arXiv subjects

Fei Liu

Publications and source records attributed to Fei Liu.

At least 109 records · Page 6Linked to original sources

arXiv2025

Knowledge-aware Diffusion-Enhanced Multimedia Recommendation

Multimedia recommendations aim to use rich multimedia content to enhance historical user-item interaction information, which can not only indicate the content relatedness among items but also reveal finer-grained preferences of users. In this paper, we propose a Knowledge-aware Diffusion-Enhanced architecture using contrastive learning paradigms (KDiffE) for multimedia recommendations. Specifically, we first utilize original user-item graphs to build an attention-aware matrix into graph neural networks, which can learn the importance between users and items for main view construction. The attention-aware matrix is constructed by adopting a random walk with a restart strategy, which can preserve the importance between users and items to generate aggregation of attention-aware node features. Then, we propose a guided diffusion model to generate strongly task-relevant knowledge graphs with less noise for constructing a knowledge-aware contrastive view, which utilizes user embeddings with an edge connected to an item to guide the generation of strongly task-relevant knowledge graphs for enhancing the item's semantic information. We perform comprehensive experiments on three multimedia datasets that reveal the effectiveness of our KDiffE and its components on various state-of-the-art methods. Our source codes are available https://github.com/1453216158/KDiffE.

cs.MM↗

arXiv2025

Binary Response Forecasting under a Factor-Augmented Framework

In this paper, we propose a novel factor-augmented forecasting regression model with a binary response variable. We develop a maximum likelihood estimation method for the regression parameters and establish the asymptotic properties of the resulting estimators. Monte Carlo simulation results show that the proposed estimation method performs very well in finite samples. Finally, we demonstrate the usefulness of the proposed model through an application to U.S. recession forecasting. The proposed model consistently outperforms conventional Probit regression across both in-sample and out-of-sample exercises, by effectively utilizing high-dimensional information through latent factors.

econ.EM↗

arXiv2025

Panel Data Estimation and Inference: Homogeneity versus Heterogeneity

In this paper, we define an underlying data generating process that allows for different magnitudes of cross-sectional dependence, along with time series autocorrelation. This is achieved via high-dimensional moving average processes of infinite order (HDMA($\infty$)). Our setup and investigation integrates and enhances homogenous and heterogeneous panel data estimation and testing in a unified way. To study HDMA($\infty$), we extend the Beveridge-Nelson decomposition to a high-dimensional time series setting, and derive a complete toolkit set. We exam homogeneity versus heterogeneity using Gaussian approximation, a prevalent technique for establishing uniform inference. For post-testing inference, we derive central limit theorems through Edgeworth expansions for both homogenous and heterogeneous settings. Additionally, we showcase the practical relevance of the established asymptotic theory by (1). connecting our results with the literature on grouping structure analysis, (2). examining a nonstationary panel data generating process, and (3). revisiting the common correlated effects (CCE) estimators. Finally, we verify our theoretical findings via extensive numerical studies using both simulated and real datasets.

econ.EM↗

arXiv2025

RL4CO: an Extensive Reinforcement Learning for Combinatorial Optimization Benchmark

Combinatorial optimization (CO) is fundamental to several real-world applications, from logistics and scheduling to hardware design and resource allocation. Deep reinforcement learning (RL) has recently shown significant benefits in solving CO problems, reducing reliance on domain expertise and improving computational efficiency. However, the absence of a unified benchmarking framework leads to inconsistent evaluations, limits reproducibility, and increases engineering overhead, raising barriers to adoption for new researchers. To address these challenges, we introduce RL4CO, a unified and extensive benchmark with in-depth library coverage of 27 CO problem environments and 23 state-of-the-art baselines. Built on efficient software libraries and best practices in implementation, RL4CO features modularized implementation and flexible configurations of diverse environments, policy architectures, RL algorithms, and utilities with extensive documentation. RL4CO helps researchers build on existing successes while exploring and developing their own designs, facilitating the entire research process by decoupling science from heavy engineering. We finally provide extensive benchmark studies to inspire new insights and future work. RL4CO has already attracted numerous researchers in the community and is open-sourced at https://github.com/ai4co/rl4co.

cs.LG↗

arXiv2025

DeFine: Decision-Making with Analogical Reasoning over Factor Profiles

LLMs are ideal for decision-making thanks to their ability to reason over long contexts. However, challenges arise when processing speech transcripts that describe complex scenarios, as they are verbose and include repetition, hedging, and vagueness. E.g., during a company's earnings call, an executive might project a positive revenue outlook to reassure investors, despite uncertainty regarding future earnings. It is crucial for LLMs to incorporate this uncertainty systematically when making decisions. In this paper, we introduce \textsc{DeFine}, a modular framework that constructs probabilistic factor profiles from complex scenarios. It then integrates these profiles with analogical reasoning, leveraging insights from similar past experiences to guide LLMs in making critical decisions in new situations. Our framework separates the tasks of quantifying uncertainty and incorporating it into LLM decision-making. This approach is particularly useful in areas such as consulting and financial deliberation, where making decisions under uncertainty is vital.

