near-ceiling performance of 92.8%, exposing a substantial gap to human-level comprehension. With standardized evaluation protocols, a rigorously annotated pipeline, and a public toolkit, MAVERIX establishes a challenging testbed for advancing audiovisual multimodal intelligence.

cs.MM↗

arXiv2025

The Power Method for Non-Hermitian Dual Quaternion Matrices

This paper proposes a power method for computing the dominant eigenvalues of a non-Hermitian dual quaternion matrix (DQM). Although the algorithmic framework parallels the Hermitian case, the theoretical analysis is substantially more complex since a non-Hermitian dual matrix may possess no eigenvalues or infinitely many eigenvalues. Besides, its eigenvalues are not necessarily dual numbers, leading to non-commutative behavior that further complicates the analysis. We first present a sufficient condition that ensures the existence of an eigenvalue whose standard part corresponds to the largest magnitude eigenvalue of the standard part matrix. Under a stronger condition, we then establish that the sequence generated by the power method converges linearly to the strict dominant eigenvalue and its associated eigenvectors. We also verify that this condition is necessary. The key to our analysis is a new Jordan-like decomposition, which addresses a gap arising from the lack of a conventional Jordan decomposition for non-Hermitian dual matrices. Our framework readily extends to non-Hermitian dual complex and dual number matrices. We also develop an adjoint method that reformulates the eigenvalue problem into an equivalent form for dual complex matrices. Numerical experiments on non-Hermitian DQMs are presented to demonstrate the efficiency of the power method.

math.NA↗

arXiv2025

The Solar Close Observations and Proximity Experiments (SCOPE) mission

The Solar Close Observations and Proximity Experiments (SCOPE) mission will send a spacecraft into the solar atmosphere at a low altitude of just 5 R_sun from the solar center. It aims to elucidate the mechanisms behind solar eruptions and coronal heating, and to directly measure the coronal magnetic field. The mission will perform in situ measurements of the current sheet between coronal mass ejections and their associated solar flares, and energetic particles produced by either reconnection or fast-mode shocks driven by coronal mass ejections. This will help to resolve the nature of reconnections in current sheets, and energetic particle acceleration regions. To investigate coronal heating, the mission will observe nano-flares on scales smaller than 70 km in the solar corona and regions smaller than 40 km in the photosphere, where magnetohydrodynamic waves originate. To study solar wind acceleration mechanisms, the mission will also track the process of ion charge-state freezing in the solar wind. A key achievement will be the observation of the coronal magnetic field at unprecedented proximity to the solar photosphere. The polar regions will also be observed at close range, and the inner edge of the solar system dust disk may be identified for the first time. This work presents the detailed background, science, and mission concept of SCOPE and discusses how we aim to address the questions mentioned above.

astro-ph.SR↗

arXiv2025

Demographic Inference from Social Media Data with Multimodal Foundation Models: Strategies, Evaluation, and Benchmarking

Demographic inference plays a crucial role in understanding the representativeness and equity of social media-based research. However, existing methods typically rely on a single modality, such as text, image, or network, and are limited to predicting one or two demographic attributes, constraining their generalizability and robustness across populations. This study leverages GPT-5, a state-of-the-art multimodal foundation model, to infer age, gender, and race from social media profiles. Using a dataset of 263 publicly available X (formerly Twitter) users, we design a progressive multimodal framework that incrementally incorporates usernames, profile descriptions, tweets, and profile images to examine how each information source contributes to inference accuracy. Results show a consistent improvement across all conditions, with the inclusion of textual and visual cues substantially enhancing performance. GPT-5 achieves an overall accuracy of 0.90 for age, 0.98 for gender, and 0.85 for race, outperforming existing models under equivalent inputs. These findings demonstrate the potential of large multimodal foundation models to capture complex, cross-modal demographic cues with minimal task-specific training. The study further highlights a transparent, interpretable approach to multimodal reasoning that advances the accuracy, fairness, and scalability of demographic inference in social data analytics.

cs.SI↗

arXiv2025

Cisco Time Series Model Technical Report

We introduce the Cisco Time Series Model, a univariate zero-shot forecaster. This time series foundation model is the result of a general architectural innovation to a time series model enabling it to accept multiresolution input, applied to a popular decoder-only time series model (TimesFM). The resulting multiresolution decoder-only model is trained on over 300B unique data points, with more than half coming from the observability domain. Quantitative and qualitative evaluations demonstrate that the resulting model achieves superior performance on observability datasets while retaining very similar performance on a standard general-purpose forecasting benchmark (GIFT-Eval), and suggest that the multiresolution structure enables the model to make more accurate predictions on long context input.

