Searcharxiv⌕ Search

arXiv subjects

Qing Yu

Publications and source records attributed to Qing Yu.

At least 37 records · Page 2Linked to original sources

Causal Motion Diffusion Models for Autoregressive Motion Generation

Recent advances in motion diffusion models have substantially improved the realism of human motion synthesis. However, existing approaches either rely on full-sequence diffusion models with bidirectional generation, which limits temporal causality and real-time applicability, or autoregressive models that suffer from instability and cumulative errors. In this work, we present Causal Motion Diffusion Models (CMDM), a unified framework for autoregressive motion generation based on a causal diffusion transformer that operates in a semantically aligned latent space. CMDM builds upon a Motion-Language-Aligned Causal VAE (MAC-VAE), which encodes motion sequences into temporally causal latent representations. On top of this latent representation, an autoregressive diffusion transformer is trained using causal diffusion forcing to perform temporally ordered denoising across motion frames. To achieve fast inference, we introduce a frame-wise sampling schedule with causal uncertainty, where each subsequent frame is predicted from partially denoised previous frames. The resulting framework supports high-quality text-to-motion generation, streaming synthesis, and long-horizon motion generation at interactive rates. Experiments on HumanML3D and SnapMoGen demonstrate that CMDM outperforms existing diffusion and autoregressive models in both semantic fidelity and temporal smoothness, while substantially reducing inference latency.

cs.CV↗

ProjFlow: Projection Sampling with Flow Matching for Zero-Shot Exact Spatial Motion Control

Generating human motion with precise spatial control is a challenging problem. Existing approaches often require task-specific training or slow optimization, and enforcing hard constraints frequently disrupts motion naturalness. Building on the observation that many animation tasks can be formulated as a linear inverse problem, we introduce ProjFlow, a training-free sampler that achieves zero-shot, exact satisfaction of linear spatial constraints while preserving motion realism. Our key advance is a novel kinematics-aware metric that encodes skeletal topology. This metric allows the sampler to enforce hard constraints by distributing corrections coherently across the entire skeleton, avoiding the unnatural artifacts of naive projection. Furthermore, for sparse inputs, such as filling in long gaps between a few keyframes, we introduce a time-varying formulation using pseudo-observations that fade during sampling. Extensive experiments on representative applications, motion inpainting, and 2D-to-3D lifting, demonstrate that ProjFlow achieves exact constraint satisfaction and matches or improves realism over zero-shot baselines, while remaining competitive with training-based controllers.

cs.CV↗

Granular jamming and rheology in microgravity

Understanding how granular materials behave in low gravity is crucial for planetary science and space exploration. It can also help us understand granular phenomena usually hidden by gravity. On Earth, gravity dominates granular behavior, but disentangling its role from intrinsic particle interactions is challenging. We present a series of compression and shear experiments conducted in microgravity using the Center of Applied Space Technology and Microgravity (ZARM) drop tower and GraviTower Bremen (GTB). Our in-house developed experimental setup enables precise measurement of packing density and in-situ shear stress via a Taylor-Couette rheometer. We find that the jamming transition occurs at lower packing density in microgravity than on Earth, confirming that gravity promotes densification. Rheological measurements further reveal that in microgravity, the lack of a secondary force field and predominance of cohesive interparticle forces increase the stress needed for granular media to flow. These findings highlight gravity's dual role in enhancing both compaction and flow, and demonstrate the need for tailored granular models, valid in low- and microgravity environments.

cond-mat.soft↗

Multiscale spatiotemporal heterogeneity analysis of bike-sharing system's self-loop phenomenon: Evidence from Shanghai

Bike-sharing is an environmentally friendly shared mobility mode, but its self-loop phenomenon, where bikes are returned to the same station after several time usage, significantly impacts equity in accessing its services. Therefore, this study conducts a multiscale analysis with a spatial autoregressive model and double machine learning framework to assess socioeconomic features and geospatial location's impact on the self-loop phenomenon at metro stations and street scales. The results reveal that bike-sharing self-loop intensity exhibits significant spatial lag effect at street scale and is positively associated with residential land use. Marginal treatment effects of residential land use is higher on streets with middle-aged residents, high fixed employment, and low car ownership. The multimodal public transit condition reveals significant positive marginal treatment effects at both scales. To enhance bike-sharing cooperation, we advocate augmenting bicycle availability in areas with high metro usage and low bus coverage, alongside implementing adaptable redistribution strategies.