cs.CL↗

arXiv2025

Stable Tracking-in-the-Loop Control of Cable-Driven Surgical Manipulators under Erroneous Kinematic Chains

Remote Center of Motion (RCM) robotic manipulators have revolutionized Minimally Invasive Surgery, enabling precise, dexterous surgical manipulation within the patient's body cavity without disturbing the insertion point on the patient. Accurate RCM tool control is vital for incorporating autonomous subtasks like suturing, blood suction, and tumor resection into robotic surgical procedures, reducing surgeon fatigue and improving patient outcomes. However, these cable-driven systems are subject to significant joint reading errors, corrupting the kinematics computation necessary to perform control. Although visual tracking with endoscopic cameras can correct errors on in-view joints, errors in the kinematic chain prior to the insertion point are irreparable because they remain out of view. No prior work has characterized the stability of control under these conditions. We fill this gap by designing a provably stable tracking-in-the-loop controller for the out-of-view portion of the RCM manipulator kinematic chain. We additionally incorporate this controller into a bilevel control scheme for the full kinematic chain. We rigorously benchmark our method in simulated and real world settings to verify our theoretical findings. Our work provides key insights into the next steps required for the transition from teleoperated to autonomous surgery.

cs.RO↗

arXiv2025

LRM-1B: Towards Large Routing Model

Vehicle routing problems (VRPs) are central to combinatorial optimization with significant practical implications. Recent advancements in neural combinatorial optimization (NCO) have demonstrated promising results by leveraging neural networks to solve VRPs, yet the exploration of model scaling within this domain remains underexplored. Inspired by the success of model scaling in large language models (LLMs), this study introduces a Large Routing Model with 1 billion parameters (LRM-1B), designed to address diverse VRP scenarios. We present a comprehensive evaluation of LRM-1B across multiple problem variants, distributions, and sizes, establishing state-of-the-art results. Our findings reveal that LRM-1B not only adapts to different VRP challenges but also showcases superior performance, outperforming existing models. Additionally, we explore the scaling behavior of neural routing models from 1M to 1B parameters. Our analysis confirms power-law between multiple model factors and performance, offering critical insights into the optimal configurations for foundation neural routing solvers.

cs.LG↗

arXiv2025

Computational Design of Two-Dimensional MoSi$_2$N$_4$ Family Field-Effect Transistor for Future Ångström-Scale CMOS Technology Nodes

Advancing complementary metal-oxide-semiconductor (CMOS) technology into the sub-1-nm angström-scale technology nodes is expected to involve alternative semiconductor channel materials, as silicon transistors encounter severe performance degradation at physical gate lengths below 10 nm. Two-dimensional (2D) semiconductors have emerged as strong candidates for overcoming short-channel effects due to their atomically thin bodies, which inherently suppress electrostatic leakage and improve gate control in aggressively scaled field-effect transistors (FETs). Among the growing library of 2D materials, the MoSi$_2$N$_4$ family -- a synthetic septuple-layered materials -- has attracted increasing attention for its remarkable ambient stability, suitable bandgaps, and favorable carrier transport characteristics, making it a promising platform for next-generation transistors. While experimental realization of sub-10-nm 2D FETs remains technologically demanding, computational device simulation using first-principles density functional theory combined with nonequilibrium Green's function transport simulations provide a powerful and cost-effective route for exploring the performance limits and optimal design of ultrascaled FET. This review consolidates the current progress in the computational design of MoSi$_2$N$_4$ family FETs. We review the physical properties of MoSi$_2$N$_4$ that makes them compelling candidates for transistor applications, as well as the simulated device performance and optimization strategy of MoSi$_2$N$_4$ family FETs. Finally, we identify key challenges and research gaps, and outline future directions that could accelerate the practical deployment of MoSi$_2$N$_4$ family FET in the angström-scale CMOS era.

cond-mat.mtrl-sci↗

arXiv2025

PlanGenLLMs: A Modern Survey of LLM Planning Capabilities

LLMs have immense potential for generating plans, transforming an initial world state into a desired goal state. A large body of research has explored the use of LLMs for various planning tasks, from web navigation to travel planning and database querying. However, many of these systems are tailored to specific problems, making it challenging to compare them or determine the best approach for new tasks. There is also a lack of clear and consistent evaluation criteria. Our survey aims to offer a comprehensive overview of current LLM planners to fill this gap. It builds on foundational work by Kartam and Wilkins (1990) and examines six key performance criteria: completeness, executability, optimality, representation, generalization, and efficiency. For each, we provide a thorough analysis of representative works and highlight their strengths and weaknesses. Our paper also identifies crucial future directions, making it a valuable resource for both practitioners and newcomers interested in leveraging LLM planning to support agentic workflows.