cs.LG↗

arXiv2025

DAPointMamba: Domain Adaptive Point Mamba for Point Cloud Completion

Domain adaptive point cloud completion (DA PCC) aims to narrow the geometric and semantic discrepancies between the labeled source and unlabeled target domains. Existing methods either suffer from limited receptive fields or quadratic complexity due to using CNNs or vision Transformers. In this paper, we present the first work that studies the adaptability of State Space Models (SSMs) in DA PCC and find that directly applying SSMs to DA PCC will encounter several challenges: directly serializing 3D point clouds into 1D sequences often disrupts the spatial topology and local geometric features of the target domain. Besides, the overlook of designs in the learning domain-agnostic representations hinders the adaptation performance. To address these issues, we propose a novel framework, DAPointMamba for DA PCC, that exhibits strong adaptability across domains and has the advantages of global receptive fields and efficient linear complexity. It has three novel modules. In particular, Cross-Domain Patch-Level Scanning introduces patch-level geometric correspondences, enabling effective local alignment. Cross-Domain Spatial SSM Alignment further strengthens spatial consistency by modulating patch features based on cross-domain similarity, effectively mitigating fine-grained structural discrepancies. Cross-Domain Channel SSM Alignment actively addresses global semantic gaps by interleaving and aligning feature channels. Extensive experiments on both synthetic and real-world benchmarks demonstrate that our DAPointMamba outperforms state-of-the-art methods with less computational complexity and inference latency.

cs.CV↗

arXiv2025

Global and local observability of hypergraphs

This paper studies observability for non-uniform hypergraphs with inputs and outputs. To capture higher-order interactions, we define a canonical non-homogeneous dynamical system with nonlinear outputs on hypergraphs. We then construct algebraic necessary and sufficient conditions based on polynomial ideals and varieties for global observability at an initial state of hypergraphs. An example is given to illustrate the proposed criteria for observability. Further, necessary and sufficient conditions for local observability are derived based on rank conditions of observability matrices, which provide a framework to study local observability for non-uniform hypergraphs. Finally, the similarity of observability for hypergraphs is proposed using similarity of tensors, which reveals the relation of observability between two hypergraphs and helps to check the observability intuitively.

eess.SY↗

arXiv2025

CARE-Bench: A Benchmark of Diverse Client Simulations Guided by Expert Principles for Evaluating LLMs in Psychological Counseling

The mismatch between the growing demand for psychological counseling and the limited availability of services has motivated research into the application of Large Language Models (LLMs) in this domain. Consequently, there is a need for a robust and unified benchmark to assess the counseling competence of various LLMs. Existing works, however, are limited by unprofessional client simulation, static question-and-answer evaluation formats, and unidimensional metrics. These limitations hinder their effectiveness in assessing a model's comprehensive ability to handle diverse and complex clients. To address this gap, we introduce \textbf{CARE-Bench}, a dynamic and interactive automated benchmark. It is built upon diverse client profiles derived from real-world counseling cases and simulated according to expert guidelines. CARE-Bench provides a multidimensional performance evaluation grounded in established psychological scales. Using CARE-Bench, we evaluate several general-purpose LLMs and specialized counseling models, revealing their current limitations. In collaboration with psychologists, we conduct a detailed analysis of the reasons for LLMs' failures when interacting with clients of different types, which provides directions for developing more comprehensive, universal, and effective counseling models.

cs.CL↗

arXiv2025

Stacking-orientation and twist-angle control on integer and fractional Chern insulators in moiré rhombohedral graphene

Rhombohedral-stacked multilayer graphene aligned with hexagonal boron nitride has emerged as an excellent platform for investigating exotic quantum phenomena arising from the interplay between electron correlations and nontrivial topology. However, the microscopic mechanism governing the emergence of both the integer and fractional Chern insulator states in this system remains an open question. In this work, we systematically investigate the electrical transport properties of RMG/hBN moiré devices with controlled alignment orientations and twist angles. We demonstrate that alignment orientation strongly modulates correlated phenomena in the moiré-proximal regime, while having negligible influence on the formation of integer and fractional Chern insulators in the moiré-distant regime. Instead, the moiré periodicity, tuned by the twist angle, serves as the key parameter controlling the stability of these correlated topological states in the moiré-distant regime. Furthermore, in the moiré-proximal regime of one specific alignment, we observe anomalous Hall effect and a variety of competing phases near ν = 1, including integer Chern insulator states, extended Chern insulator states, and trivial insulators, whose stability is highly sensitive to both the applied displacement electric field and magnetic field. Our results underscore the critical role of stacking-alignment and twist-angle engineering in exploring novel quantum states based on rhombohedral-stacked multilayer graphene moiré systems.

cond-mat.mes-hall↗

arXiv2025

What Makes Reasoning Invalid: Echo Reflection Mitigation for Large Language Models

