arXiv subjects

Yong Chen

Publications and source records attributed to Yong Chen.

At least 91 records · Page 5Linked to original sources

arXiv2025

Chain-of-Conceptual-Thought Elicits Daily Conversation in Large Language Models

Chain-of-Thought (CoT) is widely applied to enhance the LLM capability in math, coding and reasoning tasks. However, its performance is limited for open-domain tasks, when there are no clearly defined reasoning steps or logical transitions. To mitigate such challenges, we propose a new prompt-based paradigm called Chain of Conceptual Thoughts (CoCT), which suggests the LLM first to produce the tag of concepts, then complete the detailed content following the concept. To encourage this hierarchical way of thinking, we implement the concepts with emotions, strategies and topics. We experiment with this paradigm in daily and emotional support conversations, covering tasks with both in-domain and out-of-domain concept settings. Automatic, human, and LLM-based evaluations reveal that CoCT surpasses several prompt-based baselines such as self-refine, ECoT, SoT and RAG, suggesting a potential solution of LLM prompting paradigm for a wider scope of tasks.

cs.CL↗

arXiv2025

Codebook-Centric Deep Hashing: End-to-End Joint Learning of Semantic Hash Centers and Neural Hash Function

Hash center-based deep hashing methods improve upon pairwise or triplet-based approaches by assigning fixed hash centers to each class as learning targets, thereby avoiding the inefficiency of local similarity optimization. However, random center initialization often disregards inter-class semantic relationships. While existing two-stage methods mitigate this by first refining hash centers with semantics and then training the hash function, they introduce additional complexity, computational overhead, and suboptimal performance due to stage-wise discrepancies. To address these limitations, we propose $\textbf{Center-Reassigned Hashing (CRH)}$, an end-to-end framework that $\textbf{dynamically reassigns hash centers}$ from a preset codebook while jointly optimizing the hash function. Unlike previous methods, CRH adapts hash centers to the data distribution $\textbf{without explicit center optimization phases}$, enabling seamless integration of semantic relationships into the learning process. Furthermore, $\textbf{a multi-head mechanism}$ enhances the representational capacity of hash centers, capturing richer semantic structures. Extensive experiments on three benchmarks demonstrate that CRH learns semantically meaningful hash centers and outperforms state-of-the-art deep hashing methods in retrieval tasks.

cs.CV↗

arXiv2025

An asymptotic expansion of the norm of $e^{-|{t-s}|}{1}_{\{0\le s,t\le T\}}$ in the canonical Hilbert space of fractional Brownian motion

Using the inner product formula of the canonical Hilbert space of fractional Brownian motion on an interval $[0,T]$ with Hurst parameter $H\in (0,1)$ given by Alazemi et al., we show the asymptotic expansion of the norm of $f_T(s,t):=e^{-|t-s|}\mathbf{1}_{\{0\le s,t\le T\}}$ up to the term $T^{4H-4}$. As applications, we show that the existence of the oblique asymptote of the norm $\frac12\|f_T\|^2_{\mathfrak{H}^{\otimes2}}$ if and only if $H\in (0,\frac12]$ and that we obtain a sharp upper bound of the difference $\left|\frac{1}{2 {T}} \|f_T\|_{\mathfrak{H}^{\otimes 2}}^2-σ^2\right|$ for $H\in (0,\frac34)$ which implies two significant estimates concerning to an ergodic fractional Ornstein-Uhlenbeck process, where $σ^2$ is the slope of the oblique asymptote.

math.PR↗

arXiv2025

Machine-Learning-Assisted Comparison of Regression Functions

We revisit the classical problem of comparing regression functions, a fundamental question in statistical inference with broad relevance to modern applications such as data integration, transfer learning, and causal inference. Existing approaches typically rely on smoothing techniques and are thus hindered by the curse of dimensionality. We propose a generalized notion of kernel-based conditional mean dependence that provides a new characterization of the null hypothesis of equal regression functions. Building on this reformulation, we develop two novel tests that leverage modern machine learning methods for flexible estimation. We establish the asymptotic properties of the test statistics, which hold under both fixed- and high-dimensional regimes. Unlike existing methods that often require restrictive distributional assumptions, our framework only imposes mild moment conditions. The efficacy of the proposed tests is demonstrated through extensive numerical studies.

