Searcharxiv⌕ Search

arXiv subjects

Xiang Chen

Publications and source records attributed to Xiang Chen.

At least 145 records · Page 8Linked to original sources
arXiv2026

The immediate effect of kangaroo mother care on Mother-infant inter-brain synchrony and infant brain function

Kangaroo mother care (KMC) is an intervention involving skin-to-skin contact that promotes physiological stability and supports long-term neurodevelopment in preterm infants. However, the underlying neurophysiological mechanisms remain unclear. We aimed to investigate the immediate effects of the first KMC on infants' brain function, mother-infant inter-brain synchrony, as well as their associations. Fifty-eight preterm infants (gestational age < 32 weeks or birth weight < 1500 g) and their mothers underwent synchronous dual-electroencephalography recording before and during the first KMC session. Infant brain function was assessed via power spectrum energy and graph theory-based network metrics, and mother-infant inter-brain synchrony was quantified using phase-locking value (PLV), from which inter-brain density and inter-brain strength were calculated. Correlation analyses were performed between infant intra-brain metrics and inter-brain synchrony indicators.During the first KMC, preterm infants showed enhanced theta, alpha, and beta power alongside reduced relative delta power, while brain network topological metrics remained stable. Concurrently, mother-infant inter-brain synchrony was significantly enhanced across all frequency bands, as evidenced by increased inter-brain density and strength (all p < .001). Furthermore, in the alpha band, inter-brain strength correlated positively with infant local efficiency and clustering coefficient, and in the beta band, it was positively correlated with infant small-worldness. The first KMC session can immediately enhance both preterm infant single-brain activity and mother-infant inter-brain synchrony. The strength of inter-brain synchrony is associated with the infant's intra-brain network organization, suggesting that KMC may promote intra-brain development in preterm infants via enhancing mother-infant inter-brain synchrony.

q-bio.NC↗
arXiv2026

Derain-Agent: A Plug-and-Play Agent Framework for Rainy Image Restoration

While deep learning has advanced single-image deraining, existing models suffer from a fundamental limitation: they employ a static inference paradigm that fails to adapt to the complex, coupled degradations (e.g., noise artifacts, blur, and color deviation) of real-world rain. Consequently, restored images often exhibit residual artifacts and inconsistent perceptual quality. In this work, we present Derain-Agent, a plug-and-play refinement framework that transitions deraining from static processing to dynamic, agent-based restoration. Derain-Agent equips a base deraining model with two core capabilities: 1) a Planning Network that intelligently schedules an optimal sequence of restoration tools for each instance, and 2) a Strength Modulation mechanism that applies these tools with spatially adaptive intensity. This design enables precise, region-specific correction of residual errors without the prohibitive cost of iterative search. Our method demonstrates strong generalization, consistently boosting the performance of state-of-the-art deraining models on both synthetic and real-world benchmarks.

cs.CV↗
arXiv2026

UHD Image Deblurring via Autoregressive Flow with Ill-conditioned Constraints

Ultra-high-definition (UHD) image deblurring poses significant challenges for UHD restoration methods, which must balance fine-grained detail recovery and practical inference efficiency. Although prominent discriminative and generative methods have achieved remarkable results, a trade-off persists between computational cost and the ability to generate fine-grained detail for UHD image deblurring tasks. To further alleviate these issues, we propose a novel autoregressive flow method for UHD image deblurring with an ill-conditioned constraint. Our core idea is to decompose UHD restoration into a progressive, coarse-to-fine process: at each scale, the sharp estimate is formed by upsampling the previous-scale result and adding a current-scale residual, enabling stable, stage-wise refinement from low to high resolution. We further introduce Flow Matching to model residual generation as a conditional vector field and perform few-step ODE sampling with efficient Euler/Heun solvers, enriching details while keeping inference affordable. Since multi-step generation at UHD can be numerically unstable, we propose an ill-conditioning suppression scheme by imposing condition-number regularization on a feature-induced attention matrix, improving convergence and cross-scale consistency. Our method demonstrates promising performance on blurred images at 4K (3840$\times$2160) or higher resolutions.

cs.CV↗
arXiv2026

UniRain: Unified Image Deraining with RAG-based Dataset Distillation and Multi-objective Reweighted Optimization