Large Language Models (LLMs) have demonstrated remarkable performance across a wide range of reasoning tasks. Recent methods have further improved LLM performance in complex mathematical reasoning. However, when extending these methods beyond the domain of mathematical reasoning to tasks involving complex domain-specific knowledge, we observe a consistent failure of LLMs to generate novel insights during the reflection stage. Instead of conducting genuine cognitive refinement, the model tends to mechanically reiterate earlier reasoning steps without introducing new information or perspectives, a phenomenon referred to as "Echo Reflection". We attribute this behavior to two key defects: (1) Uncontrollable information flow during response generation, which allows premature intermediate thoughts to propagate unchecked and distort final decisions; (2) Insufficient exploration of internal knowledge during reflection, leading to repeating earlier findings rather than generating new cognitive insights. Building on these findings, we proposed a novel reinforcement learning method termed Adaptive Entropy Policy Optimization (AEPO). Specifically, the AEPO framework consists of two major components: (1) Reflection-aware Information Filtration, which quantifies the cognitive information flow and prevents the final answer from being affected by earlier bad cognitive information; (2) Adaptive-Entropy Optimization, which dynamically balances exploration and exploitation across different reasoning stages, promoting both reflective diversity and answer correctness. Extensive experiments demonstrate that AEPO consistently achieves state-of-the-art performance over mainstream reinforcement learning baselines across diverse benchmarks.

cs.AI↗

arXiv2025

A multi-modal vision-language model for generalizable annotation-free pathology localization

Existing deep learning models for defining pathology from clinical imaging data rely on expert annotations and lack generalization capabilities in open clinical environments. Here, we present a generalizable vision-language model for Annotation-Free pathology Localization (AFLoc). The core strength of AFLoc is extensive multi-level semantic structure-based contrastive learning, which comprehensively aligns multi-granularity medical concepts with abundant image features to adapt to the diverse expressions of pathologies without the reliance on expert image annotations. We conduct primary experiments on a dataset of 220K pairs of image-report chest X-ray images and perform validation across eight external datasets encompassing 34 types of chest pathologies. The results demonstrate that AFLoc outperforms state-of-the-art methods in both annotation-free localization and classification tasks. Additionally, we assess the generalizability of AFLoc on other modalities, including histopathology and retinal fundus images. We show that AFLoc exhibits robust generalization capabilities, even surpassing human benchmarks in localizing five different types of pathological images. These results highlight the potential of AFLoc in reducing annotation requirements and its applicability in complex clinical environments.

cs.CV↗

arXiv2025

An Unusual Dresselhaus Spin-Orbit Contribution of Even Order in Momentum

The spin-orbit (SO) coupling is conventionally known to manifest as \emph{odd} functions of momentum. Here, through both model calculations and symmetry analysis along with the method of invariants, we reveal that, in ordinary semiconductor heterostructures, a \emph{quadratic} Dresselhaus SO term -- inheriting from its bulk crystal form -- emerges via the interband effect, while complying with time-reversal and spatial symmetries. Furthermore, we observe that this unusual SO term gives rise to a range of striking quantum phenomena, including hybridized swirling texture, anisotropic energy dispersion, avoided band crossing, longitudinal \emph{Zitterbewegung}, and opposite spin evolution between different bands in quantum dynamics. These stand in stark contrast to those associated with the usual \emph{linear} SO terms. Our findings uncover a previously overlooked route for exploiting interband effects and open new avenues for spintronic functionalities that leverage unusual SO terms of \emph{even} orders in momentum.

cond-mat.mes-hall↗

arXiv2025

Doubly heavy hadron production in ultraperipheral collisions

The inclusive production of pseudoscalar heavy quarkonia ($η_c,\, η_b,\, B_c$), double heavy baryons $Ξ_{QQ^\prime}$ ($Q^{(\prime)}=c,\,b$ quarks) and tetraquarks $T_{QQ}$ in heavy ion ultraperipheral collisions (UPCs) is studied. Numerical results indicate that the experimental investigation of $η_c,\, Ξ_{cc}$, and $T_{cc}$ is feasible at the upcoming HL-LHC and future FCC. Heavy ion UPCs open another avenue for studying the production of these doubly heavy hadrons.

hep-ph↗

arXiv2025

Generative Annotation for ASR Named Entity Correction

End-to-end automatic speech recognition systems often fail to transcribe domain-specific named entities, causing catastrophic failures in downstream tasks. Numerous fast and lightweight named entity correction (NEC) models have been proposed in recent years. These models, mainly leveraging phonetic-level edit distance algorithms, have shown impressive performances. However, when the forms of the wrongly-transcribed words(s) and the ground-truth entity are significantly different, these methods often fail to locate the wrongly transcribed words in hypothesis, thus limiting their usage. We propose a novel NEC method that utilizes speech sound features to retrieve candidate entities. With speech sound features and candidate entities, we inovatively design a generative method to annotate entity errors in ASR transcripts and replace the text with correct entities. This method is effective in scenarios of word form difference. We test our method using open-source and self-constructed test sets. The results demonstrate that our NEC method can bring significant improvement to entity accuracy. The self-constructed training data and test set is publicly available at github.com/L6-NLP/Generative-Annotation-NEC.