stat.ME↗

arXiv2025

Berry-Esseen bound for the Moment Estimation of the fractional Ornstein-Uhlenbeck model under fixed step size discrete observations

Let the Ornstein-Uhlenbeck process $\{X_t,\,t\geq 0\}$ driven by a fractional Brownian motion $B^H$ described by $d X_t=-θX_t dt+ d B_t^H,\, X_0=0$ with known parameter $H\in (0,\frac34)$ be observed at discrete time instants $t_k=kh, k=1,2,\dots, n $. If $θ>0$ and if the step size $h>0$ is arbitrarily fixed, we derive Berry-Esséen bound for the ergodic type estimator (or say the moment estimator) $\hatθ_n$, i.e., the Kolmogorov distance between the distribution of $\sqrt{n}(\hatθ_n-θ)$ and its limit distribution is bounded by a constant $C_{θ, H,h}$ times $n^{-\frac12}$ and $ n^{4H-3}$ when $H\in (0,\,\frac58]$ and $H\in (\frac58,\,\frac34)$, respectively. This result greatly improve the previous result in literature where $h$ is forced to go zero. Moreover, we extend the Berry-Esseen bound to the Ornstein-Uhlenbeck model driven by a lot of Gaussian noises such as the sub-bifractional Brownian motion and others. A few ideas of the present paper come from Haress and Hu (2021), Sottinen and Viitasaari (2018), and Chen and Zhou (2021).

math.PR↗

arXiv2025

FAME: Adaptive Functional Attention with Expert Routing for Function-on-Function Regression

Functional data play a pivotal role across science and engineering, yet their infinite-dimensional nature makes representation learning challenging. Conventional statistical models depend on pre-chosen basis expansions or kernels, limiting the flexibility of data-driven discovery, while many deep-learning pipelines treat functions as fixed-grid vectors, ignoring inherent continuity. In this paper, we introduce Functional Attention with a Mixture-of-Experts (FAME), an end-to-end, fully data-driven framework for function-on-function regression. FAME forms continuous attention by coupling a bidirectional neural controlled differential equation with MoE-driven vector fields to capture intra-functional continuity, and further fuses change to inter-functional dependencies via multi-head cross attention. Extensive experiments on synthetic and real-world functional-regression benchmarks show that FAME achieves state-of-the-art accuracy, strong robustness to arbitrarily sampled discrete observations of functions.

cs.LG↗

arXiv2025

Making Language Model a Hierarchical Classifier

Decoder-only language models, such as GPT and LLaMA, generally decode on the last layer. Motivated by human's hierarchical thinking capability, we propose that a hierarchical decoder architecture could be built with different layers decoding texts simultaneously. Due to limited time and computationally resources, we choose to adapt a pretrained language model into this form of hierarchical decoder. Language heads of the last layer are copied to different selected intermediate layers, and fine-tuned with different task inputs. By thorough experiments, we validate that these selective intermediate layers could be adapted to speak meaningful and reasonable contents, and this paradigm of hierarchical decoder can obtain state-of-the-art performances on multiple tasks such as hierarchical text classification, classification-guided generation, and hierarchical text generation. HdLM outperforms all baselines on WoS, DBpedia, ESconv, EmpatheticDialogues, and several cognitive tests. We also provide thorough theoretical analysis to validate the convergence and computational savings of our methodology. This study suggests the possibility of a generalized hierarchical reasoner, pretraining from scratch.

cs.CL↗

arXiv2025

Collaborative Indirect Treatment Comparisons with Multiple Distributed Single-arm Trials

When randomized controlled trials are impractical or unethical to simultaneously compare multiple treatments, indirect treatment comparisons using single-arm trials offer valuable evidence for health technology assessments, especially for rare diseases and early-phase drug development. In practice, each sponsor conducts a single-arm trial on its own drug with restricted data-sharing and targets effects in its trial population, which can lead to unfair comparisons. This motivates methods for fair treatment comparisons across a range of target populations in distributed networks of single-arm trials sharing only aggregated data. Existing federated methods, which assume at least one site contains all treatments and allow pooling of treatment groups within the same site, cannot address this problem. We propose a novel distributed augmented calibration weighting (DAC) method to simultaneously estimate the pairwise average treatment effects (ATEs) across all trial population combinations in a distributed network of multiple single-arm trials. Using two communication rounds, DAC estimators balance covariates via calibration weighting, incorporate flexible nuisance parameter estimation, achieve doubly robust consistency, and yield results identical to pooled-data analysis. When nuisance parameters are estimated parametrically, DAC estimators are enhanced to achieve doubly robust inference with minimal squared first-order asymptotic bias. Simulations and a real-data application show good performance.

