arXiv subjects

Zihan Lin

Publications and source records attributed to Zihan Lin.

At least 37 records · Page 2Linked to original sources

arXiv2026

ResT: Reshaping Token-Level Policy Gradients for Tool-Use Large Language Models

Large language models (LLMs) transcend passive generation and act as goal-directed agents by invoking external tools. Reinforcement learning (RL) offers a principled framework for optimizing these emergent tool-use policies, yet the prevailing paradigm relies exclusively on sparse outcome rewards and lacks consideration of the particularity of tool-use tasks, inflating policy-gradient variance and resulting in inefficient training. To better understand and address these challenges, we first establish a theoretical link between policy entropy and training stability of tool-use tasks, which reveals that structured, low-entropy tokens are primary determinants of rewards. Motivated by this insight, we propose \textbf{Res}haped \textbf{T}oken-level policy gradients (\textbf{ResT}) for tool-use tasks. ResT reshapes the policy gradient through entropy-informed token reweighting, progressively upweighting reasoning tokens as training proceeds. This entropy-aware scheme enables a smooth shift from structural correctness to semantic reasoning and stabilizes convergence in multi-turn tool-use tasks. Evaluation on BFCL and API-Bank shows that ResT achieves state-of-the-art results, outperforming prior methods by up to $8.76\%$. When fine-tuned on a 4B base LLM, ResT further surpasses GPT-4o by $4.11\%$ on single-turn tasks and $1.50\%$ on multi-turn base tasks. Code is available at https://github.com/1229095296/ResT_Tool_use_LLM.git.

cs.CL↗

arXiv2026

AWPO: Enhancing Tool-Use of Large Language Models through Adaptive Integration of Reasoning Rewards

While Reinforcement Learning (RL) shows promise in training tool-use Large Language Models (LLMs) using verifiable outcome rewards, existing methods largely overlook the potential of reasoning rewards based on chain-of-thought quality for better tool utilization. Furthermore, naïvely combining reasoning and outcome rewards may yield suboptimal performance or conflict with the primary optimization objective. To address this, we propose Advantage-Weighted Policy Optimization (AWPO), a principled RL framework that adaptively integrates reasoning rewards into advantage estimation to improve tool-use performance. AWPO incorporates variance-aware gating and difficulty-aware weighting to adaptively modulate advantages from reasoning signals based on group-relative statistics, alongside a tailored clipping mechanism for stable optimization. Extensive experiments demonstrate that AWPO achieves state-of-the-art performance across standard tool-use benchmarks, significantly outperforming strong baselines and leading closed-source models in challenging multi-turn scenarios. Notably, with exceptional parameter efficiency, our 4B model surpasses Grok-4 by $16.0\%$ in multi-turn accuracy while preserving generalization capability on the out-of-distribution MMLU-Pro benchmark.

cs.CL↗

arXiv2025

Differentiable Inverse Modeling with Physics-Constrained Latent Diffusion for Heterogeneous Subsurface Parameter Fields

We present a latent diffusion-based differentiable inversion method (LD-DIM) for PDE-constrained inverse problems involving high-dimensional spatially distributed coefficients. LD-DIM couples a pretrained latent diffusion prior with an end-to-end differentiable numerical solver to reconstruct unknown heterogeneous parameter fields in a low-dimensional nonlinear manifold, improving numerical conditioning and enabling stable gradient-based optimization under sparse observations. The proposed framework integrates a latent diffusion model (LDM), trained in a compact latent space, with a differentiable finite-volume discretization of the forward PDE. Sensitivities are propagated through the discretization using adjoint-based gradients combined with reverse-mode automatic differentiation. Inversion is performed directly in latent space, which implicitly suppresses ill-conditioned degrees of freedom while preserving dominant structural modes, including sharp material interfaces. The effectiveness of LD-DIM is demonstrated using a representative inverse problem for flow in porous media, where heterogeneous conductivity fields are reconstructed from spatially sparse hydraulic head measurements. Numerical experiments assess convergence behavior and reconstruction quality for both Gaussian random fields and bimaterial coefficient distributions. The results show that LD-DIM achieves consistently improved numerical stability and reconstruction accuracy of both parameter fields and corresponding PDE solutions compared with physics-informed neural networks (PINNs) and physics-embedded variational autoencoder (VAE) baselines, while maintaining sharp discontinuities and reducing sensitivity to initialization.

math.NA↗

arXiv2025

Broadband nonlinear Hall response and multiple wave mixing in a room temperature altermagnet

