arXiv subjects

Xiaokai Chen

Publications and source records attributed to Xiaokai Chen.

At least 19 recordsLinked to original sources

arXiv2026

ToSCA: Leveraging Hierarchical Reinforcement Learning on Temporal and Strategic Abstractions of Conversational Agents

Humans naturally exhibit multiple forms of abstraction in reasoning and interaction, including temporal abstraction across decision timescales and strategic abstraction over communicative intents. Inspired by these complementary abstractions, we propose a two-level hierarchical reinforcement learning (HRL) framework for conversational agents that bridges the gap between existing token-level and utterance-level RL methods. Built upon a two-level Markov decision process (MDP), our framework conditions token-level response generation on utterance-level actions represented by explicit textual strategies. Based on theoretical analysis and efficiency considerations, we employ DQN to optimize the high-level Q-network and PPO to train the low-level actor-critic. To further alleviate reward sparsity and facilitate convergence, we introduce a dual-granularity reward mechanism that combines the utterance-level satisfaction score with token-level intrinsic self-consistency and a KL-divergence penalty. Experiments on both daily-life and emotional support conversations demonstrate that our method consistently outperforms a wide range of baselines in both strategy determination and response quality. Our implementation is available at https://github.com/AaronJi/ToSCA.

cs.CL↗

arXiv2026

A Line-search-free Method for Adaptive Decentralized Optimization

We study decentralized optimization over networks where agents cooperatively minimize a smooth (strongly) convex sum of local losses while communicating only with immediate neighbors. Prevailing decentralized methods require either centralized knowledge of global problem and network parameters for stepsize tuning--hence impractical, or costly per-iteration line-searches that demand access to local function values. We propose line-search-free, fully decentralized algorithms in which each agent adapts its stepsize using only past local iterates and gradients--with no extra function evaluations and no global tuning. The key technical ingredient is a new Lyapunov function, from which a natural adaptive stepsize rule emerges: at each iteration, each agent selects the largest stepsize that guarantees descent, based solely on a local curvature estimate built from successive gradients. The proposed algorithms enjoy strong theoretical guarantees: sublinear convergence rates for merely convex objectives and linear rates under strong convexity. Numerical experiments on standard benchmarks show consistent improvements over the state of the art, both adaptive and non-adaptive.

math.OC↗

arXiv2026

Adaptive Decentralized Composite Optimization via Three-Operator Splitting

The paper studies decentralized optimization over networks, where agents minimize a sum of {\it locally} smooth (strongly) convex losses and plus a nonsmooth convex extended value term. We propose decentralized methods wherein agents {\it adaptively} adjust their stepsize via local backtracking procedures coupled with lightweight min-consensus protocols. Our design stems from a three-operator splitting factorization applied to an equivalent reformulation of the problem. The reformulation is endowed with a new BCV preconditioning metric (Bertsekas-O'Connor-Vandenberghe), which enables efficient decentralized implementation and local stepsize adjustments. We establish robust convergence guarantees. Under mere convexity, the proposed methods converge with a sublinear rate. Under strong convexity of the sum-function, and assuming the nonsmooth component is partly smooth, we further prove linear convergence. Numerical experiments corroborate the theory and highlight the effectiveness of the proposed adaptive stepsize strategy.

math.OC↗

arXiv2026

Adams Bashforth Moulton Solver for Inversion and Editing in Rectified Flow

Rectified flow models have achieved remarkable performance in image and video generation tasks. However, existing numerical solvers face a trade-off between fast sampling and high accuracy solutions, limiting their effectiveness in downstream applications such as reconstruction and editing. To address this challenge, we propose leveraging the Adams Bashforth Moulton (ABM) predictor corrector method to enhance the accuracy of ODE solving in rectified flow models. Specifically, we introduce ABM Solver, which integrates a multi step predictor corrector approach to reduce local truncation errors and employs Adaptive Step Size Adjustment to improve sampling speed. Furthermore, to effectively preserve non edited regions while facilitating semantic modifications, we introduce a Mask Guided Feature Injection module. We estimate self-similarity to generate a spatial mask that differentiates preserved regions from those available for editing. Extensive experiments on multiple high resolution image datasets validate that ABM Solver significantly improves inversion precision and editing quality, outperforming existing solvers without requiring additional training or optimization.