stat.ME↗

arXiv2025

Dream to Chat: Model-based Reinforcement Learning on Dialogues with User Belief Modeling

World models have been widely utilized in robotics, gaming, and auto-driving. However, their applications on natural language tasks are relatively limited. In this paper, we construct the dialogue world model, which could predict the user's emotion, sentiment, and intention, and future utterances. By defining a POMDP, we argue emotion, sentiment and intention can be modeled as the user belief and solved by maximizing the information bottleneck. By this user belief modeling, we apply the model-based reinforcement learning framework to the dialogue system, and propose a framework called DreamCUB. Experiments show that the pretrained dialogue world model can achieve state-of-the-art performances on emotion classification and sentiment identification, while dialogue quality is also enhanced by joint training of the policy, critic and dialogue world model. Further analysis shows that this manner holds a reasonable exploration-exploitation balance and also transfers well to out-of-domain scenarios such as empathetic dialogues.

cs.CL↗

arXiv2025

The soft X-ray transient EP241021a: A cosmic explosion with a complex off-axis jet and cocoon from a massive progenitor

X-ray flashes (XRFs) are fast X-ray transients thought to be softer analogs of gamma-ray bursts (GRBs). With its soft X-ray sensitivity, the Einstein Probe (EP) provides a unique opportunity to study these events. We report multiwavelength observations of EP241021a, a soft X-ray transient detected by EP, and interpret its afterglow in the context of leading XRF models. The prompt emission was observed by EP-WXT and Fermi-GBM, followed by a broad campaign across radio (uGMRT, ATCA, e-MERLIN, ALMA), optical (LBT, GTC, CAHA), and X-rays (EP-FXT). Light curves and spectra were analyzed with both empirical and physical models of GRBs and spherical expansions (both nonrelativistic and mildly relativistic cocoons). The afterglow shows multiple components, consistent with a structured jet interacting with a complex environment. The early optical and X-ray decline is explained by wide, low-Lorentz-factor ($γ\sim 40$) wings, while a rebrightening at approximately 7 days arises from the off-axis jet core. Radio data require an additional mildly relativistic cocoon ($γ\sim 2$), and a late (70 days) spectral component peaking at 50 GHz suggests a second, slower cocoon ($γ\sim 1$).

astro-ph.HE↗

arXiv2025

Qianfan-VL: Domain-Enhanced Universal Vision-Language Models

We present Qianfan-VL, a series of multimodal large language models ranging from 3B to 70B parameters, achieving state-of-the-art performance through innovative domain enhancement techniques. Our approach employs multi-stage progressive training and high-precision data synthesis pipelines, which prove to be critical technologies for enhancing domain-specific capabilities while maintaining strong general performance. Qianfan-VL achieves comparable results to leading open-source models on general benchmarks, with state-of-the-art performance on benchmarks such as CCBench, SEEDBench IMG, ScienceQA, and MMStar. The domain enhancement strategy delivers significant advantages in OCR and document understanding, validated on both public benchmarks (OCRBench 873, DocVQA 94.75%) and in-house evaluations. Notably, Qianfan-VL-8B and 70B variants incorporate long chain-of-thought capabilities, demonstrating superior performance on mathematical reasoning (MathVista 78.6%) and logical inference tasks. All models are trained entirely on Baidu's Kunlun P800 chips, validating the capability of large-scale AI infrastructure to train SOTA-level multimodal models with over 90% scaling efficiency on 5000 chips for a single task. This work establishes an effective methodology for developing domain-enhanced multimodal models suitable for diverse enterprise deployment scenarios.

