arXiv subjects

Chi Zhang

Publications and source records attributed to Chi Zhang.

At least 415 records · Page 23Linked to original sources

arXiv2025

Divide, Optimize, Merge: Fine-Grained LLM Agent Optimization at Scale

LLM-based optimization has shown remarkable potential in enhancing agentic systems. However, the conventional approach of prompting LLM optimizer with the whole training trajectories on training dataset in a single pass becomes untenable as datasets grow, leading to context window overflow and degraded pattern recognition. To address these challenges, we propose Fine-Grained Optimization (FGO), a scalable framework that divides large optimization tasks into manageable subsets, performs targeted optimizations, and systematically combines optimized components through progressive merging. Evaluation across ALFWorld, LogisticsQA, and GAIA benchmarks demonstrate that FGO outperforms existing approaches by 1.6-8.6% while reducing average prompt token consumption by 56.3%. Our framework provides a practical solution for scaling up LLM-based optimization of increasingly sophisticated agent systems. Further analysis demonstrates that FGO achieves the most consistent performance gain in all training dataset sizes, showcasing its scalability and efficiency.

cs.CL↗

arXiv2025

Investigation of magnon behavior in YIG film under microwave excitation using Brillouin light scattering

We utilize conventional wave-vector-resolved Brillouin light scattering technology to investigate the spin wave response in YIG thin films under high-power microwave excitation. By varying the microwave frequency, external bias magnetic field, and in-plane wave vector, in addition to observing the dipole-exchange spin waves excited by parallel parametric pumping, we further observe broadband spin wave excitation within the dipole-exchange spin wave spectrum. This broadband excitation results from the combined effects of parallel and perpendicular parametric pumping, induced by irregularities in the excitation geometry, as well as magnon-magnon scattering arising from the absence of certain spin wave modes. Our findings offer new insights into the mechanisms of energy dissipation and relaxation processes caused by spin wave excitation in magnetic devices operating at high power.

cond-mat.mes-hall↗

arXiv2025

Video-Bench: Human-Aligned Video Generation Benchmark

Video generation assessment is essential for ensuring that generative models produce visually realistic, high-quality videos while aligning with human expectations. Current video generation benchmarks fall into two main categories: traditional benchmarks, which use metrics and embeddings to evaluate generated video quality across multiple dimensions but often lack alignment with human judgments; and large language model (LLM)-based benchmarks, though capable of human-like reasoning, are constrained by a limited understanding of video quality metrics and cross-modal consistency. To address these challenges and establish a benchmark that better aligns with human preferences, this paper introduces Video-Bench, a comprehensive benchmark featuring a rich prompt suite and extensive evaluation dimensions. This benchmark represents the first attempt to systematically leverage MLLMs across all dimensions relevant to video generation assessment in generative models. By incorporating few-shot scoring and chain-of-query techniques, Video-Bench provides a structured, scalable approach to generated video evaluation. Experiments on advanced models including Sora demonstrate that Video-Bench achieves superior alignment with human preferences across all dimensions. Moreover, in instances where our framework's assessments diverge from human evaluations, it consistently offers more objective and accurate insights, suggesting an even greater potential advantage over traditional human judgment.

cs.CV↗

arXiv2025

Probing and Inducing Combinational Creativity in Vision-Language Models

The ability to combine existing concepts into novel ideas stands as a fundamental hallmark of human intelligence. Recent advances in Vision-Language Models (VLMs) like GPT-4V and DALLE-3 have sparked debate about whether their outputs reflect combinational creativity--defined by M. A. Boden (1998) as synthesizing novel ideas through combining existing concepts--or sophisticated pattern matching of training data. Drawing inspiration from cognitive science, we investigate the combinational creativity of VLMs from the lens of concept blending. We propose the Identification-Explanation-Implication (IEI) framework, which decomposes creative processes into three levels: identifying input spaces, extracting shared attributes, and deriving novel semantic implications. To validate this framework, we curate CreativeMashup, a high-quality dataset of 666 artist-generated visual mashups annotated according to the IEI framework. Through extensive experiments, we demonstrate that in comprehension tasks, best VLMs have surpassed average human performance while falling short of expert-level understanding; in generation tasks, incorporating our IEI framework into the generation pipeline significantly enhances the creative quality of VLMs' outputs. Our findings establish both a theoretical foundation for evaluating artificial creativity and practical guidelines for improving creative generation in VLMs.