cs.CV↗

arXiv2025

Dual Role of Nb in Defect-Mediated Strength and Ductility of γ-TiAl Alloys

The origin of the superior high-temperature strength of γ-TiAl with high Nb addition remains highly controversial, largely due to the unclear role of Nb atoms. Using large-scale hybrid Monte Carlo and molecular dynamics simulations with a self-developed neural network potential,we show that Nb atoms predominantly occupy Ti sites and form short-range order with neighboring Al atoms, but a non-negligible fraction also occupies Al sites (NbAl) and promotes the formation of antisite defects (TiAl). Both the NbAl and TiAl antisites exceptionally reduce stacking fault energies and facilitate deformation twinning, thereby enhancing plasticity. Meanwhile, these substitutional and antisite defects also increase the Peierls stress of both screw and edge dislocations, which hinders dislocation motion to cause pronounced solid-solution strengthening. This work provides mechanistic insights into the dual role of Nb in enhancing both strength and ductility in γ-TiAl and further offers guidance for defect and composition engineering in advanced alloy systems.

cond-mat.mtrl-sci↗

arXiv2025

Mock Observations for the CSST Mission: Multi-Channel Imager--The Cluster Field

The Multi-Channel Imager (MCI), one of the instruments aboard the China Survey Space Telescope (CSST), is designed to simultaneously observe the sky in three filters, covering wavelengths from the near-ultraviolet (NUV) to the near-infrared (NIR). With its large field of view ($7.5^{\prime}\times7.5^{\prime}$), MCI is particularly well-suited for observing galaxy clusters, providing a powerful tool for investigating galaxy evolution, dark matter and dark energy through gravitational lensing. Here we present a comprehensive simulation framework of a strong lensing cluster as observed by MCI, aiming to fully exploit its capabilities in capturing lensing features. The framework simulates a strong lensing cluster from the CosmoDC2 catalog, calculating the gravitational potential and performing ray-tracing to derive the true positions, shapes and light distribution of galaxies within the cluster field. Additionally, the simulation incorporates intra-cluster light (ICL) and spectral energy distributions (SEDs), enabling further strong lensing analyses, such as ICL seperation from galaxy light and mass reconstruction combining strong and weak lensing measurements. This framework provides a critical benchmark for testing the MCI data pipeline and maximizing its potential in galaxy cluster research.

astro-ph.IM↗

arXiv2025

Convert Language Model into a Value-based Strategic Planner

Emotional support conversation (ESC) aims to alleviate the emotional distress of individuals through effective conversations. Although large language models (LLMs) have obtained remarkable progress on ESC, most of these studies might not define the diagram from the state model perspective, therefore providing a suboptimal solution for long-term satisfaction. To address such an issue, we leverage the Q-learning on LLMs, and propose a framework called straQ*. Our framework allows a plug-and-play LLM to bootstrap the planning during ESC, determine the optimal strategy based on long-term returns, and finally guide the LLM to response. Substantial experiments on ESC datasets suggest that straQ* outperforms many baselines, including direct inference, self-refine, chain of thought, finetuning, and finite state machines.

cs.CL↗

arXiv2025

Personalized Tree-Based Progressive Regression Model for Watch-Time Prediction in Short Video Recommendation

In online video platforms, accurate watch time prediction has become a fundamental and challenging problem in video recommendation. Previous research has revealed that the accuracy of watch time prediction highly depends on both the transformation of watch-time labels and the decomposition of the estimation process. TPM (Tree based Progressive Regression Model) achieves State-of-the-Art performance with a carefully designed and effective decomposition paradigm. TPM discretizes the watch time into several ordinal intervals and organizes them into a binary decision tree, where each node corresponds to a specific interval. At each non-leaf node, a binary classifier is used to determine the specific interval in which the watch time variable most likely falls, based on the prediction outcome at its parent node. The tree structure is central to TPM, as it defines the decomposition of watch time estimation and how ordinal intervals are discretized. However, TPM uses a predefined full binary tree, which may be sub-optimal for two reasons. First, full binary trees imply equal partitioning of the watch time space, which may fail to capture the complexity of real-world distributions. Second, rather than relying on a fixed global structure, we advocate for a personalized, data-driven tree that can be learned end-to-end. Thus, we propose PTPM to enable highly personalized decomposition of watch estimation with better efficacy and efficiency. Moreover, we show that TPM suffers from selection bias due to conditional modeling and propose a simple solution. We conduct extensive experiments on offline datasets and online environments. Offline results show improved watch time accuracy, and online A/B tests further validate the effectiveness of our framework. PTPM has been fully deployed in core traffic scenarios and now serves over 400 million users daily.