Despite significant progress has been made in image deraining, we note that most existing methods are often developed for only specific types of rain degradation and fail to generalize across diverse real-world rainy scenes. How to effectively model different rain degradations within a universal framework is important for real-world image deraining. In this paper, we propose UniRain, an effective unified image deraining framework capable of restoring images degraded by rain streak and raindrop under both daytime and nighttime conditions. To better enhance unified model generalization, we construct an intelligent retrieval augmented generation (RAG)-based dataset distillation pipeline that selects high-quality training samples from all public deraining datasets for better mixed training. Furthermore, we incorporate a simple yet effective multi-objective reweighted optimization strategy into the asymmetric mixture-of-experts (MoE) architecture to facilitate consistent performance and improve robustness across diverse scenes. Extensive experiments show that our framework performs favorably against the state-of-the-art models on our proposed benchmarks and multiple public datasets.

cs.CV↗
arXiv2026

ToProVAR: Efficient Visual Autoregressive Modeling via Tri-Dimensional Entropy-Aware Semantic Analysis and Sparsity Optimization

Visual Autoregressive(VAR) models enhance generation quality but face a critical efficiency bottleneck in later stages. In this paper, we present a novel optimization framework for VAR models that fundamentally differs from prior approaches such as FastVAR and SkipVAR. Instead of relying on heuristic skipping strategies, our method leverages attention entropy to characterize the semantic projections across different dimensions of the model architecture. This enables precise identification of parameter dynamics under varying token granularity levels, semantic scopes, and generation scales. Building on this analysis, we further uncover sparsity patterns along three critical dimensions-token, layer, and scale-and propose a set of fine-grained optimization strategies tailored to these patterns. Extensive evaluation demonstrates that our approach achieves aggressive acceleration of the generation process while significantly preserving semantic fidelity and fine details, outperforming traditional methods in both efficiency and quality. Experiments on Infinity-2B and Infinity-8B models demonstrate that ToProVAR achieves up to 3.4x acceleration with minimal quality loss, effectively mitigating the issues found in prior work. Our code will be made publicly available.

cs.CV↗
arXiv2026

CREM: Compression-Driven Representation Enhancement for Multimodal Retrieval and Comprehension

Multimodal Large Language Models (MLLMs) have shown remarkable success in comprehension tasks such as visual description and visual question answering. However, their direct application to embedding-based tasks like retrieval remains challenging due to the discrepancy between output formats and optimization objectives. Previous approaches often employ contrastive fine-tuning to adapt MLLMs for retrieval, but at the cost of losing their generative capabilities. We argue that both generative and embedding tasks fundamentally rely on shared cognitive mechanisms, specifically cross-modal representation alignment and contextual comprehension. To this end, we propose CREM (Compression-driven Representation Enhanced Model), with a unified framework that enhances multimodal representations for retrieval while preserving generative ability. Specifically, we introduce a compression-based prompt design with learnable chorus tokens to aggregate multimodal semantics and a compression-driven training strategy that integrates contrastive and generative objectives through compression-aware attention. Extensive experiments demonstrate that CREM achieves state-of-the-art retrieval performance on MMEB while maintaining strong generative performance on multiple comprehension benchmarks. Our findings highlight that generative supervision can further improve the representational quality of MLLMs under the proposed compression-driven paradigm.

cs.CV↗
arXiv2026

STaRR: Spatial-Temporal Token-Dynamics-Aware Responsive Remasking for Diffusion Language Models

Diffusion Language Models (DLMs) enable parallel decoding via iterative denoising, where remasking strategies play a critical role in balancing inference speed and output quality. Existing methods predominantly rely on static confidence thresholds, overlooking the spatial-temporal dynamics of token confidence, causing unnecessary remasking. We propose Spatial-Temporal Token-Dynamics-Aware Responsive Remasking (STaRR), a training-free framework that dynamically adapts remasking decisions based on token confidence evolution. STaRR introduces two metrics, temporal variance and spatial deviance, to guide fine-grained, step-wise dynamic thresholding. We further introduce a step-wise dynamic thresholding strategy, further enhanced with responsiveness optimizations for scalability and robustness. Experiments show that STaRR achieves an average speedup of 4.1 and up to 8.9 while maintaining comparable accuracy.

cs.CL↗
arXiv2026

Precise Attribute Intensity Control in Large Language Models via Targeted Representation Editing

