arXiv subjects

Bo Xu

Publications and source records attributed to Bo Xu.

At least 73 records · Page 4Linked to original sources

arXiv2025

MrCoM: A Meta-Regularized World-Model Generalizing Across Multi-Scenarios

Model-based reinforcement learning (MBRL) is a crucial approach to enhance the generalization capabilities and improve the sample efficiency of RL algorithms. However, current MBRL methods focus primarily on building world models for single tasks and rarely address generalization across different scenarios. Building on the insight that dynamics within the same simulation engine share inherent properties, we attempt to construct a unified world model capable of generalizing across different scenarios, named Meta-Regularized Contextual World-Model (MrCoM). This method first decomposes the latent state space into various components based on the dynamic characteristics, thereby enhancing the accuracy of world-model prediction. Further, MrCoM adopts meta-state regularization to extract unified representation of scenario-relevant information, and meta-value regularization to align world-model optimization with policy learning across diverse scenario objectives. We theoretically analyze the generalization error upper bound of MrCoM in multi-scenario settings. We systematically evaluate our algorithm's generalization ability across diverse scenarios, demonstrating significantly better performance than previous state-of-the-art methods.

cs.LG↗

arXiv2025

4D3R: Motion-Aware Neural Reconstruction and Rendering of Dynamic Scenes from Monocular Videos

Novel view synthesis from monocular videos of dynamic scenes with unknown camera poses remains a fundamental challenge in computer vision and graphics. While recent advances in 3D representations such as Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) have shown promising results for static scenes, they struggle with dynamic content and typically rely on pre-computed camera poses. We present 4D3R, a pose-free dynamic neural rendering framework that decouples static and dynamic components through a two-stage approach. Our method first leverages 3D foundational models for initial pose and geometry estimation, followed by motion-aware refinement. 4D3R introduces two key technical innovations: (1) a motion-aware bundle adjustment (MA-BA) module that combines transformer-based learned priors with SAM2 for robust dynamic object segmentation, enabling more accurate camera pose refinement; and (2) an efficient Motion-Aware Gaussian Splatting (MA-GS) representation that uses control points with a deformation field MLP and linear blend skinning to model dynamic motion, significantly reducing computational cost while maintaining high-quality reconstruction. Extensive experiments on real-world dynamic datasets demonstrate that our approach achieves up to 1.8dB PSNR improvement over state-of-the-art methods, particularly in challenging scenarios with large dynamic objects, while reducing computational requirements by 5x compared to previous dynamic scene representations.

cs.CV↗

arXiv2025

$β$-DQN: Improving Deep Q-Learning By Evolving the Behavior

While many sophisticated exploration methods have been proposed, their lack of generality and high computational cost often lead researchers to favor simpler methods like $ε$-greedy. Motivated by this, we introduce $β$-DQN, a simple and efficient exploration method that augments the standard DQN with a behavior function $β$. This function estimates the probability that each action has been taken at each state. By leveraging $β$, we generate a population of diverse policies that balance exploration between state-action coverage and overestimation bias correction. An adaptive meta-controller is designed to select an effective policy for each episode, enabling flexible and explainable exploration. $β$-DQN is straightforward to implement and adds minimal computational overhead to the standard DQN. Experiments on both simple and challenging exploration domains show that $β$-DQN outperforms existing baseline methods across a wide range of tasks, providing an effective solution for improving exploration in deep reinforcement learning.

cs.LG↗

arXiv2025

Self-Verifying Reflection Helps Transformers with CoT Reasoning

Advanced large language models (LLMs) frequently reflect in reasoning chain-of-thoughts (CoTs), where they self-verify the correctness of current solutions and explore alternatives. However, given recent findings that LLMs detect limited errors in CoTs, how reflection contributes to empirical improvements remains unclear. To analyze this issue, in this paper, we present a minimalistic reasoning framework to support basic self-verifying reflection for small transformers without natural language, which ensures analytic clarity and reduces the cost of comprehensive experiments. Theoretically, we prove that self-verifying reflection guarantees improvements if verification errors are properly bounded. Experimentally, we show that tiny transformers, with only a few million parameters, benefit from self-verification in both training and reflective execution, reaching remarkable LLM-level performance in integer multiplication and Sudoku. Similar to LLM results, we find that reinforcement learning (RL) improves in-distribution performance and incentivizes frequent reflection for tiny transformers, yet RL mainly optimizes shallow statistical patterns without faithfully reducing verification errors. In conclusion, integrating generative transformers with discriminative verification inherently facilitates CoT reasoning, regardless of scaling and natural language.

