arXiv subjects

Wei Xu

Publications and source records attributed to Wei Xu.

At least 163 records · Page 9Linked to original sources

arXiv2025

Learning Multi-Stage Pick-and-Place with a Legged Mobile Manipulator

Quadruped-based mobile manipulation presents significant challenges in robotics due to the diversity of required skills, the extended task horizon, and partial observability. After presenting a multi-stage pick-and-place task as a succinct yet sufficiently rich setup that captures key desiderata for quadruped-based mobile manipulation, we propose an approach that can train a visuo-motor policy entirely in simulation, and achieve nearly 80\% success in the real world. The policy efficiently performs search, approach, grasp, transport, and drop into actions, with emerged behaviors such as re-grasping and task chaining. We conduct an extensive set of real-world experiments with ablation studies highlighting key techniques for efficient training and effective sim-to-real transfer. Additional experiments demonstrate deployment across a variety of indoor and outdoor environments. Demo videos and additional resources are available on the project page: https://horizonrobotics.github.io/gail/SLIM.

cs.RO↗

arXiv2025

WindFM: An Open-Source Foundation Model for Zero-Shot Wind Power Forecasting

High-quality wind power forecasting is crucial for the operation of modern power grids. However, prevailing data-driven paradigms either train a site-specific model which cannot generalize to other locations or rely on fine-tuning of general-purpose time series foundation models which are difficult to incorporate domain-specific data in the energy sector. This paper introduces WindFM, a lightweight and generative Foundation Model designed specifically for probabilistic wind power forecasting. WindFM employs a discretize-and-generate framework. A specialized time-series tokenizer first converts continuous multivariate observations into discrete, hierarchical tokens. Subsequently, a decoder-only Transformer learns a universal representation of wind generation dynamics by autoregressively pre-training on these token sequences. Using the comprehensive WIND Toolkit dataset comprising approximately 150 billion time steps from more than 126,000 sites, WindFM develops a foundational understanding of the complex interplay between atmospheric conditions and power output. Extensive experiments demonstrate that our compact 8.1M parameter model achieves state-of-the-art zero-shot performance on both deterministic and probabilistic tasks, outperforming specialized models and larger foundation models without any fine-tuning. In particular, WindFM exhibits strong adaptiveness under out-of-distribution data from a different continent, demonstrating the robustness and transferability of its learned representations. Our pre-trained model is publicly available at https://github.com/shiyu-coder/WindFM.

cs.LG↗

arXiv2025

Unified Representation Learning for Multi-Intent Diversity and Behavioral Uncertainty in Recommender Systems

This paper addresses the challenge of jointly modeling user intent diversity and behavioral uncertainty in recommender systems. A unified representation learning framework is proposed. The framework builds a multi-intent representation module and an uncertainty modeling mechanism. It extracts multi-granularity interest structures from user behavior sequences. Behavioral ambiguity and preference fluctuation are captured using Bayesian distribution modeling. In the multi-intent modeling part, the model introduces multiple latent intent vectors. These vectors are weighted and fused using an attention mechanism to generate semantically rich representations of long-term user preferences. In the uncertainty modeling part, the model learns the mean and covariance of behavior representations through Gaussian distributions. This reflects the user's confidence in different behavioral contexts. Next, a learnable fusion strategy is used to combine long-term intent and short-term behavior signals. This produces the final user representation, improving both recommendation accuracy and robustness. The method is evaluated on standard public datasets. Experimental results show that it outperforms existing representative models across multiple metrics. It also demonstrates greater stability and adaptability under cold-start and behavioral disturbance scenarios. The approach alleviates modeling bottlenecks faced by traditional methods when dealing with complex user behavior. These findings confirm the effectiveness and practical value of the unified modeling strategy in real-world recommendation tasks.

cs.IR↗

arXiv2025

Communication Efficient Robotic Mixed Reality with Gaussian Splatting Cross-Layer Optimization