Precise attribute intensity control--generating Large Language Model (LLM) outputs with specific, user-defined attribute intensities--is crucial for AI systems adaptable to diverse user expectations. Current LLM alignment methods, however, typically provide only directional or open-ended guidance, failing to reliably achieve exact attribute intensities. We address this limitation with three key designs: (1) reformulating precise attribute intensity control as a target-reaching problem, rather than simple maximization; (2) training a lightweight value function via temporal-difference learning to predict final attribute intensity scores from partial generations, thereby steering LLM outputs; and (3) employing gradient-based interventions on hidden representations to navigate the model precisely towards specific attribute intensity targets. Our method enables fine-grained, continuous control over attribute intensities, moving beyond simple directional alignment. Experiments on LLaMA-3.2-3b and Phi-4-mini confirm our method's ability to steer text generation to user-specified attribute intensities with high accuracy. Finally, we demonstrate efficiency enhancements across three downstream tasks: preference data synthesis, Pareto frontier approximation and optimization, and distillation of aligned behaviors for intervention-free inference. Our code is available on https://github.com/Pre-Control/pre-control

cs.AI↗
arXiv2026

From Pixels to Policies: Reinforcing Spatial Reasoning in Language Models for Content-Aware Layout Design

We introduce LaySPA, a reinforcement learning framework that equips large language models (LLMs) with explicit and interpretable spatial reasoning for content-aware graphic layout design. LaySPA addresses two key challenges: LLMs' limited spatial reasoning and the lack of opacity in design decision making. Instead of operating at the pixel level, we reformulate layout design as a policy learning problem over a structured textual spatial environment that explicitly encodes canvas geometry, element attributes, and inter-element relationships. LaySPA produces dual-level outputs comprising interpretable reasoning traces and structured layout specifications, enabling transparent and controllable design decision making. Layout design policy is optimized via a multi-objective spatial critique that decomposes layout quality into geometric validity, relational coherence, and aesthetic consistency, and is trained using relative group optimization to stabilize learning in open-ended design spaces. Experiments demonstrate that LaySPA improves structural validity and visual quality, outperforming larger proprietary LLMs and achieving performance comparable to specialized SOTA layout generators while requiring fewer annotated samples and reduced latency.

cs.AI↗
arXiv2026

Unsupervised MR-US Multimodal Image Registration with Multilevel Correlation Pyramidal Optimization

Surgical navigation based on multimodal image registration has played a significant role in providing intraoperative guidance to surgeons by showing the relative position of the target area to critical anatomical structures during surgery. However, due to the differences between multimodal images and intraoperative image deformation caused by tissue displacement and removal during the surgery, effective registration of preoperative and intraoperative multimodal images faces significant challenges. To address the multimodal image registration challenges in Learn2Reg 2025, an unsupervised multimodal medical image registration method based on Multilevel Correlation Pyramidal Optimization (MCPO) is designed to solve these problems. First, the features of each modality are extracted based on the modality independent neighborhood descriptor, and the multimodal images is mapped to the feature space. Second, a multilevel pyramidal fusion optimization mechanism is designed to achieve global optimization and local detail complementation of the displacement field through dense correlation analysis and weight-balanced coupled convex optimization for input features at different scales. Our method focuses on the ReMIND2Reg task in Learn2Reg 2025. Based on the results, our method achieved the first place in the validation phase and test phase of ReMIND2Reg. The MCPO is also validated on the Resect dataset, achieving an average TRE of 1.798 mm. This demonstrates the broad applicability of our method in preoperative-to-intraoperative image registration. The code is available at https://github.com/wjiazheng/MCPO.

cs.CV↗
arXiv2026

DeLiVR: Differential Spatiotemporal Lie Bias for Efficient Video Deraining

Videos captured in the wild often suffer from rain streaks, blur, and noise. In addition, even slight changes in camera pose can amplify cross-frame mismatches and temporal artifacts. Existing methods rely on optical flow or heuristic alignment, which are computationally expensive and less robust. To address these challenges, Lie groups provide a principled way to represent continuous geometric transformations, making them well-suited for enforcing spatial and temporal consistency in video modeling. Building on this insight, we propose DeLiVR, an efficient video deraining method that injects spatiotemporal Lie-group differential biases directly into attention scores of the network. Specifically, the method introduces two complementary components. First, a rotation-bounded Lie relative bias predicts the in-plane angle of each frame using a compact prediction module, where normalized coordinates are rotated and compared with base coordinates to achieve geometry-consistent alignment before feature aggregation. Second, a differential group displacement computes angular differences between adjacent frames to estimate a velocity. This bias computation combines temporal decay and attention masks to focus on inter-frame relationships while precisely matching the direction of rain streaks. Extensive experimental results demonstrate the effectiveness of our method on publicly available benchmarks. The code is publicly available at https://github.com/Shuning0312/ICLR-DeLiVR.