cs.LG↗

arXiv2025

Thinking with Nothinking Calibration: A New In-Context Learning Paradigm in Reasoning Large Language Models

Reasoning large language models (RLLMs) have recently demonstrated remarkable capabilities through structured and multi-step reasoning. While prior research has primarily focused on improving their training and inference strategies, their potential for in-context learning (ICL) remains largely underexplored. To fill this gap, we propose Thinking with Nothinking Calibration (JointThinking), a new ICL paradigm that prompts the model to generate two answers in parallel: one in Thinking mode and the other in Nothinking mode. A second round of Thinking is triggered only when the two initial responses are inconsistent, using a single prompt with two different answers. Extensive experiments across multiple reasoning benchmarks demonstrate that JointThinking significantly outperforms few-shot chain-of-thought (CoT), thinking twice and majority voting. Moreover, it achieves comparable in-distribution performance to training-based SOTA reasoning method, while substantially outperforming on out-of-distribution tasks. We further conduct a systematic analysis of the calibration mechanism, showing the importance of structural thinking diversity and the benefits of consistency check. Additionally, we observe that the performance gap between actual and ideal reasoning narrows as model size increases in the second thinking, indicating the strong scalability of our approach. Finally, we discuss current limitations and outline promising directions for future ICL research in RLLMs.

cs.CL↗

arXiv2025

Ultrahigh-Q chalcogenide micro-racetrack resonators

High-quality factor microresonators are an attractive platform for the study of nonlinear photonics, with diverse applications in communications, sensing, and quantum metrology. The characterization of loss mechanisms and nonlinear properties in a microresonator is a necessity for the development of photonic integrated circuits. Here, we demonstrate a high-quality chalcogenide ($Ge_{23}Sb_{7}S_{70}$) micro-racetrack resonator utilizing Euler curves. The racetrack geometry is studied to minimize loss at both the straight-curved waveguide junction and through the waveguide curve. The material absorption, intrinsic quality factor, and nonlinear index are extracted by a comprehensive model fit to laser wavelength resonance scans. The micro-racetrack resonator possesses an absorption loss of $0.43 dB/m$, an intrinsic quality factor of $4.5 \times 10^6$, and nonlinear index of $1.28 \times 10^{-18} m^2/W$, in a waveguide cross-section less than $1 μm^2$. Our results yield state-of-the-art nonlinear microresonators and establish $Ge_{23}Sb_{7}S_{70}$ as a low-loss PIC platform.

physics.optics↗

arXiv2025

On-Demand Growth of Semiconductor Heterostructures Guided by Physics-Informed Machine Learning

Developing tailored semiconductor heterostructures on demand represents a critical capability for addressing the escalating performance demands in electronic and optoelectronic devices. However, traditional fabrication methods remain constrained by simulation-based design and iterative trial-and-error optimization. Here, we introduce SemiEpi, a self-driving platform designed for molecular beam epitaxy (MBE) to perform multi-step semiconductor heterostructure growth through in-situ monitoring and on-the-fly feedback control. By integrating standard MBE reactors, physics-informed machine learning (ML) models, and parameter initialization, SemiEpi identifies optimal initial conditions and proposes experiments for heterostructure growth, eliminating the need for extensive expertise in MBE processes. As a proof of concept, we demonstrate the optimization of high-density InAs quantum dot (QD) growth with a target emission wavelength of 1240 nm, showcasing the power of SemiEpi. We achieve a QD density of 5 x 10^10 cm^-2, a 1.6-fold increase in photoluminescence (PL) intensity, and a reduced full width at half maximum (FWHM) of 29.13 meV, leveraging in-situ reflective high-energy electron diffraction monitoring with feedback control for adjusting growth temperatures. Taken together, our results highlight the potential of ML-guided systems to address challenges in multi-step heterostructure growth, facilitate the development of a hardware-independent framework, and enhance process repeatability and stability, even without exhaustive knowledge of growth parameters.

cond-mat.mtrl-sci↗

arXiv2025

Enhancing Textual Personality Detection toward Social Media: Integrating Long-term and Short-term Perspectives

