arXiv subjects

Xinyu Liu

Publications and source records attributed to Xinyu Liu.

At least 145 records · Page 8Linked to original sources

arXiv2025

Turning Internal Gap into Self-Improvement: Promoting the Generation-Understanding Unification in MLLMs

Although unified MLLMs aim to unify generation and understanding, they are considered to exhibit an internal gap, with understanding outperforming generation. Through large-scale evaluation across multiple MLLMs and tasks, we confirm the widespread non-unification of MLLMs, and demonstrate that it indeed stems from weak generation rather than misunderstanding. This finding motivates us to propose a simple yet effective internal gap-based self-improvement framework, which mitigates internal gaps by leveraging stronger understanding to guide weaker generation without relying on any external signals. We validate this strategy through comprehensive experiments: scoring generations with understanding to construct image data for post-training (e.g., SFT and DPO) significantly improves generation while promoting unification. Furthermore, we empirically discover a co-improvement effect of such self-improvement, a phenomenon well known in pre-training but underexplored in post-training. Specifically, as generation improves, understanding becomes more effective at detecting false positives that were previously misclassified as prompt-aligned. To explain this effect, we extend learning dynamic theory to the MLLM setting, showing that the shared empirical neural tangent kernel between generation and understanding encourages aligned learning dynamics, thereby driving co-improvement. This interplay between generation and understanding further motivates a curriculum learning approach for stronger self-improvement: progressively enhanced understanding and generation revisit samples underutilized by pre-trained MLLMs, dynamically expanding post-training data and leading to improved performance and unification.

cs.CL↗

arXiv2025

The LLN and CLT for the statistical ensembles of discrete integrable Hamiltonian systems

This paper investigates the behavior of statistical ensembles under iteration map induced by discrete integrable Hamiltonian systems in deterministic case and stochastic case, addressing the problem from two perspectives: the Law of Large Numbers and the Central Limit Theorem. In deterministic case, the Law of Large Numbers simplifies the convergence conditions to the extent that the Riemann-Lebesgue lemma is no longer required. In the stochastic setting, we extend the results to general stochastic processes, beginning with the perturbation term represented by standard Brownian motion. Moreover, we establish a Central Limit Theorem for the statistical ensemble. A numerical example is also included.

math.PR↗

arXiv2025

Angular Linearization and Quantitative Convergence of Statistical Ensembles for Weighted Integrable Hamiltonian Systems

Within the framework of weighted integrable Hamiltonian systems, we study the long-time behavior of the associated statistical ensembles. We construct an action-dependent angular conjugacy that rectifies the nonuniform angular flow into a constant-speed linear flow, thereby reducing the ensemble dynamics to oscillatory integrals over the action domain. Using integration by parts along a tailored vector field and $W^{1,1}$ approximations with controlled boundary terms, we derive inverse-in-time decay for each Fourier mode and complete the summation under nonresonance and uniform nondegeneracy assumptions. Consequently, under suitable regularity and admissible initial data, we prove that the ensemble converges to the weighted equilibrium measure at rate $O(1/t)$, with an explicit parameter-dependent bound. The methodology provides a transferable analytic scheme for establishing limit theorems in near-integrable regimes.

math.DS↗

arXiv2025

Pure Exploration via Frank-Wolfe Self-Play

We study pure exploration in structured stochastic multi-armed bandits, aiming to efficiently identify the correct hypothesis from a finite set of alternatives. For a broad class of tasks, asymptotic analyses reduce to a maximin optimization that admits a two-player zero-sum game interpretation between an experimenter and a skeptic: the experimenter allocates measurements to rule out alternatives while the skeptic proposes alternatives. We reformulate the game by allowing the skeptic to adopt a mixed strategy, yielding a concave-convex saddle-point problem. This viewpoint leads to Frank-Wolfe Self-Play (FWSP): a projection-free, regularization-free, tuning-free method whose one-hot updates on both sides match the bandit sampling paradigm. However, structural constraints introduce sharp pathologies that complicate algorithm design and analysis: our linear-bandit case study exhibits nonunique optima, optimal designs with zero mass on the best arm, bilinear objectives, and nonsmoothness at the boundary. We address these challenges via a differential-inclusion argument, proving convergence of the game value for best-arm identification in linear bandits. Our analysis proceeds through a continuous-time limit: a differential inclusion with a Lyapunov function that decays exponentially, implying a vanishing duality gap and convergence to the optimal value. Although Lyapunov analysis requires differentiability of the objective, which is not guaranteed on the boundary, we show that along continuous trajectories the algorithm steers away from pathological nonsmooth points and achieves uniform global convergence to the optimal game value. We then embed the discrete-time updates into a perturbed flow and show that the discrete game value also converges. Building on FWSP, we further propose a learning algorithm based on posterior sampling. Numerical experiments demonstrate a vanishing duality gap.