cs.CL↗

arXiv2025

HHEML: Hybrid Homomorphic Encryption for Privacy-Preserving Machine Learning on Edge

Privacy-preserving machine learning (PPML) is an emerging topic to handle secure machine learning inference over sensitive data in untrusted environments. Fully homomorphic encryption (FHE) enables computation directly on encrypted data on the server side, making it a promising approach for PPML. However, it introduces significant communication and computation overhead on the client side, making it impractical for edge devices. Hybrid homomorphic encryption (HHE) addresses this limitation by combining symmetric encryption (SE) with FHE to reduce the computational cost on the client side, and combining with an FHE-friendly SE can also lessen the processing overhead on the server side, making it a more balanced and efficient alternative. Our work proposes a hardware-accelerated HHE architecture built around a lightweight symmetric cipher optimized for FHE compatibility and implemented as a dedicated hardware accelerator. To the best of our knowledge, this is the first design to integrate an end-to-end HHE framework with hardware acceleration. Beyond this, we also present several microarchitectural optimizations to achieve higher performance and energy efficiency. The proposed work is integrated into a full PPML pipeline, enabling secure inference with significantly lower latency and power consumption than software implementations. Our contributions validate the feasibility of low-power, hardware- accelerated HHE for edge deployment and provide a hardware- software co-design methodology for building scalable, secure machine learning systems in resource-constrained environments. Experiments on a PYNQ-Z2 platform with the MNIST dataset show over a 50x reduction in client-side encryption latency and nearly a 2x gain in hardware throughput compared to existing FPGA-based HHE accelerators.

cs.CR↗

arXiv2025

Taming Text-to-Image Synthesis for Novices: User-centric Prompt Generation via Multi-turn Guidance

The emergence of text-to-image synthesis (TIS) models has significantly influenced digital image creation by producing high-quality visuals from written descriptions. Yet these models are sensitive on textual prompts, posing a challenge for novice users who may not be familiar with TIS prompt writing. Existing solutions relieve this via automatic prompt expansion or generation from a user query. However, this single-turn manner suffers from limited user-centricity in terms of result interpretability and user interactivity. Thus, we propose DialPrompt, a dialogue-based TIS prompt generation model that emphasizes user experience for novice users. DialPrompt is designed to follow a multi-turn workflow, where in each round of dialogue the model guides user to express their preferences on possible optimization dimensions before generating the final TIS prompt. To achieve this, we mined 15 essential dimensions for high-quality prompts from advanced users and curated a multi-turn dataset. Through training on this dataset, DialPrompt improves user-centricity by allowing users to perceive and control the creation process of TIS prompts. Experiments indicate that DialPrompt improves significantly in user-centricity score compared with existing approaches while maintaining a competitive quality of synthesized images. In our user evaluation, DialPrompt is highly rated by 19 human reviewers (especially novices).

cs.AI↗

arXiv2025

The dark matter content of Milky Way dwarf spheroidal galaxies: Draco, Sextans and Ursa Minor

The Milky Way Survey of the Dark Energy Spectroscopic Instrument (DESI) has so far observed three classical dwarf spheroidal galaxies (dSphs): Draco, Sextans and Ursa Minor. Based on the observed line-of-sight velocities and metallicities of their member stars, we apply the axisymmetric Jeans Anisotropic Multi-Gaussian Expansion modeling (JAM) approach to recover their inner dark matter distributions. In particular, both the traditional single-population Jeans model and the multiple population chemodynamical model are adopted. With the chemodynamical model, we divide member stars of each dSph into metal-rich and metal-poor populations. The metal-rich populations are more centrally concentrated and dynamically colder, featuring lower velocity dispersion profiles than the metal-poor populations. We find a diversity of the inner density slopes $γ$ of dark matter halos, with the best constraints by single-population or chemodynamical models consistent with each other. The inner density slopes are $0.71^{+0.34}_{-0.35}$, $0.26^{+0.22}_{-0.12}$ and $0.33^{+0.20}_{-0.16}$ for Draco, Sextans and Ursa Minor, respectively. We also present the measured astrophysical J and D factors of the three dSphs. Our results indicate that the study of the dark matter content of dSphs through stellar kinematics is still subject to uncertainties behind both the methodology and the observed data, through comparisons with previous measurements and data sets.

astro-ph.GA↗