cs.IR↗

arXiv2025

A Parameter-free Decentralized Algorithm for Composite Convex Optimization

The paper studies decentralized optimization over networks, where agents minimize a composite objective consisting of the sum of smooth convex functions--the agents' losses--and an additional nonsmooth convex extended value function. We propose a decentralized algorithm wherein agents ${\it adaptively}$ adjust their stepsize using local backtracking procedures that require ${\it no}$ ${\it global}$ (network) information or extensive inter-agent communications. Our adaptive decentralized method enjoys robust convergence guarantees, outperforming existing decentralized methods, which are not adaptive. Our design is centered on a three-operator splitting, applied to a reformulation of the optimization problem. This reformulation utilizes a proposed BCV metric, which facilitates decentralized implementation and local stepsize adjustments while guarantying convergence.

math.OC↗

arXiv2025

Adaptive Stepsize Selection in Decentralized Convex Optimization

We study decentralized optimization where multiple agents minimize the average of their (strongly) convex, smooth losses over a communication graph. Convergence of the existing decentralized methods generally hinges on an apriori, proper selection of the stepsize. Choosing this value is notoriously delicate: (i) it demands global knowledge from all the agents of the graph's connectivity and every local smoothness/strong-convexity constants--information they rarely have; (ii) even with perfect information, the worst-case tuning forces an overly small stepsize, slowing convergence in practice; and (iii) large-scale trial-and-error tuning is prohibitive. This work introduces a decentralized algorithm that is fully adaptive in the choice of the agents' stepsizes, without any global information and using only neighbor-to-neighbor communications--agents need not even know whether the problem is strongly convex. The algorithm retains strong guarantees: it converges at \emph{linear} rate when the losses are strongly convex and at \emph{sublinear} rate otherwise, matching the best-known rates of (nonadaptive) parameter-dependent methods.

math.OC↗

arXiv2025

Multi-Party Supervised Fine-tuning of Language Models for Multi-Party Dialogue Generation

Large Language Models (LLM) are usually fine-tuned to participate in dyadic or two-party dialogues, which can not adapt well to multi-party dialogues (MPD), which hinders their applications in such scenarios including multi-personal meetings, discussions and daily communication. Previous LLM-based researches mainly focus on the multi-agent framework, while their base LLMs are still pairwisely fine-tuned. In this work, we design a multi-party fine-tuning framework (MuPaS) for LLMs on the multi-party dialogue datasets, and prove such a straightforward framework can let the LLM align with the multi-party conversation style efficiently and effectively. We also design two training strategies which can convert MuPaS into the MPD simulator. Substantial experiments show that MuPaS can achieve state-of-the-art multi-party response, higher accuracy of the-next-speaker prediction, higher human and automatic evaluated utterance qualities, and can even generate reasonably with out-of-distribution scene, topic and role descriptions. The MuPaS framework bridges the LLM training with more complicated multi-party applications, such as conversation generation, virtual rehearsal or meta-universe.

cs.CL↗

arXiv2025

DCatalyst: A Unified Accelerated Framework for Decentralized Optimization

We study decentralized optimization over a network of agents, modeled as graphs, with no central server. The goal is to minimize $f+r$, where $f$ represents a (strongly) convex function averaging the local agents' losses, and $r$ is a convex, extended-value function. We introduce DCatalyst, a unified black-box framework that integrates Nesterov acceleration into decentralized optimization algorithms. %, enhancing their performance. At its core, DCatalyst operates as an \textit{inexact}, \textit{momentum-accelerated} proximal method (forming the outer loop) that seamlessly incorporates any selected decentralized algorithm (as the inner loop). We demonstrate that DCatalyst achieves optimal communication and computational complexity (up to log-factors) across various decentralized algorithms and problem instances. Notably, it extends acceleration capabilities to problem classes previously lacking accelerated solution methods, thereby broadening the effectiveness of decentralized methods. On the technical side, our framework introduce the {\it inexact estimating sequences}--a novel extension of the well-known Nesterov's estimating sequences, tailored for the minimization of composite losses in decentralized settings. This method adeptly handles consensus errors and inexact solutions of agents' subproblems, challenges not addressed by existing models.