cs.CV↗

arXiv2025

Seed1.5-Thinking: Advancing Superb Reasoning Models with Reinforcement Learning

We introduce Seed1.5-Thinking, capable of reasoning through thinking before responding, resulting in improved performance on a wide range of benchmarks. Seed1.5-Thinking achieves 86.7 on AIME 2024, 55.0 on Codeforces and 77.3 on GPQA, demonstrating excellent reasoning abilities in STEM and coding. Beyond reasoning tasks, the method demonstrates notable generalization across diverse domains. For instance, it surpasses DeepSeek R1 by 8% in win rate on non-reasoning tasks, indicating its broader applicability. Compared to other state-of-the-art reasoning models, Seed1.5-Thinking is a Mixture-of-Experts (MoE) model with a relatively small size, featuring 20B activated and 200B total parameters. As part of our effort to assess generalized reasoning, we develop two internal benchmarks, BeyondAIME and Codeforces, both of which will be publicly released to support future research. Model trial link: https://www.volcengine.com/experience/ark.

cs.CL↗

arXiv2025

Bias correction in treatment effect estimates following data-driven biomarker cutoff selection

Predictive biomarkers are playing an essential role in precision medicine. Identifying an optimal cutoff to select patient subsets with greater benefit from treatment is critical and more challenging for predictive biomarkers measured with a continuous scale. It is a common practice to perform exploratory subset analysis in early-stage studies to select the cutoff. However, data-driven cutoff selection will often cause bias in treatment effect estimates and lead to over-optimistic expectations in the future phase III trial. In this study, we first conducted extensive simulations to investigate factors influencing the bias, including the cutoff selection rule, the number of candidates cutoffs, the magnitude of the predictive effect, and sample sizes. Our insights emphasize the importance of accounting for bias and uncertainties caused by small sample sizes and data-driven selection procedures in Go/No Go decision-making, and population and sample size determination for phase III studies. Secondly, we evaluated the performance of Bootstrap Bias Correction and the Approximate Bayesian Computation (ABC) method for bias correction through extensive simulations. We conclude by providing a recommendation for the application of the two approaches in clinical practice.

stat.AP↗

arXiv2025

Experimental Multi-Dimensional Side-Channel-Secure Quantum Key Distribution

Quantum key distribution (QKD) theoretically provides unconditional security between remote parties. However, guaranteeing practical security through device characterisation alone is challenging in real-world implementations due to the multi-dimensional spaces in which the devices may be operated. The side-channel-secure (SCS)-QKD protocol, which only requires bounding the upper limits of the intensities for the two states, theoretically provides a rigorous solution to the challenge and achieves measurement-device-independent security in detection and security for whatever multi-dimensional side channel attack in the source. Here, we demonstrate a practical implementation of SCS-QKD, achieving a secure key rate of $6.60$ kbps through a 50.5 km fibre and a maximum distribution distance of 101.1 km while accounting for finite-size effects. Our experiment also represents an approximate forty-times improvement over the previous experiment.