cs.LG↗

Who You Are Matters: Bridging Topics and Social Roles via LLM-Enhanced Logical Recommendation

Recommender systems filter contents/items valuable to users by inferring preferences from user features and historical behaviors. Mainstream approaches follow the learning-to-rank paradigm, which focus on discovering and modeling item topics (e.g., categories), and capturing user preferences on these topics based on historical interactions. However, this paradigm often neglects the modeling of user characteristics and their social roles, which are logical confounders influencing the correlated interest and user preference transition. To bridge this gap, we introduce the user role identification task and the behavioral logic modeling task that aim to explicitly model user roles and learn the logical relations between item topics and user social roles. We show that it is possible to explicitly solve these tasks through an efficient integration framework of Large Language Model (LLM) and recommendation systems, for which we propose TagCF. On the one hand, TagCF exploits the (Multi-modal) LLM's world knowledge and logic inference ability to extract realistic tag-based virtual logic graphs that reveal dynamic and expressive knowledge of users, refining our understanding of user behaviors. On the other hand, TagCF presents empirically effective integration modules that take advantage of the extracted tag-logic information, augmenting the recommendation performance. We conduct both online experiments and offline experiments with industrial and public datasets as verification of TagCF's effectiveness, and we empirically show that the user role modeling strategy is potentially a better choice than the modeling of item topics. Additionally, we provide evidence that the extracted logic graphs are empirically a general and transferable knowledge that can benefit a wide range of recommendation tasks. Our code is available in https://github.com/Code2Q/TagCF.

cs.IR↗

Fabrication and characterization of AlMn alloy superconducting films for 0vbb experiments

Neutrinoless double-beta decay (0vbb) experiments constitute a pivotal probe for elucidating the characteristics of neutrinos and further discovering new physics. Compared to the neutron transmutation doped germanium thermistors (NTD-Ge) used in 0vbb experiments such as CUORE, transition edge sensors (TES) theoretically have a relatively faster response time and higher energy resolution. These make TES detectors good choice for next generation 0vbb experiments. In this paper, AlMn alloy superconducting films, the main components of TES, were prepared and studied. The relationship between critical temperature (Tc) and annealing temperature was established, and the impact of magnetic field on Tc was tested. The experimental results demonstrate that the Tc of AlMn film can be tuned in the required range of 10 - 20 mK by using the above methods, which is a key step for the application of AlMn TES in 0vbb experiment. In the test range, the Tc of AlMn film is sensitive to out-of-plane magnetic field but not to the in-plane magnetic field. Furthermore, we find that a higher annealing temperature results in a more uniform distribution of Mn ions in depth, which opens a new avenue for elucidating the underlying mechanism for tuning Tc.

hep-ex↗

WLFM: A Well-Logs Foundation Model for Multi-Task and Cross-Well Geological Interpretation

Well-log interpretation is fundamental for subsurface characterization but remains challenged by heterogeneous tool responses, noisy signals, and limited labels. We propose WLFM, a foundation model pretrained on multi-curve logs from 1200 wells, comprising three stages: tokenization of log patches into geological tokens, self-supervised pretraining with masked-token modeling and stratigraphy-aware contrastive learning, and multi-task adaptation with few-shot fine-tuning. WLFM consistently outperforms state-of-the-art baselines, achieving 0.0041 MSE in porosity estimation and 74.13\% accuracy in lithology classification, while WLFM-Finetune further improves to 0.0038 MSE and 78.10\% accuracy. Beyond predictive accuracy, WLFM exhibits emergent layer-awareness, learns a reusable geological vocabulary, and reconstructs masked curves with reasonable fidelity, though systematic offsets are observed in shallow and ultra-deep intervals. Although boundary detection is not explicitly evaluated here, clustering analyses suggest strong potential for future extension. These results establish WLFM as a scalable, interpretable, and transferable backbone for geological AI, with implications for multi-modal integration of logs, seismic, and textual data.

cs.LG↗

PINO: Person-Interaction Noise Optimization for Long-Duration and Customizable Motion Generation of Arbitrary-Sized Groups