math.OC↗

arXiv2024

Enhancing Convergence of Decentralized Gradient Tracking under the KL Property

We study decentralized multiagent optimization over networks, modeled as undirected graphs. The optimization problem consists of minimizing a nonconvex smooth function plus a convex extended-value function, which enforces constraints or extra structure on the solution (e.g., sparsity, low-rank). We further assume that the objective function satisfies the Kurdyka-Łojasiewicz (KL) property, with given exponent $θ\in [0,1)$. The KL property is satisfied by several (nonconvex) functions of practical interest, e.g., arising from machine learning applications; in the centralized setting, it permits to achieve strong convergence guarantees. Here we establish convergence of the same type for the notorious decentralized gradient-tracking-based algorithm SONATA. Specifically, $\textbf{(i)}$ when $θ\in (0,1/2]$, the sequence generated by SONATA converges to a stationary solution of the problem at R-linear rate;$ \textbf{(ii)} $when $θ\in (1/2,1)$, sublinear rate is certified; and finally $\textbf{(iii)}$ when $θ=0$, the iterates will either converge in a finite number of steps or converges at R-linear rate. This matches the convergence behavior of centralized proximal-gradient algorithms except when $θ=0$. Numerical results validate our theoretical findings.

math.OC↗

arXiv2024

Inferring the mass content of galaxy clusters with satellite kinematics and Jeans Anisotropic modeling

Satellite galaxies can be used to indicate the dynamical mass of galaxy groups and clusters. In this study, we apply the axis-symmetric Jeans Anisotropic Multi-Gaussian Expansion JAM modeling to satellite galaxies in 28 galaxy clusters selected from the TNG300-1 simulation with halo mass of $\log_{10}M_{200}/M_\odot>14.3$. If using true bound satellites as tracers, the best constrained total mass within the half-mass radius of satellites, $M(<r_\mathrm{half})$, and the virial mass, $M_{200}$, have average biases of -0.01 and $0.03$~dex, with average scatters of 0.11~dex and 0.15~dex. If selecting companions in redshift space with line-of-sight depth of 2,000~km/s, the biases are -0.06 and $0.01$~dex, while the scatters are 0.12 and 0.18~dex for $M(<r_\mathrm{half})$ and $M_{200}$. By comparing the best-fitting and actual density profiles, we find $\sim$29% of best-fitting density profiles show very good agreement with the truth, $\sim$32% display over or under estimates at most of the radial range with biased $M(<r_\mathrm{half})$, and 39% show under/over estimates in central regions and over/under estimates in the outskirts, with good constraints on $M(<r_\mathrm{half})$, yet most of the best constraints are still consistent with the true profiles within 1-$σ$ statistical uncertainties for the three circumstances. Using a mock DESI Bright Galaxy Survey catalog with the effect of fiber incompleteness, we find DESI fiber assignments and the choice of flux limits barely modify the velocity dispersion profiles and are thus unlikely to affect the dynamical modeling outcomes. Our results show that with current and future deep spectroscopic surveys, JAM can be a powerful tool to constrain the underlying density profiles of individual massive galaxy clusters.

astro-ph.CO↗

arXiv2024

Real Face Video Animation Platform

In recent years, facial video generation models have gained popularity. However, these models often lack expressive power when dealing with exaggerated anime-style faces due to the absence of high-quality anime-style face training sets. We propose a facial animation platform that enables real-time conversion from real human faces to cartoon-style faces, supporting multiple models. Built on the Gradio framework, our platform ensures excellent interactivity and user-friendliness. Users can input a real face video or image and select their desired cartoon style. The system will then automatically analyze facial features, execute necessary preprocessing, and invoke appropriate models to generate expressive anime-style faces. We employ a variety of models within our system to process the HDTF dataset, thereby creating an animated facial video dataset.