quant-ph↗

arXiv2025

Physics Informed Constrained Learning of Dynamics from Static Data

A physics-informed neural network (PINN) models the dynamics of a system by integrating the governing physical laws into the architecture of a neural network. By enforcing physical laws as constraints, PINN overcomes challenges with data scarsity and potentially high dimensionality. Existing PINN frameworks rely on fully observed time-course data, the acquisition of which could be prohibitive for many systems. In this study, we developed a new PINN learning paradigm, namely Constrained Learning, that enables the approximation of first-order derivatives or motions using non-time course or partially observed data. Computational principles and a general mathematical formulation of Constrained Learning were developed. We further introduced MPOCtrL (Message Passing Optimization-based Constrained Learning) an optimization approach tailored for the Constrained Learning framework that strives to balance the fitting of physical models and observed data. Its code is available at github link: https://github.com/ptdang1001/MPOCtrL Experiments on synthetic and real-world data demonstrated that MPOCtrL can effectively detect the nonlinear dependency between observed data and the underlying physical properties of the system. In particular, on the task of metabolic flux analysis, MPOCtrL outperforms all existing data-driven flux estimators.

cs.LG↗

arXiv2025

DianJin-R1: Evaluating and Enhancing Financial Reasoning in Large Language Models

Effective reasoning remains a core challenge for large language models (LLMs) in the financial domain, where tasks often require domain-specific knowledge, precise numerical calculations, and strict adherence to compliance rules. We propose DianJin-R1, a reasoning-enhanced framework designed to address these challenges through reasoning-augmented supervision and reinforcement learning. Central to our approach is DianJin-R1-Data, a high-quality dataset constructed from CFLUE, FinQA, and a proprietary compliance corpus (Chinese Compliance Check, CCC), combining diverse financial reasoning scenarios with verified annotations. Our models, DianJin-R1-7B and DianJin-R1-32B, are fine-tuned from Qwen2.5-7B-Instruct and Qwen2.5-32B-Instruct using a structured format that generates both reasoning steps and final answers. To further refine reasoning quality, we apply Group Relative Policy Optimization (GRPO), a reinforcement learning method that incorporates dual reward signals: one encouraging structured outputs and another rewarding answer correctness. We evaluate our models on five benchmarks: three financial datasets (CFLUE, FinQA, and CCC) and two general reasoning benchmarks (MATH-500 and GPQA-Diamond). Experimental results show that DianJin-R1 models consistently outperform their non-reasoning counterparts, especially on complex financial tasks. Moreover, on the real-world CCC dataset, our single-call reasoning models match or even surpass the performance of multi-agent systems that require significantly more computational cost. These findings demonstrate the effectiveness of DianJin-R1 in enhancing financial reasoning through structured supervision and reward-aligned learning, offering a scalable and practical solution for real-world applications.

cs.AI↗

arXiv2025

Dynamic Asset Pricing: Integrating FinBERT-Based Sentiment Quantification with the Fama--French Five-Factor Model

This paper presents a comprehensive study on the integration of text-derived, time-varying sentiment factors into traditional multi-factor asset pricing models. Leveraging FinBERT, a domain-specific deep learning language model, we construct a dynamic sentiment index and its volatility from large-scale financial news and social media data covering 2020 to 2022. By embedding these sentiment measures into the Fama French five-factor regression, we rigorously examine whether sentiment significantly explains variations in daily stock returns and how its impact evolves across different market volatility regimes. Empirical results demonstrate that sentiment has a consistently positive impact on returns during normal periods, while its effect is amplified or even reversed under extreme market conditions. Rolling regressions reveal the time-varying nature of sentiment sensitivity, and an event study around the June 15, 2022 Federal Reserve 75 basis point rate hike shows that a sentiment-augmented five-factor model better explains abnormal returns relative to the baseline model. Our findings support the incorporation of high-frequency, NLP-derived sentiment into classical asset pricing frameworks and suggest implications for investors and regulators.