Crystalline symmetries determine the linear and nonlinear response of materials to external stimuli such as mechanical pressure and electromagnetic fields, governing phenomena such as piezoelectricity, optical activity, and multiple wave mixing with wide ranging technological applications. Altermagnets present a new class of materials with magnetic crystalline order where specific crystal symmetry operations connect antiferromagnetic sublattices, leading to non-relativistic spin-splitting of the electronic band structure. Hence, the electric material properties of altermagnets should uniquely mirror these underlying symmetry properties, potentially giving rise to novel phenomena in response to external driving fields. Here, we report the discovery of a broadband third-order nonlinear anomalous Hall effect in altermagnetic CrSb at room temperature. The comparison of our observations with symmetry analyses and model calculations shows that this nonlinear Hall response is induced by the nonlinear electric susceptibility of a Berry curvature quadrupole, which exists within the spin-split band structure of CrSb and is characterized by the underlying crystalline and magnetic symmetries. We then utilize this third-order nonlinear electric susceptibility of CrSb to realize a multiple wave mixing device with pronounced four wave mixing output, which could, in principle, be extended to THz frequencies. Our study discovers that the crystalline magnetic order of altermagnets determines their nonlinear electric material properties, which could facilitate applications in high-frequency electronics, THz generation, communication networks, and energy harvesting.

cond-mat.mes-hall↗

arXiv2025

History-Aware Neural Operator: Robust Data-Driven Constitutive Modeling of Path-Dependent Materials

This study presents an end-to-end learning framework for data-driven modeling of path-dependent inelastic materials using neural operators. The framework is built on the premise that irreversible evolution of material responses, governed by hidden dynamics, can be inferred from observable data. We develop the History-Aware Neural Operator (HANO), an autoregressive model that predicts path-dependent material responses from short segments of recent strain-stress history without relying on hidden state variables, thereby overcoming self-consistency issues commonly encountered in recurrent neural network (RNN)-based models. Built on a Fourier-based neural operator backbone, HANO enables discretization-invariant learning. To enhance its ability to capture both global loading patterns and critical local path dependencies, we embed a hierarchical self-attention mechanism that facilitates multiscale feature extraction. Beyond ensuring self-consistency, HANO mitigates sensitivity to initial hidden states, a commonly overlooked issue that can lead to instability in recurrent models when applied to generalized loading paths. By modeling stress-strain evolution as a continuous operator rather than relying on fixed input-output mappings, HANO naturally accommodates varying path discretizations and exhibits robust performance under complex conditions, including irregular sampling, multi-cycle loading, noisy data, and pre-stressed states. We evaluate HANO on two benchmark problems: elastoplasticity with hardening and progressive anisotropic damage in brittle solids. Results show that HANO consistently outperforms baseline models in predictive accuracy, generalization, and robustness. With its demonstrated capabilities, HANO provides an effective data-driven surrogate for simulating inelastic materials and is well-suited for integration with classical numerical solvers.

cs.LG↗

arXiv2025

MultiEditor: Controllable Multimodal Object Editing for Driving Scenarios Using 3D Gaussian Splatting Priors

Autonomous driving systems rely heavily on multimodal perception data to understand complex environments. However, the long-tailed distribution of real-world data hinders generalization, especially for rare but safety-critical vehicle categories. To address this challenge, we propose MultiEditor, a dual-branch latent diffusion framework designed to edit images and LiDAR point clouds in driving scenarios jointly. At the core of our approach is introducing 3D Gaussian Splatting (3DGS) as a structural and appearance prior for target objects. Leveraging this prior, we design a multi-level appearance control mechanism--comprising pixel-level pasting, semantic-level guidance, and multi-branch refinement--to achieve high-fidelity reconstruction across modalities. We further propose a depth-guided deformable cross-modality condition module that adaptively enables mutual guidance between modalities using 3DGS-rendered depth, significantly enhancing cross-modality consistency. Extensive experiments demonstrate that MultiEditor achieves superior performance in visual and geometric fidelity, editing controllability, and cross-modality consistency. Furthermore, generating rare-category vehicle data with MultiEditor substantially enhances the detection accuracy of perception models on underrepresented classes.