cs.LG↗

arXiv2025

TCPO: Thought-Centric Preference Optimization for Effective Embodied Decision-making

Using effective generalization capabilities of vision language models (VLMs) in context-specific dynamic tasks for embodied artificial intelligence remains a significant challenge. Although supervised fine-tuned models can better align with the real physical world, they still exhibit sluggish responses and hallucination issues in dynamically changing environments, necessitating further alignment. Existing post-SFT methods, reliant on reinforcement learning and chain-of-thought (CoT) approaches, are constrained by sparse rewards and action-only optimization, resulting in low sample efficiency, poor consistency, and model degradation. To address these issues, this paper proposes Thought-Centric Preference Optimization (TCPO) for effective embodied decision-making. Specifically, TCPO introduces a stepwise preference-based optimization approach, transforming sparse reward signals into richer step sample pairs. It emphasizes the alignment of the model's intermediate reasoning process, mitigating the problem of model degradation. Moreover, by incorporating Action Policy Consistency Constraint (APC), it further imposes consistency constraints on the model output. Experiments in the ALFWorld environment demonstrate an average success rate of 26.67%, achieving a 6% improvement over RL4VLM and validating the effectiveness of our approach in mitigating model degradation after fine-tuning. These results highlight the potential of integrating preference-based learning techniques with CoT processes to enhance the decision-making capabilities of vision-language models in embodied agents.

cs.AI↗

arXiv2025

FusionCounting: Robust visible-infrared image fusion guided by crowd counting via multi-task learning

Visible and infrared image fusion (VIF) is an important multimedia task in computer vision. Most VIF methods focus primarily on optimizing fused image quality. Recent studies have begun incorporating downstream tasks, such as semantic segmentation and object detection, to provide semantic guidance for VIF. However, semantic segmentation requires extensive annotations, while object detection, despite reducing annotation efforts compared with segmentation, faces challenges in highly crowded scenes due to overlapping bounding boxes and occlusion. Moreover, although RGB-T crowd counting has gained increasing attention in recent years, no studies have integrated VIF and crowd counting into a unified framework. To address these challenges, we propose FusionCounting, a novel multi-task learning framework that integrates crowd counting into the VIF process. Crowd counting provides a direct quantitative measure of population density with minimal annotation, making it particularly suitable for dense scenes. Our framework leverages both input images and population density information in a mutually beneficial multi-task design. To accelerate convergence and balance tasks contributions, we introduce a dynamic loss function weighting strategy. Furthermore, we incorporate adversarial training to enhance the robustness of both VIF and crowd counting, improving the model's stability and resilience to adversarial attacks. Experimental results on public datasets demonstrate that FusionCounting not only enhances image fusion quality but also achieves superior crowd counting performance.

cs.CV↗

arXiv2025

Constructing a Norm for Children's Scientific Drawing: Distribution Features Based on Semantic Similarity of Large Language Models

The use of children's drawings to examining their conceptual understanding has been proven to be an effective method, but there are two major problems with previous research: 1. The content of the drawings heavily relies on the task, and the ecological validity of the conclusions is low; 2. The interpretation of drawings relies too much on the subjective feelings of the researchers. To address this issue, this study uses the Large Language Model (LLM) to identify 1420 children's scientific drawings (covering 9 scientific themes/concepts), and uses the word2vec algorithm to calculate their semantic similarity. The study explores whether there are consistent drawing representations for children on the same theme, and attempts to establish a norm for children's scientific drawings, providing a baseline reference for follow-up children's drawing research. The results show that the representation of most drawings has consistency, manifested as most semantic similarity>0.8. At the same time, it was found that the consistency of the representation is independent of the accuracy (of LLM's recognition), indicating the existence of consistency bias. In the subsequent exploration of influencing factors, we used Kendall rank correlation coefficient to investigate the effects of "sample size", "abstract degree", and "focus points" on drawings, and used word frequency statistics to explore whether children represented abstract themes/concepts by reproducing what was taught in class. It was found that accuracy (of LLM's recognition) is the most sensitive indicator, and data such as sample size and semantic similarity are related to it; The consistency between classroom experiments and teaching purpose is also an important factor, many students focus more on the experiments themselves rather than what they explain.