cs.CE↗

arXiv2025

Distill Any Depth: Distillation Creates a Stronger Monocular Depth Estimator

Recent advances in zero-shot monocular depth estimation(MDE) have significantly improved generalization by unifying depth distributions through normalized depth representations and by leveraging large-scale unlabeled data via pseudo-label distillation. However, existing methods that rely on global depth normalization treat all depth values equally, which can amplify noise in pseudo-labels and reduce distillation effectiveness. In this paper, we present a systematic analysis of depth normalization strategies in the context of pseudo-label distillation. Our study shows that, under recent distillation paradigms (e.g., shared-context distillation), normalization is not always necessary, as omitting it can help mitigate the impact of noisy supervision. Furthermore, rather than focusing solely on how depth information is represented, we propose Cross-Context Distillation, which integrates both global and local depth cues to enhance pseudo-label quality. We also introduce an assistant-guided distillation strategy that incorporates complementary depth priors from a diffusion-based teacher model, enhancing supervision diversity and robustness. Extensive experiments on benchmark datasets demonstrate that our approach significantly outperforms state-of-the-art methods, both quantitatively and qualitatively.

cs.CV↗

arXiv2025

Phased Array Calibration based on Rotating-Element Harmonic Electric-Field Vector with Time Modulation

Calibration is crucial for ensuring the performance of phased array since amplitude-phase imbalance between elements results in significant performance degradation. While amplitude-only calibration methods offer advantages when phase measurements are impractical, conventional approaches face two key challenges: they typically require high-resolution phase shifters and remain susceptible to phase errors inherent in these components. To overcome these limitations, we propose a Rotating element Harmonic Electric-field Vector (RHEV) strategy, which enables precise calibration through time modulation principles. The proposed technique functions as follows. Two 1-bit phase shifters are periodically phase-switched at the same frequency, each generating corresponding harmonics. By adjusting the relative delay between their modulation timings, the phase difference between the $+1$st harmonics produced by the two elements can be precisely controlled, utilizing the time-shift property of the Fourier transform. Furthermore, the +1st harmonic generated by sequential modulation of individual elements exhibits a linear relationship with the amplitude of the modulated element, enabling amplitude ambiguity resolution. The proposed RHEV-based calibration method generates phase shifts through relative timing delays rather than physical phase shifter adjustments, rendering it less susceptible to phase shift errors. Additionally, since the calibration process exclusively utilizes the $+1$st harmonic, which is produced solely by the modulated unit, the method demonstrates consistent performance regardless of array size. Extensive numerical simulations, practical in-channel and over-the-air (OTA) calibration experiments demonstrate the effectiveness and distinct advantages of the proposed method.

eess.SP↗

arXiv2025

Metric-Solver: Sliding Anchored Metric Depth Estimation from a Single Image

Accurate and generalizable metric depth estimation is crucial for various computer vision applications but remains challenging due to the diverse depth scales encountered in indoor and outdoor environments. In this paper, we introduce Metric-Solver, a novel sliding anchor-based metric depth estimation method that dynamically adapts to varying scene scales. Our approach leverages an anchor-based representation, where a reference depth serves as an anchor to separate and normalize the scene depth into two components: scaled near-field depth and tapered far-field depth. The anchor acts as a normalization factor, enabling the near-field depth to be normalized within a consistent range while mapping far-field depth smoothly toward zero. Through this approach, any depth from zero to infinity in the scene can be represented within a unified representation, effectively eliminating the need to manually account for scene scale variations. More importantly, for the same scene, the anchor can slide along the depth axis, dynamically adjusting to different depth scales. A smaller anchor provides higher resolution in the near-field, improving depth precision for closer objects while a larger anchor improves depth estimation in far regions. This adaptability enables the model to handle depth predictions at varying distances and ensure strong generalization across datasets. Our design enables a unified and adaptive depth representation across diverse environments. Extensive experiments demonstrate that Metric-Solver outperforms existing methods in both accuracy and cross-dataset generalization.