Generating realistic group interactions involving multiple characters remains challenging due to increasing complexity as group size expands. While existing conditional diffusion models incrementally generate motions by conditioning on previously generated characters, they rely on single shared prompts, limiting nuanced control and leading to overly simplified interactions. In this paper, we introduce Person-Interaction Noise Optimization (PINO), a novel, training-free framework designed for generating realistic and customizable interactions among groups of arbitrary size. PINO decomposes complex group interactions into semantically relevant pairwise interactions, and leverages pretrained two-person interaction diffusion models to incrementally compose group interactions. To ensure physical plausibility and avoid common artifacts such as overlapping or penetration between characters, PINO employs physics-based penalties during noise optimization. This approach allows precise user control over character orientation, speed, and spatial relationships without additional training. Comprehensive evaluations demonstrate that PINO generates visually realistic, physically coherent, and adaptable multi-person interactions suitable for diverse animation, gaming, and robotics applications.

cs.CV↗

Generalized Out-of-Distribution Detection and Beyond in Vision Language Model Era: A Survey

Detecting out-of-distribution (OOD) samples is crucial for ensuring the safety of machine learning systems and has shaped the field of OOD detection. Meanwhile, several other problems are closely related to OOD detection, including anomaly detection (AD), novelty detection (ND), open set recognition (OSR), and outlier detection (OD). To unify these problems, a generalized OOD detection framework was proposed, taxonomically categorizing these five problems. However, Vision Language Models (VLMs) such as CLIP have significantly changed the paradigm and blurred the boundaries between these fields, again confusing researchers. In this survey, we first present a generalized OOD detection v2, encapsulating the evolution of these fields in the VLM era. Our framework reveals that, with some field inactivity and integration, the demanding challenges have become OOD detection and AD. Then, we highlight the significant shift in the definition, problem settings, and benchmarks; we thus feature a comprehensive review of the methodology for OOD detection and related tasks to clarify their relationship to OOD detection. Finally, we explore the advancements in the emerging Large Vision Language Model (LVLM) era, such as GPT-4V. We conclude with open challenges and future directions. The resource is available at https://github.com/AtsuMiyai/Awesome-OOD-VLM.

cs.CV↗

Unsolvable Problem Detection: Robust Understanding Evaluation for Large Multimodal Models

This paper introduces a novel task to evaluate the robust understanding capability of Large Multimodal Models (LMMs), termed $\textbf{Unsolvable Problem Detection (UPD)}$. Multiple-choice question answering (MCQA) is widely used to assess the understanding capability of LMMs, but it does not guarantee that LMMs truly comprehend the answer. UPD assesses the LMM's ability to withhold answers when encountering unsolvable problems of MCQA, verifying whether the model truly understands the answer. UPD encompasses three problems: Absent Answer Detection (AAD), Incompatible Answer Set Detection (IASD), and Incompatible Visual Question Detection (IVQD), covering unsolvable cases like answer-lacking or incompatible choices and image-question mismatches. For the evaluation, we introduce the MM-UPD Bench, a benchmark for assessing performance across various ability dimensions. Our experiments reveal that even most LMMs, which demonstrate adequate performance on existing benchmarks, struggle significantly with MM-UPD, underscoring a novel aspect of trustworthiness that current benchmarks have overlooked. A detailed analysis shows that LMMs have different bottlenecks and chain-of-thought and self-reflection improved performance for LMMs with the bottleneck in their LLM capability. We hope our insights will enhance the broader understanding and development of more reliable LMMs. The code is available at https://github.com/AtsuMiyai/UPD.

cs.CV↗

Updated Determination of Ellis-Jaffe Sum Rules up to $\rm N^{3}LO$ QCD corrections

In this paper, we explore the properties of the Ellis-Jaffe Sum Rule (EJSR) by employing the Principle of Maximum Conformality (PMC) approach to address its perturbative part up to next-to-next-to-next-to-leading order ($\rm N^{3}LO$) QCD contributions. By applying the PMC, we achieve a precise perturbative QCD prediction for the EJSR, free from conventional ambiguities associated with the renormalization scale choices. Considering the presence of the $α_s$ Landau pole near the asymptotic scale, we incorporate the low-energy $α_s$ model based on analytic perturbation theory (APT) to refine the EJSR behavior in the infrared region. By combining the PMC approach with the low-energy APT model, the agreement between theoretical calculations and experimental measurements of EJSR is significantly improved, as evidenced by the reduced discrepancy from $χ^{2}/d.o. f|_{\rm Conv.}=1.86$ to $χ^{2}/d.o. f|_{\rm PMC}=1.19$, thereby validating the effectiveness of our approach.

hep-ph↗

A Benchmark and Evaluation for Real-World Out-of-Distribution Detection Using Vision-Language Models