cs.CL↗

arXiv2025

Improved Personalized Headline Generation via Denoising Fake Interests from Implicit Feedback

Accurate personalized headline generation hinges on precisely capturing user interests from historical behaviors. However, existing methods neglect personalized-irrelevant click noise in entire historical clickstreams, which may lead to hallucinated headlines that deviate from genuine user preferences. In this paper, we reveal the detrimental impact of click noise on personalized generation quality through rigorous analysis in both user and news dimensions. Based on these insights, we propose a novel Personalized Headline Generation framework via Denoising Fake Interests from Implicit Feedback (PHG-DIF). PHG-DIF first employs dual-stage filtering to effectively remove clickstream noise, identified by short dwell times and abnormal click bursts, and then leverages multi-level temporal fusion to dynamically model users' evolving and multi-faceted interests for precise profiling. Moreover, we release DT-PENS, a new benchmark dataset comprising the click behavior of 1,000 carefully curated users and nearly 10,000 annotated personalized headlines with historical dwell time annotations. Extensive experiments demonstrate that PHG-DIF substantially mitigates the adverse effects of click noise and significantly improves headline quality, achieving state-of-the-art (SOTA) results on DT-PENS. Our framework implementation and dataset are available at https://github.com/liukejin-up/PHG-DIF.

cs.CL↗

arXiv2025

g-Factor Enhanced Upper Critical Field in Superconducting PdTe2 due to Quantum Confinement

The Pauli limiting field of superconductors determines the maximal possible value of magnetic field at which superconductivity remains possible. For weak-coupling superconductors, it is determined by an established relation that can be found by setting the condensation energy equal to the magnetization free energy. The latter is a function of the carrier g-factor. Here, we demonstrate in a van der Waals superconductor PdTe2, that quantum confinement can tune the effective g-factor causing the Pauli limit to become thickness dependent. We experimentally probe the in-plane upper critical field (Hc2||) of PdTe2 at intermediate thicknesses down to 20mK. Hc2|| is enhanced by more than an order of magnitude as the thickness is varied from 50nm down to 19nm. We model its temperature and thickness dependence, revealing that both orbital and spin Zeeman depairing mechanisms impact its value. While the variation of the orbital interaction is expected, our findings reveal how the Zeeman interaction impacts superconductivity in thin films. They aid in the search for mixed and odd pairing superconductivity where an enhancement of Hc2|| can be occasionally associated with those unconventional pairing symmetries.

cond-mat.supr-con↗

arXiv2025

Unified Semiclassical Theory of Nonlinear Hall Effect:Bridging Ballistic and Diffusive Transport Regime

The nonlinear Hall effect has attracted considerable attention and undergone extensive investigation in recent years. However, theoretical studies addressing size-dependent effects remain largely unexplored. In this work, we establish a unified semiclassical framework based on the Boltzmann transport equation, incorporating generalized boundary conditions to bridge the ballistic and diffusive transport regimes. Our analysis reveals that the nonlinear Hall effect arises from the combined action of two distinct mechanisms: the Berry curvature dipole and the Fermi-surface integral of Berry curvature. Furthermore, we investigate the Hall effect in topological crystalline insulators (TCIs), elucidating that the size dependence originates from competition between the two transport mechanisms. By connecting the two distinct regimes, our theoretical framework provides a comprehensive understanding of the nonlinear Hall effect in finite-sized systems, offering both fundamental insights and a useful analytical tool for more size-dependent investigations.

cond-mat.mes-hall↗

arXiv2025

EndoGen: Conditional Autoregressive Endoscopic Video Generation

Endoscopic video generation is crucial for advancing medical imaging and enhancing diagnostic capabilities. However, prior efforts in this field have either focused on static images, lacking the dynamic context required for practical applications, or have relied on unconditional generation that fails to provide meaningful references for clinicians. Therefore, in this paper, we propose the first conditional endoscopic video generation framework, namely EndoGen. Specifically, we build an autoregressive model with a tailored Spatiotemporal Grid-Frame Patterning (SGP) strategy. It reformulates the learning of generating multiple frames as a grid-based image generation pattern, which effectively capitalizes the inherent global dependency modeling capabilities of autoregressive architectures. Furthermore, we propose a Semantic-Aware Token Masking (SAT) mechanism, which enhances the model's ability to produce rich and diverse content by selectively focusing on semantically meaningful regions during the generation process. Through extensive experiments, we demonstrate the effectiveness of our framework in generating high-quality, conditionally guided endoscopic content, and improves the performance of downstream task of polyp segmentation. Code released at https://www.github.com/CUHK-AIM-Group/EndoGen.