cs.AI↗

arXiv2025

Dependency Network-Based Portfolio Design with Forecasting and VaR Constraints

This study proposes a novel portfolio optimization framework that integrates statistical social network analysis with time series forecasting and risk management. Using daily stock data from the S&P 500 (2020-2024), we construct dependency networks via Vector Autoregression (VAR) and Forecast Error Variance Decomposition (FEVD), transforming influence relationships into a cost-based network. Specifically, FEVD breaks down the VAR's forecast error variance to quantify how much each stock's shocks contribute to another's uncertainty information we invert to form influence-based edge weights in our network. By applying the Minimum Spanning Tree (MST) algorithm, we extract the core inter-stock structure and identify central stocks through degree centrality. A dynamic portfolio is constructed using the top-ranked stocks, with capital allocated based on Value at Risk (VaR). To refine stock selection, we incorporate forecasts from ARIMA and Neural Network Autoregressive (NNAR) models. Trading simulations over a one-year period demonstrate that the MST-based strategies outperform a buy-and-hold benchmark, with the tuned NNAR-enhanced strategy achieving a 63.74% return versus 18.00% for the benchmark. Our results highlight the potential of combining network structures, predictive modeling, and risk metrics to improve adaptive financial decision-making.

q-fin.PM↗

arXiv2025

Enhancing Sequential Recommender with Large Language Models for Joint Video and Comment Recommendation

Nowadays, reading or writing comments on captivating videos has emerged as a critical part of the viewing experience on online video platforms. However, existing recommender systems primarily focus on users' interaction behaviors with videos, neglecting comment content and interaction in user preference modeling. In this paper, we propose a novel recommendation approach called LSVCR that utilizes user interaction histories with both videos and comments to jointly perform personalized video and comment recommendation. Specifically, our approach comprises two key components: sequential recommendation (SR) model and supplemental large language model (LLM) recommender. The SR model functions as the primary recommendation backbone (retained in deployment) of our method for efficient user preference modeling. Concurrently, we employ a LLM as the supplemental recommender (discarded in deployment) to better capture underlying user preferences derived from heterogeneous interaction behaviors. In order to integrate the strengths of the SR model and the supplemental LLM recommender, we introduce a two-stage training paradigm. The first stage, personalized preference alignment, aims to align the preference representations from both components, thereby enhancing the semantics of the SR model. The second stage, recommendation-oriented fine-tuning, involves fine-tuning the alignment-enhanced SR model according to specific objectives. Extensive experiments in both video and comment recommendation tasks demonstrate the effectiveness of LSVCR. Moreover, online A/B testing on KuaiShou platform verifies the practical benefits of our approach. In particular, we attain a cumulative gain of 4.13% in comment watch time.

cs.IR↗

arXiv2025

Enhancing Trading Performance Through Sentiment Analysis with Large Language Models: Evidence from the S&P 500

This study integrates real-time sentiment analysis from financial news, GPT-2 and FinBERT, with technical indicators and time-series models like ARIMA and ETS to optimize S&P 500 trading strategies. By merging sentiment data with momentum and trend-based metrics, including a benchmark buy-and-hold and sentiment-based approach, is evaluated through assets values and returns. Results show that combining sentiment-driven insights with traditional models improves trading performance, offering a more dynamic approach to stock trading that adapts to market changes in volatile environments.

q-fin.CP↗

arXiv2025

Inter-event Interval Microscopy for Event Cameras

Event cameras, an innovative bio-inspired sensor, differ from traditional cameras by sensing changes in intensity rather than directly perceiving intensity and recording these variations as a continuous stream of "events". The intensity reconstruction from these sparse events has long been a challenging problem. Previous approaches mainly focused on transforming motion-induced events into videos or achieving intensity imaging for static scenes by integrating modulation devices at the event camera acquisition end. In this paper, for the first time, we achieve event-to-intensity conversion using a static event camera for both static and dynamic scenes in fluorescence microscopy. Unlike conventional methods that primarily rely on event integration, the proposed Inter-event Interval Microscopy (IEIM) quantifies the time interval between consecutive events at each pixel. With a fixed threshold in the event camera, the time interval can precisely represent the intensity. At the hardware level, the proposed IEIM integrates a pulse light modulation device within a microscope equipped with an event camera, termed Pulse Modulation-based Event-driven Fluorescence Microscopy. Additionally, we have collected IEIMat dataset under various scenes including high dynamic range and high-speed scenarios. Experimental results on the IEIMat dataset demonstrate that the proposed IEIM achieves superior spatial and temporal resolution, as well as a higher dynamic range, with lower bandwidth compared to other methods. The code and the IEIMat dataset will be made publicly available.