Realizing low-cost communication in robotic mixed reality (RoboMR) systems presents a challenge, due to the necessity of uploading high-resolution images through wireless channels. This paper proposes Gaussian splatting (GS) RoboMR (GSMR), which enables the simulator to opportunistically render a photo-realistic view from the robot's pose by calling ``memory'' from a GS model, thus reducing the need for excessive image uploads. However, the GS model may involve discrepancies compared to the actual environments. To this end, a GS cross-layer optimization (GSCLO) framework is further proposed, which jointly optimizes content switching (i.e., deciding whether to upload image or not) and power allocation (i.e., adjusting to content profiles) across different frames by minimizing a newly derived GSMR loss function. The GSCLO problem is addressed by an accelerated penalty optimization (APO) algorithm that reduces computational complexity by over $10$x compared to traditional branch-and-bound and search algorithms. Moreover, variants of GSCLO are presented to achieve robust, low-power, and multi-robot GSMR. Extensive experiments demonstrate that the proposed GSMR paradigm and GSCLO method achieve significant improvements over existing benchmarks on both wheeled and legged robots in terms of diverse metrics in various scenarios. For the first time, it is found that RoboMR can be achieved with ultra-low communication costs, and mixture of data is useful for enhancing GS performance in dynamic scenarios.

cs.RO↗

arXiv2025

Family of Unconventional Superconductivities in Crystalline Graphene

Unconventional superconductors exhibit multiple broken symmetries and exceed the range of the Bardeen-Cooper-Schrieffer (BCS) theory. For instance, time-reversal symmetry can be broken in addition to the gauge symmetry, resulting in superconductors that can be enhanced or induced by a magnetic field. However, such unconventional superconductivities are more vulnerable to impurities than their BCS counterparts, requiring highly ordered and clean material systems to observe them. Crystalline rhombohedral multilayer graphene is a promising platform to explore unconventional superconductivity due to its superior material quality and gate-tunable strong correlation effects. Here we report transport measurements of rhombohedral tetralayer and pentalayer graphene, where a spectrum of superconductivities in a clean limit are observed. Three of them (SC2-4) show highly unusual enhancements by magnetic fields: 1. SC2 is strengthened by an in-plane field; 2. SC3 is boosted by a small out-of-plane field; 3. SC4 is induced by an in-plane field. All these superconductors are robust against an in-plane field up to 8.5 Tesla, exceeding the Pauli limit of conventional superconductors by tens of times and suggesting their unconventional nature. Moreover, we observed that proximitized spin-orbit coupling generates a plethora of new superconductors in the phase diagram, while maintaining the high quality of bare rhombohedral graphene. Our work establishes a family of new superconductors in rhombohedral multilayer graphene, which also provides an ideal platform to engineer non-Abelian quasiparticles by proximitizing with quantum anomalous Hall states existing in the same material system.

cond-mat.mes-hall↗

arXiv2025

Joint Planning and Operations of Wind Power under Decision-dependent Uncertainty

We study a joint wind farm planning and operational scheduling problem under decision-dependent uncertainty. The objective is to determine the optimal number of wind turbines at each location to minimize total cost, including both investment and operational expenses. Due to the stochastic nature and geographical heterogeneity of wind power, fluctuations across dispersed wind farms can partially offset one another, thereby influencing the distribution of aggregated wind power generation-a phenomenon known as the smoothing effect. Effectively harnessing this effect requires strategic capacity allocation, which introduces decision-dependent uncertainty into the planning process. To address this challenge, we propose a two-stage distributionally robust optimization model with a decision-dependent Wasserstein ambiguity set, in which both the distribution and the radius are modeled as functions of the planning decisions, reflecting the statistical characteristics of wind power resources. Then, we reformulate the model as a mixed-integer second-order cone program, and the optimal objective value provides a probabilistic guarantee on the out-of-sample performance. To improve computational efficiency, we develop a constraint generation based solution framework that accelerates the solution procedure by hundreds of times. Numerical experiments using different datasets validate the effectiveness of the solution framework and demonstrate the superior performance of the proposed model.

math.OC↗

arXiv2025

ROSE: A Reward-Oriented Data Selection Framework for LLM Task-Specific Instruction Tuning

Instruction tuning has underscored the significant potential of large language models (LLMs) in producing more human controllable and effective outputs in various domains. In this work, we focus on the data selection problem for task-specific instruction tuning of LLMs. Prevailing methods primarily rely on the crafted similarity metrics to select training data that aligns with the test data distribution. The goal is to minimize instruction tuning loss on the test data, ultimately improving performance on the target task. However, it has been widely observed that instruction tuning loss (i.e., cross-entropy loss for next token prediction) in LLMs often fails to exhibit a monotonic relationship with actual task performance. This misalignment undermines the effectiveness of current data selection methods for task-specific instruction tuning. To address this issue, we introduce ROSE, a novel Reward-Oriented inStruction data sElection method which leverages pairwise preference loss as a reward signal to optimize data selection for task-specific instruction tuning. Specifically, ROSE adapts an influence formulation to approximate the influence of training data points relative to a few-shot preference validation set to select the most task-related training data points. Experimental results show that by selecting just 5\% of the training data using ROSE, our approach can achieve competitive results compared to fine-tuning with the full training dataset, and it surpasses other state-of-the-art data selection methods for task-specific instruction tuning. Our qualitative analysis further confirms the robust generalizability of our method across multiple benchmark datasets and diverse model architectures.