Textual personality detection aims to identify personality characteristics by analyzing user-generated content on social media platforms. Extensive psychological literature highlights that personality encompasses both long-term stable traits and short-term dynamic states. However, existing studies often concentrate only on either long-term or short-term personality representations, neglecting the integration of both aspects. This limitation hinders a comprehensive understanding of individuals' personalities, as both stable traits and dynamic states are vital. To bridge this gap, we propose a Dual Enhanced Network (DEN) to jointly model users' long-term and short-term personality traits. In DEN, the Long-term Personality Encoding module models stable long-term personality traits by analyzing consistent patterns in the usage of psychological entities. The Short-term Personality Encoding module captures dynamic short-term personality states by modeling the contextual information of individual posts in real-time. The Bi-directional Interaction module integrates both aspects of personality, creating a cohesive and comprehensive representation of the user's personality. Experimental results on two personality detection datasets demonstrate the effectiveness of the DEN model and underscore the importance of considering both stable and dynamic aspects of personality in textual personality detection.

cs.CL↗

arXiv2025

STAIR: Addressing Stage Misalignment through Temporal-Aligned Preference Reinforcement Learning

Preference-based reinforcement learning (PbRL) bypasses complex reward engineering by learning rewards directly from human preferences, enabling better alignment with human intentions. However, its effectiveness in multi-stage tasks, where agents sequentially perform sub-tasks (e.g., navigation, grasping), is limited by stage misalignment: Comparing segments from mismatched stages, such as movement versus manipulation, results in uninformative feedback, thus hindering policy learning. In this paper, we validate the stage misalignment issue through theoretical analysis and empirical experiments. To address this issue, we propose STage-AlIgned Reward learning (STAIR), which first learns a stage approximation based on temporal distance, then prioritizes comparisons within the same stage. Temporal distance is learned via contrastive learning, which groups temporally close states into coherent stages, without predefined task knowledge, and adapts dynamically to policy changes. Extensive experiments demonstrate STAIR's superiority in multi-stage tasks and competitive performance in single-stage tasks. Furthermore, human studies show that stages approximated by STAIR are consistent with human cognition, confirming its effectiveness in mitigating stage misalignment.

cs.LG↗

arXiv2025

Superconductivity at 22.3 K in Compressed Sodium-intercalated Graphite

Graphite intercalation compounds (GICs) have long been recognized as promising candidates for high-temperature superconductivity by intercalation or charge doping, yet experimental progress has stalled with transition temperatures (Tc) limited to 11.5 K at ambient pressure and 15.1 K at 7.5 GPa in calcium-intercalated graphite over decades. Here, we report robust superconductivity in sodium-intercalated graphite with Tc of 22.3 K, as demonstrated by clear zero-resistance behavior. Our approach involves simply room-temperature grinding of graphite with sodium, followed by slight compression up to 7.1 GPa, circumventing complex synthesis procedures. Through synchrotron X-ray diffraction combined with first-principles calculations, we identify the major superconducting phase as an orthorhombic stage-2 GIC structure with slightly over-stoichiometric composition (Na1+xC8). Electron-phonon coupling calculations reveal that superconductivity primarily emerges from the interactions between out-of-plane carbon electrons and low-frequency Na/C vibrations.The enhancement in Tc establishes sodium as superior for achieving higher-Tc in GICs and illustrates promising pathway for further optimization through compositional and structural tuning.

cond-mat.supr-con↗

arXiv2025

Empowering LLMs with Parameterized Skills for Adversarial Long-Horizon Planning

Recent advancements in Large Language Models(LLMs) have led to the development of LLM-based AI agents. A key challenge is the creation of agents that can effectively ground themselves in complex, adversarial long-horizon environments. Existing methods mainly focus on (1) using LLMs as policies to interact with the environment through generating low-level feasible actions, and (2) utilizing LLMs to generate high-level tasks or language guides to stimulate action generation. However, the former struggles to generate reliable actions, while the latter relies heavily on expert experience to translate high-level tasks into specific action sequences. To address these challenges, we introduce the Plan with Language, Act with Parameter (PLAP) planning framework that facilitates the grounding of LLM-based agents in long-horizon environments. The PLAP method comprises three key components: (1) a skill library containing environment-specific parameterized skills, (2) a skill planner powered by LLMs, and (3) a skill executor converting the parameterized skills into executable action sequences. We implement PLAP in MicroRTS, a long-horizon real-time strategy game that provides an unfamiliar and challenging environment for LLMs. The experimental results demonstrate the effectiveness of PLAP. In particular, GPT-4o-driven PLAP in a zero-shot setting outperforms 80% of baseline agents, and Qwen2-72B-driven PLAP, with carefully crafted few-shot examples, surpasses the top-tier scripted agent, CoacAI. Additionally, we design comprehensive evaluation metrics and test 6 closed-source and 2 open-source LLMs within the PLAP framework, ultimately releasing an LLM leaderboard ranking long-horizon skill planning ability. Our code is available at https://github.com/AI-Research-TeamX/PLAP.