cs.CV↗

arXiv2025

Comment Staytime Prediction with LLM-enhanced Comment Understanding

In modern online streaming platforms, the comments section plays a critical role in enhancing the overall user experience. Understanding user behavior within the comments section is essential for comprehensive user interest modeling. A key factor of user engagement is staytime, which refers to the amount of time that users browse and post comments. Existing watchtime prediction methods struggle to adapt to staytime prediction, overlooking interactions with individual comments and their interrelation. In this paper, we present a micro-video recommendation dataset with video comments (named as KuaiComt) which is collected from Kuaishou platform. correspondingly, we propose a practical framework for comment staytime prediction with LLM-enhanced Comment Understanding (LCU). Our framework leverages the strong text comprehension capabilities of large language models (LLMs) to understand textual information of comments, while also incorporating fine-grained comment ranking signals as auxiliary tasks. The framework is two-staged: first, the LLM is fine-tuned using domain-specific tasks to bridge the video and the comments; second, we incorporate the LLM outputs into the prediction model and design two comment ranking auxiliary tasks to better understand user preference. Extensive offline experiments demonstrate the effectiveness of our framework, showing significant improvements on the task of comment staytime prediction. Additionally, online A/B testing further validates the practical benefits on industrial scenario. Our dataset KuaiComt (https://github.com/lyingCS/KuaiComt.github.io) and code for LCU (https://github.com/lyingCS/LCU) are fully released.

cs.IR↗

arXiv2025

A real-time battle situation intelligent awareness system based on Meta-learning & RNN

In modern warfare, real-time and accurate battle situation analysis is crucial for making strategic and tactical decisions. The proposed real-time battle situation intelligent awareness system (BSIAS) aims at meta-learning analysis and stepwise RNN (recurrent neural network) modeling, where the former carries out the basic processing and analysis of battlefield data, which includes multi-steps such as data cleansing, data fusion, data mining and continuously updates, and the latter optimizes the battlefield modeling by stepwise capturing the temporal dependencies of data set. BSIAS can predict the possible movement from any side of the fence and attack routes by taking a simulated battle as an example, which can be an intelligent support platform for commanders to make scientific decisions during wartime. This work delivers the potential application of integrated BSIAS in the field of battlefield command & analysis engineering.

cs.LG↗

arXiv2024

Observation of surface Fermi arcs in altermagnetic Weyl semimetal CrSb

As a special type of collinear antiferromagnetism (AFM), altermagnetism has garnered significant research interest recently. Altermagnets exhibit broken parity-time symmetry and zero net magnetization in real space, leading to substantial band splitting in momentum space even in the absence of spin-orbit coupling. Meanwhile, parity-time symmetry breaking always induce nontrivial band topology such as Weyl nodes. While Weyl semimetal states and nodal lines have been theoretically proposed in altermagnets, rare reports of experimental observation have been made up to this point. Using ARPES and first-principles calculations, we systematically studied the electronic structure of the room-temperature altermagnet candidate CrSb. At generic locations in momentum space, we clearly observed band spin splitting. Furthermore, we identified discrete surface Fermi arcs on the (100) cleaved side surface close to the Fermi level originating from bulk band topology. Our results imply that CrSb contains interesting nontrivial topological Weyl physics, in addition to being an excellent room temperature altermagnet.

cond-mat.mtrl-sci↗

arXiv2024

Investigation of W-SiC compositionally graded films as a divertor material

W-SiC composite material is a promising plasma-facing material candidate alternative to pure W due to the low neutron activation, low impurity radiation, and low tritium diffusivity of SiC while leveraging the high erosion resistance of the W armor. Additionally, W and SiC have high thermomechanical compatibility given their similar thermal expansion rates. The present study addresses the synthesis and performance of compositionally graded W-SiC films fabricated by pulsed-DC magnetron sputtering. Compositional gradients were characterized using transmission electron microscopy (TEM) and energy-dispersive X-ray spectroscopy (EDS), and crystallographic information was obtained using electron diffraction and X-ray diffraction (XRD). Samples were exposed to L-mode deuterium plasma discharges in the DIII-D tokamak using the Divertor Material Evaluation System (DiMES). Post-mortem characterizations were performed using scanning electron microscopy (SEM) and XRD. Electron diffraction and XRD showed that the compositionally graded W-SiC films were composed of polycrystalline W and amorphous SiC with amorphous W+SiC interlayers. No macroscopic delamination or microstructural changes were observed under mild exposure conditions. This study serves as a preliminary examination of W-SiC compositionally graded composites as a potential candidate divertor material in future tokamak devices.

physics.plasm-ph↗

arXiv2024

Observation of Giant Spin Splitting and d-wave Spin Texture in Room Temperature Altermagnet RuO2