cs.LG↗

arXiv2025

An HCAI Methodological Framework (HCAI-MF): Putting It Into Action to Enable Human-Centered AI

Human-centered artificial intelligence (HCAI) is a design philosophy that prioritizes humans in the design, development, deployment, and use of AI systems, aiming to maximize AI's benefits while mitigating its negative impacts. Despite its growing prominence in literature, the lack of methodological guidance for its implementation poses challenges to HCAI practice. To address this gap, this paper proposes a comprehensive HCAI methodological framework (HCAI-MF) comprising five key components: HCAI requirement hierarchy, approach and method taxonomy, process, interdisciplinary collaboration approach, and multi-level design paradigms. A case study demonstrates HCAI-MF's practical implications, while the paper also analyzes implementation challenges. Actionable recommendations and a "three-layer" HCAI implementation strategy are provided to address these challenges and guide future evolution of HCAI-MF. HCAI-MF is presented as a systematic and executable methodology capable of overcoming current gaps, enabling effective design, development, deployment, and use of AI systems, and advancing HCAI practice.

cs.HC↗

arXiv2025

Human-Centered Human-AI Interaction (HC-HAII): A Human-Centered AI Perspective

This chapter systematically promotes an emerging interdisciplinary field of human-artificial intelligence interaction (human-AI interaction, HAII) from a human-centered AI (HCAI) perspective. It introduces a framework of human-centered HAII (HC-HAII). HC-HAII places humans at the core of HAII research and applications, emphasizing the importance of adopting a human-centered approach over a technology-centered one. The chapter presents the HC-HAII methodology, including human-centered methods, process, interdisciplinary teams, and multi-level design paradigms. It also highlights key research challenges and future directions. As the first chapter, this chapter also provides a structural overview of this book, which brings together contributions from an interdisciplinary community of researchers and practitioners to advance the theory, methodology, and applications of HCAI in diverse domains of HAII. The purpose of this chapter is to provide a fundamental framework for this book, centered on HAII research and applications based on the HCAI approach, which will pave the way for the content of subsequent chapters.

cs.HC↗

arXiv2025

Evaluating LLMs on Chinese Idiom Translation

Idioms, whose figurative meanings usually differ from their literal interpretations, are common in everyday language, especially in Chinese, where they often contain historical references and follow specific structural patterns. Despite recent progress in machine translation with large language models, little is known about Chinese idiom translation. In this work, we introduce IdiomEval, a framework with a comprehensive error taxonomy for Chinese idiom translation. We annotate 900 translation pairs from nine modern systems, including GPT-4o and Google Translate, across four domains: web, news, Wikipedia, and social media. We find these systems fail at idiom translation, producing incorrect, literal, partial, or even missing translations. The best-performing system, GPT-4, makes errors in 28% of cases. We also find that existing evaluation metrics measure idiom quality poorly with Pearson correlation below 0.48 with human ratings. We thus develop improved models that achieve F$_1$ scores of 0.68 for detecting idiom translation errors.

cs.CL↗

arXiv2025

A Framework of Arithmetic-Level Variable Precision Computing for In-Memory Architecture: Case Study in MIMO Signal Processing

Computational complexity poses a significant challenge in wireless communication. Most existing attempts aim to reduce it through algorithm-specific approaches. However, the precision of computing, which directly relates to both computing performance and computational complexity, is a dimension that is fundamental but rarely explored in the literature. With the emerging architecture of in-memory computing, variable precision computing (VPC) is enabled, allowing each arithmetic operation to be processed with a distinct and specifically optimized computing precision. In this paper, we establish a unified framework of arithmetic-level variable precision computing (AL-VPC), which aims to determine the optimized computing precision for each arithmetic operation. We first develop an arithmetic propagation error model exploiting stochastic analysis, and then formulate a mathematical optimization problem to strike balance between computing performance and computational complexity. Two algorithms, namely, offline VPC and online VPC, are proposed to solve the problem considering various practical concerns. Particularly, in a case study on zero-forcing (ZF) precoding, we reveal the Pareto boundary between computing performance and complexity, which exhibits up to a 60% sum-rate enhancement or equivalently up to a 30% complexity reduction compared to the traditional fixed-length methods.