cs.CV↗

arXiv2025

A Structure-Guided Gauss-Newton Method for Shallow ReLU Neural Network

In this paper, we propose a structure-guided Gauss-Newton (SgGN) method for solving least squares problems using a shallow ReLU neural network. The method effectively takes advantage of both the least squares structure and the neural network structure of the objective function. By categorizing the weights and biases of the hidden and output layers of the network as nonlinear and linear parameters, respectively, the method iterates back and forth between the nonlinear and linear parameters. The nonlinear parameters are updated by a damped Gauss-Newton method and the linear ones are updated by a linear solver. Moreover, at the Gauss-Newton step, a special form of the Gauss-Newton matrix is derived for the shallow ReLU neural network and is used for efficient iterations. It is shown that the corresponding mass and Gauss-Newton matrices in the respective linear and nonlinear steps are symmetric and positive definite under reasonable assumptions. Thus, the SgGN method naturally produces an effective search direction without the need of additional techniques like shifting in the Levenberg-Marquardt method to achieve invertibility of the Gauss-Newton matrix. The convergence and accuracy of the method are demonstrated numerically for several challenging function approximation problems, especially those with discontinuities or sharp transition layers that pose significant challenges for commonly used training algorithms in machine learning.

cs.LG↗

arXiv2025

Camera-based implicit mind reading by capturing higher-order semantic dynamics of human gaze within environmental context

Emotion recognition,as a step toward mind reading,seeks to infer internal states from external cues.Most existing methods rely on explicit signals-such as facial expressions,speech,or gestures-that reflect only bodily responses and overlook the influence of environmental context.These cues are often voluntary,easy to mask,and insufficient for capturing deeper,implicit emotions. Physiological signal-based approaches offer more direct access to internal states but require complex sensors that compromise natural behavior and limit scalability.Gaze-based methods typically rely on static fixation analysis and fail to capture the rich,dynamic interactions between gaze and the environment,and thus cannot uncover the deep connection between emotion and implicit behavior.To address these limitations,we propose a novel camera-based,user-unaware emotion recognition approach that integrates gaze fixation patterns with environmental semantics and temporal dynamics.Leveraging standard HD cameras,our method unobtrusively captures users'eye appearance and head movements in natural settings-without the need for specialized hardware or active user participation.From these visual cues,the system estimates gaze trajectories over time and space, providing the basis for modeling the spatial, semantic,and temporal dimensions of gaze behavior. This allows us to capture the dynamic interplay between visual attention and the surrounding environment,revealing that emotions are not merely physiological responses but complex outcomes of human-environment interactions.The proposed approach enables user-unaware,real-time,and continuous emotion recognition,offering high generalizability and low deployment cost.

cs.CV↗

arXiv2025

NL2SQL-BUGs: A Benchmark for Detecting Semantic Errors in NL2SQL Translation

Natural Language to SQL (i.e., NL2SQL) translation is crucial for democratizing database access, but even state-of-the-art models frequently generate semantically incorrect SQL queries, hindering the widespread adoption of these techniques by database vendors. While existing NL2SQL benchmarks primarily focus on correct query translation, we argue that a benchmark dedicated to identifying common errors in NL2SQL translations is equally important, as accurately detecting these errors is a prerequisite for any subsequent correction-whether performed by humans or models. To address this gap, we propose NL2SQL-BUGs, the first benchmark dedicated to detecting and categorizing semantic errors in NL2SQL translation. NL2SQL-BUGs adopts a two-level taxonomy to systematically classify semantic errors, covering 9 main categories and 31 subcategories. The benchmark consists of 2,018 expert-annotated instances, each containing a natural language query, database schema, and SQL query, with detailed error annotations for semantically incorrect queries. Through comprehensive experiments, we demonstrate that current large language models exhibit significant limitations in semantic error detection, achieving an average detection accuracy of 75.16%. Specifically, our method successfully detected 106 errors (accounting for 6.91%) in BIRD, a widely-used NL2SQL dataset, which were previously undetected annotation errors. This highlights the importance of semantic error detection in NL2SQL systems. The benchmark is publicly available at https://nl2sql-bugs.github.io/.