cs.CV↗

arXiv2025

YuE: Scaling Open Foundation Models for Long-Form Music Generation

We tackle the task of long-form music generation--particularly the challenging \textbf{lyrics-to-song} problem--by introducing YuE, a family of open foundation models based on the LLaMA2 architecture. Specifically, YuE scales to trillions of tokens and generates up to five minutes of music while maintaining lyrical alignment, coherent musical structure, and engaging vocal melodies with appropriate accompaniment. It achieves this through (1) track-decoupled next-token prediction to overcome dense mixture signals, (2) structural progressive conditioning for long-context lyrical alignment, and (3) a multitask, multiphase pre-training recipe to converge and generalize. In addition, we redesign the in-context learning technique for music generation, enabling versatile style transfer (e.g., converting Japanese city pop into an English rap while preserving the original accompaniment) and bidirectional generation. Through extensive evaluation, we demonstrate that YuE matches or even surpasses some of the proprietary systems in musicality and vocal agility. In addition, fine-tuning YuE enables additional controls and enhanced support for tail languages. Furthermore, beyond generation, we show that YuE's learned representations can perform well on music understanding tasks, where the results of YuE match or exceed state-of-the-art methods on the MARBLE benchmark. Keywords: lyrics2song, song generation, long-form, foundation model, music generation

eess.AS↗

arXiv2025

Empowering Clinical Trial Design through AI: A Randomized Evaluation of PowerGPT

Sample size calculations for power analysis are critical for clinical research and trial design, yet their complexity and reliance on statistical expertise create barriers for many researchers. We introduce PowerGPT, an AI-powered system integrating large language models (LLMs) with statistical engines to automate test selection and sample size estimation in trial design. In a randomized trial to evaluate its effectiveness, PowerGPT significantly improved task completion rates (99.3% vs. 88.9% for test selection, 99.3% vs. 77.8% for sample size calculation) and accuracy (94.1% vs. 55.4% in sample size estimation, p < 0.001), while reducing average completion time (4.0 vs. 9.3 minutes, p < 0.001). These gains were consistent across various statistical tests and benefited both statisticians and non-statisticians as well as bridging expertise gaps. Already under deployment across multiple institutions, PowerGPT represents a scalable AI-driven approach that enhances accessibility, efficiency, and accuracy in statistical power analysis for clinical research.

cs.AI↗

arXiv2025

Timing and spectral studies of SRGA J144459.2$-$604207 with NICER, Einstein Probe, IXPE, NuSTAR, Insight-HXMT and INTEGRAL during its 2024 outburst

SRGA J144459.2$-$604207 is a newly confirmed accreting millisecond X-ray pulsar and type I X-ray burster. We present the broadband X-ray timing and spectral behaviors of SRGA J144459.2$-$604207 during its 2024 outburst. The data were collected from NICER, Einstein Probe, IXPE, Insight-HXMT, NuSTAR and INTEGRAL observations. X-ray pulsations have been detected for the 1.5--90 keV energy range throughout the `ON' phase of the outburst from MJD $\sim 60355-60385$. We refined the orbital and spin ephemerides assuming a circular orbit, and found that the pulsar was in a spin-up state during MJD $\sim$ 60361--60377 showing a significant spin-up rate $\dotν$ of $(3.15\pm 0.36)\times10^{-13}~{\rm Hz~s^{-1}}$. Around MJD $\sim 60377$ a swing was detected in the spin evolution accompanied by significantly enhanced pulsed emission. We studied the pulse profile morphology during the X-ray bursts as observed by Insight-HXMT, IXPE and NuSTAR. During the bursts, pulsations were detected across the 2--60 keV with shapes broadly consistent with those observed for the persistent emission. We found, however, that the `burst' pulse profiles exhibit significant phase offsets relative to the pre- and post-burst profiles. These offsets systematically decrease with increasing energy, $Δϕ\approx0.15$, 0.11 and 0.02 for IXPE, Insight-HXMT ME and HE in 2--8, 5--30 and 20--60 keV, respectively, and $Δϕ\approx 0.21$, 0.10 and 0.07 for NuSTAR in 3--10, 20--35 and 35--60 keV, respectively, compared to the pre- and post-burst profiles. We performed a joint spectral analysis of quasi-simultaneous NICER, NuSTAR, and Insight-HXMT data for two epochs. The resulting spectra from both observations were consistent and well-described by an absorbed thermal Comptonization model, nthcomp, plus relativistic reflection, relxillCp.

astro-ph.HE↗

arXiv2025

Maximizing social welfare among EF1 allocations at the presence of two types of agents