eess.SP↗

arXiv2025

Energy-Efficient Hybrid Beamfocusing for Near-Field Integrated Sensing and Communication

Integrated sensing and communication (ISAC) is a pivotal component of sixth-generation (6G) wireless networks, leveraging high-frequency bands and massive multiple-input multiple-output (M-MIMO) to deliver both high-capacity communication and high-precision sensing. However, these technological advancements lead to significant near-field effects, while the implementation of M-MIMO \mbox{is associated with considerable} hardware costs and escalated power consumption. In this context, hybrid architecture designs emerge as both hardware-efficient and energy-efficient solutions. Motivated by these considerations, we investigate the design of energy-efficient hybrid beamfocusing for near-field ISAC under two distinct target scenarios, i.e., a point target and an extended target. Specifically, we first derive the closed-form Cramér-Rao bound (CRB) of joint angle-and-distance estimation for the point target and the Bayesian CRB (BCRB) of the target response matrix for the extended target. Building on these derived results, we minimize the CRB/BCRB by optimizing the transmit beamfocusing, while ensuring the energy efficiency (EE) of the system and the quality-of-service (QoS) for communication users. To address the resulting \mbox{nonconvex problems}, we first utilize a penalty-based successive convex approximation technique with a fully-digital beamformer to obtain a suboptimal solution. Then, we propose an efficient alternating \mbox{optimization} algorithm to design the analog-and-digital beamformer. \mbox{Simulation} results indicate that joint distance-and-angle estimation is feasible in the near-field region. However, the adopted hybrid architectures inevitably degrade the accuracy of distance estimation, compared with their fully-digital counterparts. Furthermore, enhancements in system EE would compromise the accuracy of target estimation, unveiling a nontrivial tradeoff.

cs.IT↗

arXiv2025

Kronos: A Foundation Model for the Language of Financial Markets

The success of large-scale pre-training paradigm, exemplified by Large Language Models (LLMs), has inspired the development of Time Series Foundation Models (TSFMs). However, their application to financial candlestick (K-line) data remains limited, often underperforming non-pre-trained architectures. Moreover, existing TSFMs often overlook crucial downstream tasks such as volatility prediction and synthetic data generation. To address these limitations, we propose Kronos, a unified, scalable pre-training framework tailored to financial K-line modeling. Kronos introduces a specialized tokenizer that discretizes continuous market information into token sequences, preserving both price dynamics and trade activity patterns. We pre-train Kronos using an autoregressive objective on a massive, multi-market corpus of over 12 billion K-line records from 45 global exchanges, enabling it to learn nuanced temporal and cross-asset representations. Kronos excels in a zero-shot setting across a diverse set of financial tasks. On benchmark datasets, Kronos boosts price series forecasting RankIC by 93% over the leading TSFM and 87% over the best non-pre-trained baseline. It also achieves a 9% lower MAE in volatility forecasting and a 22% improvement in generative fidelity for synthetic K-line sequences. These results establish Kronos as a robust, versatile foundation model for end-to-end financial time series analysis. Our pre-trained model is publicly available at https://github.com/shiyu-coder/Kronos.

q-fin.ST↗

arXiv2025

Tabular Data Understanding with LLMs: A Survey of Recent Advances and Challenges

Tables have gained significant attention in large language models (LLMs) and multimodal large language models (MLLMs) due to their complex and flexible structure. Unlike linear text inputs, tables are two-dimensional, encompassing formats that range from well-structured database tables to complex, multi-layered spreadsheets, each with different purposes. This diversity in format and purpose has led to the development of specialized methods and tasks, instead of universal approaches, making navigation of table understanding tasks challenging. To address these challenges, this paper introduces key concepts through a taxonomy of tabular input representations and an introduction of table understanding tasks. We highlight several critical gaps in the field that indicate the need for further research: (1) the predominance of retrieval-focused tasks that require minimal reasoning beyond mathematical and logical operations; (2) significant challenges faced by models when processing complex table structures, large-scale tables, length context, or multi-table scenarios; and (3) the limited generalization of models across different tabular representations and formats.

cs.CL↗

arXiv2025

Beyond the Reported Cutoff: Where Large Language Models Fall Short on Financial Knowledge