cs.CL↗

arXiv2025

An Efficient Data-Driven Framework for Linear Quadratic Output Feedback Control

Linear quadratic regulator with unmeasurable states and unknown system matrix parameters better aligns with practical scenarios. However, for this problem, balancing the optimality of the resulting controller and the leniency of the algorithm's feasibility conditions remains a non-trivial challenge, as no well-established general method has yet been developed to address this trade-off. To address this gap, this study first develops a comprehensive theoretical framework for state parameterization that equivalently substitutes for unknown states. By analyzing the controllability of consistent systems satisfied by substitute states, this framework quantifies the capability of substitute state data matrices to parameterize unknown closed-loop systems and output feedback controllers, thereby constructing a modified state parameterization form that meets the complete data parameterization condition of Willems' Fundamental Lemma. Leveraging this framework, this study proposes efficient model-free off-policy policy iteration and value iteration algorithms with theoretical guarantees to solve for the optimal output feedback controller. Compared with existing studies, particularly for multi-output problems where existing model-free reinforcement learning algorithms may fail, the proposed method removes redundant information in substitute states and the additional full row rank condition on regression matrices, thereby ensuring the solution of optimal output feedback controllers equivalent to optimal state feedback controllers for multi-output systems. Furthermore, this study pioneers a comprehensive and highly scalable theoretical analysis of state parameterization from a data-driven viewpoint, and the proposed algorithms exhibit significant advantages in implementation conditions, data demand, unknown handling, and convergence speed.

math.OC↗

arXiv2025

INSEva: A Comprehensive Chinese Benchmark for Large Language Models in Insurance

Insurance, as a critical component of the global financial system, demands high standards of accuracy and reliability in AI applications. While existing benchmarks evaluate AI capabilities across various domains, they often fail to capture the unique characteristics and requirements of the insurance domain. To address this gap, we present INSEva, a comprehensive Chinese benchmark specifically designed for evaluating AI systems' knowledge and capabilities in insurance. INSEva features a multi-dimensional evaluation taxonomy covering business areas, task formats, difficulty levels, and cognitive-knowledge dimension, comprising 38,704 high-quality evaluation examples sourced from authoritative materials. Our benchmark implements tailored evaluation methods for assessing both faithfulness and completeness in open-ended responses. Through extensive evaluation of 8 state-of-the-art Large Language Models (LLMs), we identify significant performance variations across different dimensions. While general LLMs demonstrate basic insurance domain competency with average scores above 80, substantial gaps remain in handling complex, real-world insurance scenarios. The benchmark will be public soon.

cs.CL↗

arXiv2025

SERES: Semantic-aware neural reconstruction from sparse views

We propose a semantic-aware neural reconstruction method to generate 3D high-fidelity models from sparse images. To tackle the challenge of severe radiance ambiguity caused by mismatched features in sparse input, we enrich neural implicit representations by adding patch-based semantic logits that are optimized together with the signed distance field and the radiance field. A novel regularization based on the geometric primitive masks is introduced to mitigate shape ambiguity. The performance of our approach has been verified in experimental evaluation. The average chamfer distances of our reconstruction on the DTU dataset can be reduced by 44% for SparseNeuS and 20% for VolRecon. When working as a plugin for those dense reconstruction baselines such as NeuS and Neuralangelo, the average error on the DTU dataset can be reduced by 69% and 68% respectively.

cs.CV↗

arXiv2025

SC2Arena and StarEvolve: Benchmark and Self-Improvement Framework for LLMs in Complex Decision-Making Tasks