cs.DB↗

arXiv2025

Track Any Anomalous Object: A Granular Video Anomaly Detection Pipeline

Video anomaly detection (VAD) is crucial in scenarios such as surveillance and autonomous driving, where timely detection of unexpected activities is essential. Although existing methods have primarily focused on detecting anomalous objects in videos -- either by identifying anomalous frames or objects -- they often neglect finer-grained analysis, such as anomalous pixels, which limits their ability to capture a broader range of anomalies. To address this challenge, we propose a new framework called Track Any Anomalous Object (TAO), which introduces a granular video anomaly detection pipeline that, for the first time, integrates the detection of multiple fine-grained anomalous objects into a unified framework. Unlike methods that assign anomaly scores to every pixel, our approach transforms the problem into pixel-level tracking of anomalous objects. By linking anomaly scores to downstream tasks such as segmentation and tracking, our method removes the need for threshold tuning and achieves more precise anomaly localization in long and complex video sequences. Experiments demonstrate that TAO sets new benchmarks in accuracy and robustness. Project page available online.

cs.CV↗

arXiv2025

Inhomogeneous Quantum Quenches of Conformal Field Theory with Boundaries

We develop a method to calculate generic time-dependent correlation functions for inhomogeneous quantum quenches in (1+1)-dimensional conformal field theory (CFT) induced by sudden Hamiltonian deformations that modulate the energy density inhomogeneously. Our work particularly focuses on the effects of spatial boundaries, which have remained unresolved by previous analytical methods. For generic post-quench Hamiltonian, we develop a generic method to calculate the correlations by mirroring the system, which otherwise are Euclidean path integrals in complicated spacetime geometries difficult to calculate. On the other hand, for a special class of inhomogeneous post-quench Hamiltonians, including the Möbius and sine-square-deformation Hamiltonians, we show that the quantum quenches exhibit simple boundary effects calculable from Euclidean path integrals in a straightforward strip spacetime geometry. Applying our method to the time evolution of entanglement entropy, we find that for generic cases, the entanglement entropy shows discontinuities (shockwave fronts) propagating from the boundaries.In contrast, such discontinuities are absent in cases with simple boundary effects. We verify that our generic CFT formula matches well with numerical calculations from free fermion tight-binding models for various quench scenarios.

cond-mat.stat-mech↗

arXiv2025

Linear $Q$-Learning Does Not Diverge in $L^2$: Convergence Rates to a Bounded Set

$Q$-learning is one of the most fundamental reinforcement learning algorithms. It is widely believed that $Q$-learning with linear function approximation (i.e., linear $Q$-learning) suffers from possible divergence until the recent work Meyn (2024) which establishes the ultimate almost sure boundedness of the iterates of linear $Q$-learning. Building on this success, this paper further establishes the first $L^2$ convergence rate of linear $Q$-learning iterates (to a bounded set). Similar to Meyn (2024), we do not make any modification to the original linear $Q$-learning algorithm, do not make any Bellman completeness assumption, and do not make any near-optimality assumption on the behavior policy. All we need is an $ε$-softmax behavior policy with an adaptive temperature. The key to our analysis is the general result of stochastic approximations under Markovian noise with fast-changing transition functions. As a side product, we also use this general result to establish the $L^2$ convergence rate of tabular $Q$-learning with an $ε$-softmax behavior policy, for which we rely on a novel pseudo-contraction property of the weighted Bellman optimality operator.

cs.LG↗

arXiv2025

Spectral analysis of the magneto-optical response in valley polarized Pb$_{1-x}$Sn$_x$Se

Since the last century, considerable efforts have been devoted to the study of valley-degenerate narrow gap semiconductors, such as the Pb$_{1-x}$Sn$_x$Se alloy. This material possesses band edges at the $L$-points of their Brillouin zone, yielding a valley degeneracy of four. However, in (111)-oriented films, it is still not fully understood how differences between the longitudinal valley, oriented along the growth axis, and the oblique valleys, oriented at an angle with respect to that axis, appear in infrared magneto-optical spectroscopy. In this work, we report a magneto-optical study on this family of alloys, focusing on an anomaly in the interband transition of the absorption strength ratio between longitudinal and oblique valleys under a magnetic field applied along the [111] direction. Based on the Mitchell-Wallis model, we provide a theoretical fit for the experimental transmission data, which quantitatively explains the spectral shape of the data at magnetic fields as high as 35T. In particular, we attribute this anomalous absorption strength variation to the carrier density difference between the two types of valleys as well as the field-dependent multiple-beam interference or the Fabry-Pérot interference. Our analysis also allows for the extraction of the real and imaginary parts of the dielectric function.

cond-mat.mes-hall↗