Large Language Models (LLMs) are frequently utilized as sources of knowledge for question-answering. While it is known that LLMs may lack access to real-time data or newer data produced after the model's cutoff date, it is less clear how their knowledge spans across historical information. In this study, we assess the breadth of LLMs' knowledge using financial data of U.S. publicly traded companies by evaluating more than 197k questions and comparing model responses to factual data. We further explore the impact of company characteristics, such as size, retail investment, institutional attention, and readability of financial filings, on the accuracy of knowledge represented in LLMs. Our results reveal that LLMs are less informed about past financial performance, but they display a stronger awareness of larger companies and more recent information. Interestingly, at the same time, our analysis also reveals that LLMs are more likely to hallucinate for larger companies, especially for data from more recent years. The code, prompts, and model outputs are available on GitHub.

cs.CL↗

arXiv2025

MegatronApp: Efficient and Comprehensive Management on Distributed LLM Training

The rapid escalation in the parameter count of large language models (LLMs) has transformed model training from a single-node endeavor into a highly intricate, cross-node activity. While frameworks such as Megatron-LM successfully integrate tensor (TP), pipeline (PP), and data (DP) parallelism to enable trillion-parameter training, they simultaneously expose practitioners to unprecedented systems-level challenges in performance optimization, diagnosis, and interpretability. MegatronApp is an open-source toolchain expressly designed to meet these challenges. It introduces four orthogonal, yet seamlessly composable modules--MegaScan, MegaFBD, MegaDPP, and MegaScope--that collectively elevate the reliability, efficiency, and transparency of production-scale training. This paper presents the motivation, architecture, and distinctive contributions of each module, and elucidates how their synergistic integration augments the Megatron-LM ecosystem.

cs.DC↗

arXiv2025

Pressure-Induced Low-Spin State Destabilization and Piezo-Chromic Effect in an Iron(II) Spin Crossover Complex with Pyrazol-Pyridine-Triazolate Coordination Core

Rapidly developing science and technology demand new materials with versatile and promising properties for practical applications. In this context, pseudo-octahedral iron(II) spin crossover (SCO) complexes are particularly appealing - not only for their fundamental scientific interest but also for their potential as key components in the development of multifunctional switchable molecular materials and novel technological applications. This work presents the synthesis and structure of a new mononuclear SCO complex [FeII(L)2]0*nMeOH (n = 2, 0) where L is the asymmetrically substituted tridentate ligand [4-trifluoromethylphenyl-(1H-1,2,4-triazol-5-yl)-6-(1H-pyrazol-1-yl)pyridine]. Due to high trigonal distortion, the solvated form (n = 2) remains high spin (HS) at all temperatures. In contrast, the more regular Oh geometry of the unsolvated form, 4CF3, favors a complete spin transition (ST) at room temperature, which has been investigated, in the pressure interval 0-0.64 GPa, by means of its magnetic and optical properties. Contrary to intuition and experience, the increase of pressure on 4CF3 denotes a radically abnormal behavior of this ST, involving: i) decrease of the characteristic temperatures, ii) increase of the high-spin molar fraction in the temperature range where the low-spin state is stable at ambient pressure; iii) increase of the thermal hysteresis width; and iv) above certain threshold pressure, full stabilization of the high-spin state. All these observations have been explained in the framework of a thermodynamic that model based on the elastic interactions.

cond-mat.mtrl-sci↗

arXiv2025

Robust ISAC Transceiver Beamforming Design under Low-Resolution AD/DA Converters

In this letter, we investigate the robust beamforming design for an integrated sensing and communication (ISAC) system featuring low-resolution digital-to-analog converters (DACs) and analog-to-digital converters (ADCs). Taking into account quantization noise, we aim at maximizing the radar signal-to-quantization-plus-noise ratio (SQNR) while guaranteeing the minimum required signal-to-quantization-plus-interference-plus-noise ratio (SQINR) for communication users. To address this nonconvex design problem, we first examine a scenario involving a point target and uniform-resolution DACs, where the globally optimal solution is obtained by applying the semidefinite relaxation (SDR) technique. For more general scenarios, including those with mixed-DACs and/or an extended target, we develop a low-complexity majorization-minimization (MM)-based algorithm to tackle the problem iteratively. Compared to the non-robust algorithm, the proposed algorithm demonstrates improved detection performance under practical quantization. Simulation results confirm the robustness and efficacy of our proposed algorithm in low-resolution quantization scenarios.

eess.SP↗