Out-of-distribution (OOD) detection is a task that detects OOD samples during inference to ensure the safety of deployed models. However, conventional benchmarks have reached performance saturation, making it difficult to compare recent OOD detection methods. To address this challenge, we introduce three novel OOD detection benchmarks that enable a deeper understanding of method characteristics and reflect real-world conditions. First, we present ImageNet-X, designed to evaluate performance under challenging semantic shifts. Second, we propose ImageNet-FS-X for full-spectrum OOD detection, assessing robustness to covariate shifts (feature distribution shifts). Finally, we propose Wilds-FS-X, which extends these evaluations to real-world datasets, offering a more comprehensive testbed. Our experiments reveal that recent CLIP-based OOD detection methods struggle to varying degrees across the three proposed benchmarks, and none of them consistently outperforms the others. We hope the community goes beyond specific benchmarks and includes more challenging conditions reflecting real-world scenarios. The code is https://github.com/hoshi23/OOD-X-Benchmarks.

cs.CV↗

Nonlinear Stability of Large-Period Traveling Waves Bifurcating from the Heteroclinic Loop in the FitzHugh-Nagumo Equation

A wave front and a wave back that spontaneously connect two hyperbolic equilibria, known as a heteroclinic wave loop, give rise to periodic waves with arbitrarily large spatial periods through the heteroclinic bifurcation. The nonlinear stability of these periodic waves is established in the setting of the FitzHugh-Nagumo equation, which is a well-known reaction-diffusion model with degenerate diffusion. First, for general systems, we give the expressions of spectra with small modulus for linearized operators about these periodic waves via the Lyapunov-Schmidt reduction and the Lin-Sandstede method. Second, applying these spectral results to the FitzHugh-Nagumo equation, we establish their diffusive spectral stability. Finally, we consider the nonlinear stability of these periodic waves against localized perturbations. We introduce a spatiotemporal phase modulation $φ$, and couple it with the associated modulated perturbation $\mathbf{V}$ along with the unmodulated perturbation $\mathbf{\widetilde{V}}$ to close a nonlinear iteration argument.

math.AP↗

Chiral perturbation theory and Bose-Einstein condensation in QCD

We present recent results in three-flavor chiral perturbation theory at finite isospin $μ_I$ and strangeness $μ_s$ chemical potentials at zero temperature. The phase diagram to ${\cal O}(p^2)$ in the $μ_I$--$μ_S$ plane is mapped out with and without electromagnetic effects. The phase diagram consists of a vacuum phase and three Bose-condensed phases with condensates of $π^{\pm}$, $K^{\pm}$, and $K^{0}/\bar{K}^0$, respectively. Including electromagnetic interactions, the Bose-condensed phases become Higgs phases via the Higgs mechanism. The tree-level spectrum for the mesons and gauge bosons is also derived. We calculate the pressure, energy density, isospin density, and speed of sound in the pion-condensed phase to ${\cal O}(p^4)$ for three-flavor $χ$PT. The results are compared with recent lattice simulations and the agreement is very good for isospin chemical potentials up to approximately 200 MeV. Moreover, by integrating out the $s$-quark, we show that the thermodynamic quantities can be mapped onto their two-flavor counterparts with renormalized parameters. %to ${\cal O}(p^6)$ for two-flavor $χ$PT in the chiral limit. We also consider the nonrelativistic limit. It is shown that the energy density can be matched onto the classic result by Lee, Huang and Yang (LHY) for a dilute Bose, with an $s$-wave scattering length that includes radiative corrections. The breaking of the $U(1)$ symmetry in the Bose-condensed phases gives rise to a Goldstone bosons, whose dispersion is linear for momenta $p\llμ_I$. In this regime, we use Son's prescription to construct an effective theory for the Goldstone field which is valid in this regime. It is shown that its damping rate is of order $p^5$. This result is in agreement with Beliav's for a dilute Bose gas.

hep-ph↗

Determination of $α_s(M_Z)$ via a high-precision effective coupling $α^{g_1}_s(Q)$