cs.CV↗

arXiv2023

Discrete Conditional Diffusion for Reranking in Recommendation

Reranking plays a crucial role in modern multi-stage recommender systems by rearranging the initial ranking list to model interplay between items. Considering the inherent challenges of reranking such as combinatorial searching space, some previous studies have adopted the evaluator-generator paradigm, with a generator producing feasible sequences and a evaluator selecting the best one based on estimated listwise utility. Inspired by the remarkable success of diffusion generative models, this paper explores the potential of diffusion models for generating high-quality sequences in reranking. However, we argue that it is nontrivial to take diffusion models as the generator in the context of recommendation. Firstly, diffusion models primarily operate in continuous data space, differing from the discrete data space of item permutations. Secondly, the recommendation task is different from conventional generation tasks as the purpose of recommender systems is to fulfill user interests. Lastly, real-life recommender systems require efficiency, posing challenges for the inference of diffusion models. To overcome these challenges, we propose a novel Discrete Conditional Diffusion Reranking (DCDR) framework for recommendation. DCDR extends traditional diffusion models by introducing a discrete forward process with tractable posteriors, which adds noise to item sequences through step-wise discrete operations (e.g., swapping). Additionally, DCDR incorporates a conditional reverse process that generates item sequences conditioned on expected user responses. Extensive offline experiments conducted on public datasets demonstrate that DCDR outperforms state-of-the-art reranking methods. Furthermore, DCDR has been deployed in a real-world video app with over 300 million daily active users, significantly enhancing online recommendation quality.

cs.IR↗

arXiv2023

Tree based Progressive Regression Model for Watch-Time Prediction in Short-video Recommendation

An accurate prediction of watch time has been of vital importance to enhance user engagement in video recommender systems. To achieve this, there are four properties that a watch time prediction framework should satisfy: first, despite its continuous value, watch time is also an ordinal variable and the relative ordering between its values reflects the differences in user preferences. Therefore the ordinal relations should be reflected in watch time predictions. Second, the conditional dependence between the video-watching behaviors should be captured in the model. For instance, one has to watch half of the video before he/she finishes watching the whole video. Third, modeling watch time with a point estimation ignores the fact that models might give results with high uncertainty and this could cause bad cases in recommender systems. Therefore the framework should be aware of prediction uncertainty. Forth, the real-life recommender systems suffer from severe bias amplifications thus an estimation without bias amplification is expected. Therefore we propose TPM for watch time prediction. Specifically, the ordinal ranks of watch time are introduced into TPM and the problem is decomposed into a series of conditional dependent classification tasks which are organized into a tree structure. The expectation of watch time can be generated by traversing the tree and the variance of watch time predictions is explicitly introduced into the objective function as a measurement for uncertainty. Moreover, we illustrate that backdoor adjustment can be seamlessly incorporated into TPM, which alleviates bias amplifications. Extensive offline evaluations have been conducted in public datasets and TPM have been deployed in a real-world video app Kuaishou with over 300 million DAUs. The results indicate that TPM outperforms state-of-the-art approaches and indeed improves video consumption significantly.

cs.IR↗

arXiv2022

The Sphere of Influence of the Bright Central Galaxies in the Diffuse Light of SDSS Clusters

The bright central galaxies (BCGs) dominate the inner portion of the diffuse cluster light, but it is still unclear where the intracluster light (ICL) takes over. To investigate the BCG-ICL transition, we stack the images of ${\sim}3000$ clusters between $0.2{<}z{<}0.3$ in the SDSS $gri$ bands, and measure their BCG+ICL stellar surface mass profile $Σ_{*}^{\texttt{B+I}}$ down to $3{\times}10^4\,M_{\odot}/\mathrm{kpc}^{2}$ at $R{\simeq}1\,\mathrm{Mpc}$ (${\sim}32$ mag/arcsec$^2$ in the $r$-band). We develop a physically-motivated method to decompose $Σ_{*}^{\texttt{B+I}}$ into three components, including an inner de Vaucouleurs' profile, an outer ICL that follows the dark matter distribution measured from weak lensing, and an intriguing transitional component between 70 and 200 kpc. To investigate the origin of this transition, we split the clusters into two subsamples by their BCG stellar mass $M_*^{\mathrm{BCG}}$ (mass enclosed roughly within 50 kpc) while making sure they have the same distribution of satellite richness. The $Σ_{*}^{\texttt{B+I}}$ profiles of the two subsamples differ by more than a factor of two at $R{<}50\,\mathrm{kpc}$, consistent with their 0.34 dex difference in $M_*^{\mathrm{BCG}}$, whereas on scales beyond 400 kpc the two profiles converge to the same amplitudes, suggesting a satellite-stripping origin of the outer ICL. Remarkably, however, the discrepancy between the two $Σ_{*}^{\texttt{B+I}}$ profiles persist at above $50\%$ level on all scales below 200 kpc, thereby revealing the BCG sphere of influence with radius $R_{\mathrm{SOI}}{\simeq}$ 200 kpc. Finally, we speculate that the surprisingly large sphere of influence of the BCG is tied to the elevated escape velocity profile within $r_s$, the characteristic radius of the dark matter haloes.

astro-ph.GA↗