cs.AI↗

arXiv2025

HARBOR: Exploring Persona Dynamics in Multi-Agent Competition

We investigate factors contributing to LLM agents' success in competitive multi-agent environments, using auctions as a testbed where agents bid to maximize profit. The agents are equipped with bidding domain knowledge, distinct personas that reflect item preferences, and a memory of auction history. Our work extends the classic auction scenario by creating a realistic environment where multiple agents bid on houses, weighing aspects such as size, location, and budget to secure the most desirable homes at the lowest prices. Particularly, we investigate three key questions: (a) How does a persona influence an agent's behavior in a competitive setting? (b) Can an agent effectively profile its competitors' behavior during auctions? (c) How can persona profiling be leveraged to create an advantage using strategies such as theory of mind? Through a series of experiments, we analyze the behaviors of LLM agents and shed light on new findings. Our testbed, called HARBOR, offers a valuable platform for deepening our understanding of multi-agent workflows in competitive environments.

cs.MA↗

arXiv2025

Enhancing Character-Level Understanding in LLMs through Token Internal Structure Learning

Tokenization methods like Byte-Pair Encoding (BPE) enhance computational efficiency in large language models (LLMs) but often obscure internal character structures within tokens. This limitation hinders LLMs' ability to predict precise character positions, which is crucial in tasks like Chinese Spelling Correction (CSC) where identifying the positions of misspelled characters accelerates correction processes. We propose Token Internal Position Awareness (TIPA), a method that significantly improves models' ability to capture character positions within tokens by training them on reverse character prediction tasks using the tokenizer's vocabulary. Experiments demonstrate that TIPA enhances position prediction accuracy in LLMs, enabling more precise identification of target characters in original text. Furthermore, when applied to downstream tasks that do not require exact position prediction, TIPA still boosts performance in tasks needing character-level information, validating its versatility and effectiveness.

cs.CL↗

arXiv2025

Photometric and Spectroscopic Studies of Two Early-Type Eclipsing Binaries

Using high-precision photometric data from TESS, medium resolution spectroscopic data from LAMOST, and long-term eclipse timings, we provide orbital parameters for two early-type detached eclipsing binary systems: TYC 3740-2072-1 and TYC 2888-780-1, and analyze the orbital period variations and evolutionary status of these two targets. TYC 3740-2072-1, with a spectral type of B1V, consists of a $6.914 M_\odot$ subgiant and a $6.233 M_\odot$ main-sequence component. It is expected to evolve into a semi-detached binary, potentially serving as a progenitor of a Type Ia supernova. TYC 2888-780-1 has a spectral type of A3 and consists of two main-sequence components with masses of $1.682 M_\odot$ and $1.673 M_\odot$, respectively. It is undergoing stable evolution. Through eclipse timing analysis, we find that both targets exhibit apsidal motion effects, with observed AM rates of $\dotω_{obs} = 0.0412~\text{deg}~\text{cycle}^{-1}$ and $\dotω_{obs} = 0.0205~\text{deg}~\text{cycle}^{-1}$, respectively. Additionally, TYC 2888-780-1 exhibits orbital period variations, which we attribute to the light travel time effect caused by a third body, the minimum mass of this third body is estimated to be $0.598 M_\odot$.

astro-ph.SR↗

arXiv2025

Improving Noise Robustness of LLM-based Zero-shot TTS via Discrete Acoustic Token Denoising

Large language model (LLM) based zero-shot text-to-speech (TTS) methods tend to preserve the acoustic environment of the audio prompt, leading to degradation in synthesized speech quality when the audio prompt contains noise. In this paper, we propose a novel neural codec-based speech denoiser and integrate it with the advanced LLM-based TTS model, LauraTTS, to achieve noise-robust zero-shot TTS. The proposed codec denoiser consists of an audio codec, a token denoiser, and an embedding refiner. The token denoiser predicts the first two groups of clean acoustic tokens from the noisy ones, which can serve as the acoustic prompt for LauraTTS to synthesize high-quality personalized speech or be converted to clean speech waveforms through the embedding refiner and codec decoder. Experimental results show that our proposed codec denoiser outperforms state-of-the-art speech enhancement (SE) methods, and the proposed noise-robust LauraTTS surpasses the approach using additional SE models.