cs.CV↗
arXiv2026

Triple Differential Heavy-to-light Semi-leptonic Decays at Next-to-Next-to-Next-to-Leading Order in QCD

We report the first complete calculation of the five heavy-to-light hadronic structure functions underlying semi-leptonic heavy-quark decays at next-to-next-to-next-to-leading order ($\mathcal{O}(α_s^3)$) in perturbative QCD. This theoretical advance, achieved via an innovative hybrid computational strategy, enables precision predictions for triple differential decay rates. The results are essential for harnessing the potential of high-precision experiments at Belle II, BES III, and LHCb. Selected applications of this work include a state-of-the-art prediction for the inclusive $B \to X_u \ell ν$ width, crucial for a percent-level determination of $|V_{ub}|$, and the first $\mathcal{O}(α_s^3)$ results for lepton-energy moments in charm decays, vital for extracting $|V_{cs}|$ and $|V_{cd}|$. Our analysis also reveals significant higher-order corrections in the large-$q^2$ region of $b \to u$ transitions, offering new insights into the persistent tension between inclusive and exclusive $|V_{ub}|$ determinations.

hep-ph↗
arXiv2026

ThinkRouter: Efficient Reasoning via Routing Thinking between Latent and Discrete Spaces

Recent work explores latent reasoning to improve reasoning efficiency by replacing explicit reasoning trajectories with continuous representations in a latent space, yet its effectiveness varies across settings. Analysis of model confidence dynamics under latent reasoning reveals that thinking trajectories ending in incorrect answers contain fewer low-confidence steps than those ending in correct answers. Meanwhile, we suggest that soft embeddings aggregated by multiple low-confidence thinking alternatives may introduce and propagate noise, leading to high confidence in unreliable reasoning trajectories. Motivated by these observations, ThinkRouter, an inference-time confidence-aware routing mechanism is proposed to avoid high confidence and noise for efficient reasoning. ThinkRouter routes thinking to the discrete token space when model confidence is low, and to the latent space otherwise. Extensive experiments on STEM reasoning and coding benchmarks across diverse large reasoning models demonstrate that ThinkRouter outperforms explicit CoT, random routing, and latent reasoning baselines in terms of accuracy, achieving an average improvement of 19.70 points in Pass@1, while reducing generation length by up to 15.55%. Further comprehensive analysis reveals that ThinkRouter can calibrate errors arising from explicit CoT and latent reasoning, and accelerates end-of-thinking token generation by globally lowering model confidence.

cs.AI↗
arXiv2026

Heavy-to-light Structure Functions at $\mathcal{O}(α_s^3)$ in QCD

We present the first complete $\mathcal{O}(α_s^2)$ and $\mathcal{O}(α_s^3)$ perturbative QCD corrections to all five heavy-to-light structure functions underlying the triple-differential semi-leptonic decay rates of heavy quarks. This is achieved via a hybrid computational strategy that combines an efficient linear interpolation (with a suitable function basis) based on stratified Gauss-Kronrod points in the leptonic-mass $q^2$ with the differential equations in the other variable, further armed with reduced numerical $\varepsilon$-dependence. Among the selected applications, we highlight the state-of-the-art prediction $Γ(B \rightarrow X_u \ell \barν_{\ell}) = \frac{|V_{ub}|^2}{|3.82\times 10^{-3}|^2}\,\big( 6.53 \,\pm 0.12 \, \pm 0.13\, \pm 0.03\, \big) \times 10^{-16}\,\text{GeV}\,$ derived in the kinetic-mass scheme. We report several notable observations regarding the convergence of the first three orders of QCD corrections to the $q^2$-spectrum and to inclusive moments of the lepton-energy spectrum in semi-leptonic weak decays of $b$- and $c$-quark in different quark-mass schemes; they are important both for improving the inclusive determinations of the relevant CKM elements, non-perturbative dynamical parameters, and for gaining new insights into the potential impact of high-order QCD corrections. Lastly we discuss a novel interesting point encountered in the consistent perturbative reformulation of the differential $q^2$-spectrum from the pole-mass to other mass schemes: certain boundary-effect terms are identified that are non-vanishing for $b \rightarrow u \ell \barν_{\ell}$ firstly at $\mathcal{O}(α_s^3)$; their incorporation is essential to preserve the integrity of the integrated moments of the perturbatively re-expanded $q^2$-spectrum but necessitates histogramming from $\mathcal{O}(α_s^3)$ onward even within pure perturbation theory.