Recently, a novel magnetic phase called altermagnetism has been proposed, ushering in a third distinct magnetic phase beyond ferromagnetism and antiferromagnetism. It is expected that this groundbreaking phase exhibits unique physical properties such as C-paired spin-valley locking, anomalous Hall effect, nontrivial Berry phase, and giant magnetoresistance, etc. Among all the predicted candidates, several room temperature altermagnets are suggested to host significant potential applications in the near future. Nevertheless, direct evidence about the spin pattern of the room temperature altermagnet is still unrevealed. Previous studies found that RuO2 is identified as the most promising candidate for room temperature d-wave altermagnetism, exhibiting a substantial spin splitting of up to 1.4 eV. In this study, utilizing angle-resolved photoemission spectroscopy (ARPES), we report experimental observation of the spin splitting in RuO2. Furthermore, employing spin-ARPES, we directly observed the d-wave spin pattern. Our results unequivocally show that RuO2 is a perfect d-wave altermagnet with great potential for upcoming spintronic applications.

cond-mat.mtrl-sci↗

arXiv2024

Large Language Models are Zero-Shot Rankers for Recommender Systems

Recently, large language models (LLMs) (e.g., GPT-4) have demonstrated impressive general-purpose task-solving abilities, including the potential to approach recommendation tasks. Along this line of research, this work aims to investigate the capacity of LLMs that act as the ranking model for recommender systems. We first formalize the recommendation problem as a conditional ranking task, considering sequential interaction histories as conditions and the items retrieved by other candidate generation models as candidates. To solve the ranking task by LLMs, we carefully design the prompting template and conduct extensive experiments on two widely-used datasets. We show that LLMs have promising zero-shot ranking abilities but (1) struggle to perceive the order of historical interactions, and (2) can be biased by popularity or item positions in the prompts. We demonstrate that these issues can be alleviated using specially designed prompting and bootstrapping strategies. Equipped with these insights, zero-shot LLMs can even challenge conventional recommendation models when ranking candidates are retrieved by multiple candidate generators. The code and processed datasets are available at https://github.com/RUCAIBox/LLMRank.

cs.IR↗

arXiv2024

Self context-aware emotion perception on human-robot interaction

Emotion recognition plays a crucial role in various domains of human-robot interaction. In long-term interactions with humans, robots need to respond continuously and accurately, however, the mainstream emotion recognition methods mostly focus on short-term emotion recognition, disregarding the context in which emotions are perceived. Humans consider that contextual information and different contexts can lead to completely different emotional expressions. In this paper, we introduce self context-aware model (SCAM) that employs a two-dimensional emotion coordinate system for anchoring and re-labeling distinct emotions. Simultaneously, it incorporates its distinctive information retention structure and contextual loss. This approach has yielded significant improvements across audio, video, and multimodal. In the auditory modality, there has been a notable enhancement in accuracy, rising from 63.10% to 72.46%. Similarly, the visual modality has demonstrated improved accuracy, increasing from 77.03% to 80.82%. In the multimodal, accuracy has experienced an elevation from 77.48% to 78.93%. In the future, we will validate the reliability and usability of SCAM on robots through psychology experiments.

cs.HC↗

arXiv2023

INeAT: Iterative Neural Adaptive Tomography

Computed Tomography (CT) with its remarkable capability for three-dimensional imaging from multiple projections, enjoys a broad range of applications in clinical diagnosis, scientific observation, and industrial detection. Neural Adaptive Tomography (NeAT) is a recently proposed 3D rendering method based on neural radiance field for CT, and it demonstrates superior performance compared to traditional methods. However, it still faces challenges when dealing with the substantial perturbations and pose shifts encountered in CT scanning processes. Here, we propose a neural rendering method for CT reconstruction, named Iterative Neural Adaptive Tomography (INeAT), which incorporates iterative posture optimization to effectively counteract the influence of posture perturbations in data, particularly in cases involving significant posture variations. Through the implementation of a posture feedback optimization strategy, INeAT iteratively refines the posture corresponding to the input images based on the reconstructed 3D volume. We demonstrate that INeAT achieves artifact-suppressed and resolution-enhanced reconstruction in scenarios with significant pose disturbances. Furthermore, we show that our INeAT maintains comparable reconstruction performance to stable-state acquisitions even using data from unstable-state acquisitions, which significantly reduces the time required for CT scanning and relaxes the stringent requirements on imaging hardware systems, underscoring its immense potential for applications in short-time and low-cost CT technology.

eess.IV↗