Evaluating large language models (LLMs) in complex decision-making is essential for advancing AI's ability for strategic planning and real-time adaptation. However, existing benchmarks for tasks like StarCraft II fail to capture the game's full complexity, such as its complete game context, diverse action spaces, and all playable races. To address this gap, we present SC2Arena, a benchmark that fully supports all playable races, low-level action spaces, and optimizes text-based observations to tackle spatial reasoning challenges. Complementing this, we introduce StarEvolve, a hierarchical framework that integrates strategic planning with tactical execution, featuring iterative self-correction and continuous improvement via fine-tuning on high-quality gameplay data. Its key components include a Planner-Executor-Verifier structure to break down gameplay, and a scoring system for selecting high-quality training samples. Comprehensive analysis using SC2Arena provides valuable insights into developing generalist agents that were not possible with previous benchmarks. Experimental results also demonstrate that our proposed StarEvolve achieves superior performance in strategic planning. Our code, environment, and algorithms are publicly available.

cs.LG↗

arXiv2025

DPMT: Dual Process Multi-scale Theory of Mind Framework for Real-time Human-AI Collaboration

Real-time human-artificial intelligence (AI) collaboration is crucial yet challenging, especially when AI agents must adapt to diverse and unseen human behaviors in dynamic scenarios. Existing large language model (LLM) agents often fail to accurately model the complex human mental characteristics such as domain intentions, especially in the absence of direct communication. To address this limitation, we propose a novel dual process multi-scale theory of mind (DPMT) framework, drawing inspiration from cognitive science dual process theory. Our DPMT framework incorporates a multi-scale theory of mind (ToM) module to facilitate robust human partner modeling through mental characteristic reasoning. Experimental results demonstrate that DPMT significantly enhances human-AI collaboration, and ablation studies further validate the contributions of our multi-scale ToM in the slow system.

cs.LG↗

arXiv2025

IP2: Entity-Guided Interest Probing for Personalized News Recommendation

News recommender systems aim to provide personalized news reading experiences for users based on their reading history. Behavioral science studies suggest that screen-based news reading contains three successive steps: scanning, title reading, and then clicking. Adhering to these steps, we find that intra-news entity interest dominates the scanning stage, while the inter-news entity interest guides title reading and influences click decisions. Unfortunately, current methods overlook the unique utility of entities in news recommendation. To this end, we propose a novel method called IP2 to probe entity-guided reading interest at both intra- and inter-news levels. At the intra-news level, a Transformer-based entity encoder is devised to aggregate mentioned entities in the news title into one signature entity. Then, a signature entity-title contrastive pre-training is adopted to initialize entities with proper meanings using the news story context, which in the meantime facilitates us to probe for intra-news entity interest. As for the inter-news level, a dual tower user encoder is presented to capture inter-news reading interest from both the title meaning and entity sides. In addition to highlighting the contribution of inter-news entity guidance, a cross-tower attention link is adopted to calibrate title reading interest using inter-news entity interest, thus further aligning with real-world behavior. Extensive experiments on two real-world datasets demonstrate that our IP2 achieves state-of-the-art performance in news recommendation.

cs.IR↗

arXiv2025

3DGS_LSR:Large_Scale Relocation for Autonomous Driving Based on 3D Gaussian Splatting

In autonomous robotic systems, precise localization is a prerequisite for safe navigation. However, in complex urban environments, GNSS positioning often suffers from signal occlusion and multipath effects, leading to unreliable absolute positioning. Traditional mapping approaches are constrained by storage requirements and computational inefficiency, limiting their applicability to resource-constrained robotic platforms. To address these challenges, we propose 3DGS-LSR: a large-scale relocalization framework leveraging 3D Gaussian Splatting (3DGS), enabling centimeter-level positioning using only a single monocular RGB image on the client side. We combine multi-sensor data to construct high-accuracy 3DGS maps in large outdoor scenes, while the robot-side localization requires just a standard camera input. Using SuperPoint and SuperGlue for feature extraction and matching, our core innovation is an iterative optimization strategy that refines localization results through step-by-step rendering, making it suitable for real-time autonomous navigation. Experimental validation on the KITTI dataset demonstrates our 3DGS-LSR achieves average positioning accuracies of 0.026m, 0.029m, and 0.081m in town roads, boulevard roads, and traffic-dense highways respectively, significantly outperforming other representative methods while requiring only monocular RGB input. This approach provides autonomous robots with reliable localization capabilities even in challenging urban environments where GNSS fails.

cs.RO↗