eess.AS↗

arXiv2025

OmniStyle: Filtering High Quality Style Transfer Data at Scale

In this paper, we introduce OmniStyle-1M, a large-scale paired style transfer dataset comprising over one million content-style-stylized image triplets across 1,000 diverse style categories, each enhanced with textual descriptions and instruction prompts. We show that OmniStyle-1M can not only enable efficient and scalable of style transfer models through supervised training but also facilitate precise control over target stylization. Especially, to ensure the quality of the dataset, we introduce OmniFilter, a comprehensive style transfer quality assessment framework, which filters high-quality triplets based on content preservation, style consistency, and aesthetic appeal. Building upon this foundation, we propose OmniStyle, a framework based on the Diffusion Transformer (DiT) architecture designed for high-quality and efficient style transfer. This framework supports both instruction-guided and image-guided style transfer, generating high resolution outputs with exceptional detail. Extensive qualitative and quantitative evaluations demonstrate OmniStyle's superior performance compared to existing approaches, highlighting its efficiency and versatility. OmniStyle-1M and its accompanying methodologies provide a significant contribution to advancing high-quality style transfer, offering a valuable resource for the research community.

cs.CV↗

arXiv2025

ARS: Automatic Routing Solver with Large Language Models

Real-world Vehicle Routing Problems (VRPs) are characterized by a variety of practical constraints, making manual solver design both knowledge-intensive and time-consuming. Although there is increasing interest in automating the design of routing algorithms, existing research has explored only a limited array of VRP variants and fails to adequately address the complex and prevalent constraints encountered in real-world situations. To fill this gap, this paper introduces RoutBench, a benchmark of 1,000 VRP variants derived from 24 attributes, for evaluating the effectiveness of automatic routing solvers in addressing complex constraints. Along with RoutBench, we present the Automatic Routing Solver (ARS), which employs Large Language Model (LLM) agents to enhance a backbone algorithm framework by automatically generating constraint-aware heuristic code, based on problem descriptions and several representative constraints selected from a database. Our experiments show that ARS outperforms state-of-the-art LLM-based methods and commonly used solvers, automatically solving 91.67% of common VRPs and achieving at least a 30% improvement across all benchmarks.

cs.AI↗

arXiv2025

REMEDI: Relative Feature Enhanced Meta-Learning with Distillation for Imbalanced Prediction

Predicting future vehicle purchases among existing owners presents a critical challenge due to extreme class imbalance (<0.5% positive rate) and complex behavioral patterns. We propose REMEDI (Relative feature Enhanced Meta-learning with Distillation for Imbalanced prediction), a novel multi-stage framework addressing these challenges. REMEDI first trains diverse base models to capture complementary aspects of user behavior. Second, inspired by comparative op-timization techniques, we introduce relative performance meta-features (deviation from ensemble mean, rank among peers) for effective model fusion through a hybrid-expert architecture. Third, we distill the ensemble's knowledge into a single efficient model via supervised fine-tuning with MSE loss, enabling practical deployment. Evaluated on approximately 800,000 vehicle owners, REMEDI significantly outperforms baseline approaches, achieving the business target of identifying ~50% of actual buyers within the top 60,000 recommendations at ~10% precision. The distilled model preserves the ensemble's predictive power while maintaining deployment efficiency, demonstrating REMEDI's effectiveness for imbalanced prediction in industry settings.

cs.LG↗

arXiv2025

PRIME: Physics-Related Intelligent Mixture of Experts for Transistor Characteristics Prediction

In recent years, machine learning has been extensively applied to data prediction during process ramp-up, with a particular focus on transistor characteristics for circuit design and manufacture. However, capturing the nonlinear current response across multiple operating regions remains a challenge for neural networks. To address such challenge, a novel machine learning framework, PRIME (Physics-Related Intelligent Mixture of Experts), is proposed to capture and integrate complex regional characteristics. In essence, our framework incorporates physics-based knowledge with data-driven intelligence. By leveraging a dynamic weighting mechanism in its gating network, PRIME adaptively activates the suitable expert model based on distinct input data features. Extensive evaluations are conducted on various gate-all-around (GAA) structures to examine the effectiveness of PRIME and considerable improvements (60\%-84\%) in prediction accuracy are shown over state-of-the-art models.

cs.LG↗

arXiv2025

The Bass--Quillen conjecture for torsors over valuation rings

For a valuation ring $V$, a smooth $V$-algebra $A$, and a reductive $V$-group scheme $G$ satisfying a certain natural isotropicity condition, we prove that every Nisnevich $G$-torsor on $\mathbb{A}^N_A$ descends to a $G$-torsor on $A$. As a corollary, we generalize Raghunathan's theorem on torsors over affine spaces to a relative setting. We also extend several affine representability results of Asok, Hoyois, and Wendt from equi-characteristics to mixed characteristics. Our proof relies on previous work on the purity of reductive torsors over smooth relative curves and the Grothendieck--Serre conjecture for constant reductive group schemes.

math.AG↗