We propose a novel method to determine the strong coupling of quantum chromodynamics (QCD) and fix its running behavior at all scales by using the Bjorken sum rules (BSR). The BSR defines an effective coupling $α^{g_1}_s(Q)$ which includes the nonperturbative high-twist corrections and perturbative QCD (pQCD) corrections to the leading-twist part. For the leading-twist part of $α^{g_1}_s(Q)$, we adopt the infinite-order scale-setting procedure of the principle of maximum conformality ($\rm{PMC}_\infty$) to deal with its pQCD corrections, which reveals the intrinsic conformality of series and eliminates conventional renormalization scheme-and-scale ambiguities. Using the $\rm{PMC}_\infty$ approach, we not only eliminate \textit{the first kind of residual scale dependence} due to uncalculated higher-order terms, but also resolve the previous ``self-consistence problem". The holographic light-front QCD model is used for $α^{g_1}_s(Q)$ in the infrared region, which also reveals a conformal behavior at $Q\to 0$. As a combination, we obtain a precise $α^{g_1}_s(Q)$ at all scales, which matches well with the known experimental data with $p$-value $\sim99\%$, we determine the strong coupling constant at the critical scale $M_Z$, $α_s(M_Z)=0.1191\pm{0.0012}\mp0.0006$, where the first error comes from $Δκ$ of LFHQCD model and the second error is from \textit{the second kind of residual scale dependence} that is negligible.

hep-ph↗

GL-MCM: Global and Local Maximum Concept Matching for Zero-Shot Out-of-Distribution Detection

Zero-shot out-of-distribution (OOD) detection is a task that detects OOD images during inference with only in-distribution (ID) class names. Existing methods assume ID images contain a single, centered object, and do not consider the more realistic multi-object scenarios, where both ID and OOD objects are present. To meet the needs of many users, the detection method must have the flexibility to adapt the type of ID images. To this end, we present Global-Local Maximum Concept Matching (GL-MCM), which incorporates local image scores as an auxiliary score to enhance the separability of global and local visual features. Due to the simple ensemble score function design, GL-MCM can control the type of ID images with a single weight parameter. Experiments on ImageNet and multi-object benchmarks demonstrate that GL-MCM outperforms baseline zero-shot methods and is comparable to fully supervised methods. Furthermore, GL-MCM offers strong flexibility in adjusting the target type of ID images. The code is available via https://github.com/AtsuMiyai/GL-MCM.

cs.CV↗

Global Estimation of Building-Integrated Facade and Rooftop Photovoltaic Potential by Integrating 3D Building Footprint and Spatio-Temporal Datasets

This research tackles the challenges of estimating Building-Integrated Photovoltaics (BIPV) potential across various temporal and spatial scales, accounting for different geographical climates and urban morphology. We introduce a holistic methodology for evaluating BIPV potential, integrating 3D building footprint models with diverse meteorological data sources to account for dynamic shadow effects. The approach enables the assessment of PV potential on facades and rooftops at different levels-individual buildings, urban blocks, and cities globally. Through an analysis of 120 typical cities, we highlight the importance of 3D building forms, cityscape morphology, and geographic positioning in measuring BIPV potential at various levels. In particular, our simulation study reveals that among cities with optimal facade PV performance, the average ratio of facade PV potential to rooftop PV potential is approximately 68.2%. Additionally, approximately 17.5% of the analyzed samples demonstrate even higher facade PV potentials compared to rooftop installations. This finding underscores the strategic value of incorporating facade PV applications into urban sustainable energy systems.

cs.IR↗

Chronologically Accurate Retrieval for Temporal Grounding of Motion-Language Models

With the release of large-scale motion datasets with textual annotations, the task of establishing a robust latent space for language and 3D human motion has recently witnessed a surge of interest. Methods have been proposed to convert human motion and texts into features to achieve accurate correspondence between them. Despite these efforts to align language and motion representations, we claim that the temporal element is often overlooked, especially for compound actions, resulting in chronological inaccuracies. To shed light on the temporal alignment in motion-language latent spaces, we propose Chronologically Accurate Retrieval (CAR) to evaluate the chronological understanding of the models. We decompose textual descriptions into events, and prepare negative text samples by shuffling the order of events in compound action descriptions. We then design a simple task for motion-language models to retrieve the more likely text from the ground truth and its chronologically shuffled version. CAR reveals many cases where current motion-language models fail to distinguish the event chronology of human motion, despite their impressive performance in terms of conventional evaluation metrics. To achieve better temporal alignment between text and motion, we further propose to use these texts with shuffled sequence of events as negative samples during training to reinforce the motion-language models. We conduct experiments on text-motion retrieval and text-to-motion generation using the reinforced motion-language models, which demonstrate improved performance over conventional approaches, indicating the necessity to consider temporal elements in motion-language alignment.

cs.CV↗