hep-ph↗
arXiv2026

Electrostatic Screening Modulation of Graphene's Electronic Structure and the Helical Wavefunction Dominated Topological Properties

This study examines electrostatic screening effects in graphene using tight binding calculations based on the Binding energy and Bond Charge model and a modified version of it. The results indicate that the modified BBC potential decays in an exponential manner with distance, which suppresses electron electron interactions. The hopping integrals exhibit a pronounced decrease over distance and shift with parameter variation. A band gap opens once the parameter exceeds a certain threshold. The density of states shows a prominent peak near the Fermi level, whereas the low-energy region remains largely unchanged. The low energy helical wave functions in graphene display topological characteristics, including pseudospin momentum locking and a π Berry phase, resulting in distinctive transport properties. By avoiding the Coulomb singularity, the model offers valuable insights for the engineering of screening in two-dimensional systems and the design of topological devices.

cond-mat.mes-hall↗
arXiv2026

SARM: LLM-Augmented Semantic Anchor for End-to-End Live-Streaming Ranking

Large-scale live-streaming recommendation requires precise modeling of non-stationary content semantics under strict real-time serving constraints. In industrial deployment, two common approaches exhibit fundamental limitations: discrete semantic abstractions sacrifice descriptive precision through clustering, while dense multimodal embeddings are extracted independently and remain weakly aligned with ranking optimization, limiting fine-grained content-aware ranking. To address these limitations, we propose \textbf{SARM}, an end-to-end ranking architecture that integrates natural-language semantic anchors directly into ranking optimization, enabling fine-grained author representations conditioned on multimodal content. Each semantic anchor is represented as learnable text tokens jointly optimized with ranking features, allowing the model to adapt content descriptions to ranking objectives. A lightweight dual-token gated design captures domain-specific live-streaming semantics, while an asymmetric deployment strategy preserves low-latency online training and serving. Extensive offline evaluation and large-scale A/B tests show consistent improvements over production baselines. SARM is fully deployed and serves over 400 million users daily.

cs.IR↗
arXiv2026

QARM V2: Quantitative Alignment Multi-Modal Recommendation for Reasoning User Sequence Modeling

With the evolution of large language models (LLMs), there is growing interest in leveraging their rich semantic understanding to enhance industrial recommendation systems (RecSys). Traditional RecSys relies on ID-based embeddings for user sequence modeling in the General Search Unit (GSU) and Exact Search Unit (ESU) paradigm, which suffers from low information density, knowledge isolation, and weak generalization ability. While LLMs offer complementary strengths with dense semantic representations and strong generalization, directly applying LLM embeddings to RecSys faces critical challenges: representation unmatch with business objectives and representation unlearning end-to-end with downstream tasks. In this paper, we present QARM V2, a unified framework that bridges LLM semantic understanding with RecSys business requirements for user sequence modeling.

cs.IR↗
arXiv2026

Top-Quark Decay at Next-to-Next-to-Next-to-Leading Order in QCD

We present the first complete high-precision QCD corrections to the inclusive decay width $\mathrmΓ_t$, the $W$-helicity fractions $f_{\mathrm{L,R,0}}$ and semi-inclusive distributions for the top-quark decay process $t \rightarrow b + W^+ + X_{\mathrm{\tiny QCD}}$ at NNNLO in the strong coupling constant $α_s$. In particular, the pure NNNLO QCD correction decreases the $\mathrmΓ_t$ by about $0.8\%$ of the previous NNLO result at the top-quark pole mass scale, exceeding the error estimated by the usual scale-variation prescription. After taking into account all sources of errors, we get $\mathrmΓ_t = 1.3148^{+0.003}_{-0.005} + 0.027\,(m_t - 172.69)\,\text{GeV} $, the error of which meets the request by future colliders. On the other hand, the NNNLO QCD effects on $f_{\mathrm{L,R,0}}$ are found to be much smaller, at the level of one per-mille for the dominating $f_{0}$, predestining them to act as precision observables for the top-quark decay process.

hep-ph↗