We study the fair allocation of indivisible items to $n$ agents to maximize the utilitarian social welfare, where the fairness criterion is envy-free up to one item and there are only two different utility functions shared by the agents. We present a $2$-approximation algorithm when the two utility functions are normalized, improving the previous best ratio of $16 \sqrt{n}$ shown for general normalized utility functions; thus this constant ratio approximation algorithm confirms the APX-completeness in this special case previously shown APX-hard. When there are only three agents, i.e., $n = 3$, the previous best ratio is $3$ shown for general utility functions, and we present an improved and tight $\frac 53$-approximation algorithm when the two utility functions are normalized, and a best possible and tight $2$-approximation algorithm when the two utility functions are unnormalized.

cs.GT↗

arXiv2025

The enhanced X-ray Timing and Polarimetry mission -- eXTP for launch in 2030

In this paper we present the current status of the enhanced X-ray Timing and Polarimetry mission, which has been fully approved for launch in 2030. eXTP is a space science mission designed to study fundamental physics under extreme conditions of matter density, gravity, and magnetism. The mission aims at determining the equation of state of matter at supra-nuclear density, measuring the effects of quantum electro-dynamics, and understanding the dynamics of matter in strong-field gravity. In addition to investigating fundamental physics, the eXTP mission is poised to become a leading observatory for time-domain and multi-messenger astronomy in the 2030's, as well as providing observations of unprecedented quality on a variety of galactic and extragalactic objects. After briefly introducing the history and a summary of the scientific objectives of the eXTP mission, this paper presents a comprehensive overview of: 1) the cutting-edge technology, technical specifications, and anticipated performance of the mission's scientific instruments; 2) the full mission profile, encompassing spacecraft design, operational capabilities, and ground segment infrastructure.

astro-ph.HE↗

arXiv2025

DiffOSeg: Omni Medical Image Segmentation via Multi-Expert Collaboration Diffusion Model

Annotation variability remains a substantial challenge in medical image segmentation, stemming from ambiguous imaging boundaries and diverse clinical expertise. Traditional deep learning methods producing single deterministic segmentation predictions often fail to capture these annotator biases. Although recent studies have explored multi-rater segmentation, existing methods typically focus on a single perspective -- either generating a probabilistic ``gold standard'' consensus or preserving expert-specific preferences -- thus struggling to provide a more omni view. In this study, we propose DiffOSeg, a two-stage diffusion-based framework, which aims to simultaneously achieve both consensus-driven (combining all experts' opinions) and preference-driven (reflecting experts' individual assessments) segmentation. Stage I establishes population consensus through a probabilistic consensus strategy, while Stage II captures expert-specific preference via adaptive prompts. Demonstrated on two public datasets (LIDC-IDRI and NPC-170), our model outperforms existing state-of-the-art methods across all evaluated metrics. Source code is available at https://github.com/string-ellipses/DiffOSeg .

cs.CV↗

arXiv2025

FICGen: Frequency-Inspired Contextual Disentanglement for Layout-driven Degraded Image Generation

Layout-to-image (L2I) generation has exhibited promising results in natural domains, but suffers from limited generative fidelity and weak alignment with user-provided layouts when applied to degraded scenes (i.e., low-light, underwater). We primarily attribute these limitations to the "contextual illusion dilemma" in degraded conditions, where foreground instances are overwhelmed by context-dominant frequency distributions. Motivated by this, our paper proposes a new Frequency-Inspired Contextual Disentanglement Generative (FICGen) paradigm, which seeks to transfer frequency knowledge of degraded images into the latent diffusion space, thereby facilitating the rendering of degraded instances and their surroundings via contextual frequency-aware guidance. To be specific, FICGen consists of two major steps. Firstly, we introduce a learnable dual-query mechanism, each paired with a dedicated frequency resampler, to extract contextual frequency prototypes from pre-collected degraded exemplars in the training set. Secondly, a visual-frequency enhanced attention is employed to inject frequency prototypes into the degraded generation process. To alleviate the contextual illusion and attribute leakage, an instance coherence map is developed to regulate latent-space disentanglement between individual instances and their surroundings, coupled with an adaptive spatial-frequency aggregation module to reconstruct spatial-frequency mixed degraded representations. Extensive experiments on 5 benchmarks involving a variety of degraded scenarios-from severe low-light to mild blur-demonstrate that FICGen consistently surpasses existing L2I methods in terms of generative fidelity, alignment and downstream auxiliary trainability.

cs.CV↗