cs.CV↗

arXiv2025

AppAgentX: Evolving GUI Agents as Proficient Smartphone Users

Recent advancements in Large Language Models (LLMs) have led to the development of intelligent LLM-based agents capable of interacting with graphical user interfaces (GUIs). These agents demonstrate strong reasoning and adaptability, enabling them to perform complex tasks that traditionally required predefined rules. However, the reliance on step-by-step reasoning in LLM-based agents often results in inefficiencies, particularly for routine tasks. In contrast, traditional rule-based systems excel in efficiency but lack the intelligence and flexibility to adapt to novel scenarios. To address this challenge, we propose a novel evolutionary framework for GUI agents that enhances operational efficiency while retaining intelligence and flexibility. Our approach incorporates a memory mechanism that records the agent's task execution history. By analyzing this history, the agent identifies repetitive action sequences and evolves high-level actions that act as shortcuts, replacing these low-level operations and improving efficiency. This allows the agent to focus on tasks requiring more complex reasoning, while simplifying routine actions. Experimental results on multiple benchmark tasks demonstrate that our approach significantly outperforms existing methods in both efficiency and accuracy. The code will be open-sourced to support further research.

cs.AI↗

arXiv2025

Entanglement induced by quantum gravity in an infinite square well

In this work, we examine the entanglement dynamics of two massive particles confined within their respective infinite square potential wells induced by gravity. Assuming that each particle is initially in the ground state of its infinite square well, we investigate the formation of entanglement between the particles as a result of their gravitational interaction during their adiabatic movement towards each other. Our results reveal that, under suitable parameters, entanglement swiftly emerges. Compared to previous schemes, our approach significantly reduces the particle mass, greatly lowering the experimental threshold.

quant-ph↗

arXiv2025

VAPO: Efficient and Reliable Reinforcement Learning for Advanced Reasoning Tasks

We present VAPO, Value-based Augmented Proximal Policy Optimization framework for reasoning models., a novel framework tailored for reasoning models within the value-based paradigm. Benchmarked the AIME 2024 dataset, VAPO, built on the Qwen 32B pre-trained model, attains a state-of-the-art score of $\mathbf{60.4}$. In direct comparison under identical experimental settings, VAPO outperforms the previously reported results of DeepSeek-R1-Zero-Qwen-32B and DAPO by more than 10 points. The training process of VAPO stands out for its stability and efficiency. It reaches state-of-the-art performance within a mere 5,000 steps. Moreover, across multiple independent runs, no training crashes occur, underscoring its reliability. This research delves into long chain-of-thought (long-CoT) reasoning using a value-based reinforcement learning framework. We pinpoint three key challenges that plague value-based methods: value model bias, the presence of heterogeneous sequence lengths, and the sparsity of reward signals. Through systematic design, VAPO offers an integrated solution that effectively alleviates these challenges, enabling enhanced performance in long-CoT reasoning tasks.

cs.AI↗

arXiv2025

CADCrafter: Generating Computer-Aided Design Models from Unconstrained Images

Creating CAD digital twins from the physical world is crucial for manufacturing, design, and simulation. However, current methods typically rely on costly 3D scanning with labor-intensive post-processing. To provide a user-friendly design process, we explore the problem of reverse engineering from unconstrained real-world CAD images that can be easily captured by users of all experiences. However, the scarcity of real-world CAD data poses challenges in directly training such models. To tackle these challenges, we propose CADCrafter, an image-to-parametric CAD model generation framework that trains solely on synthetic textureless CAD data while testing on real-world images. To bridge the significant representation disparity between images and parametric CAD models, we introduce a geometry encoder to accurately capture diverse geometric features. Moreover, the texture-invariant properties of the geometric features can also facilitate the generalization to real-world scenarios. Since compiling CAD parameter sequences into explicit CAD models is a non-differentiable process, the network training inherently lacks explicit geometric supervision. To impose geometric validity constraints, we employ direct preference optimization (DPO) to fine-tune our model with the automatic code checker feedback on CAD sequence quality. Furthermore, we collected a real-world dataset, comprised of multi-view images and corresponding CAD command sequence pairs, to evaluate our method. Experimental results demonstrate that our approach can robustly handle real unconstrained CAD images, and even generalize to unseen general objects.

cs.CV↗

arXiv2025

Translating Multimodal AI into Real-World Inspection: TEMAI Evaluation Framework and Pathways for Implementation

This paper introduces the Translational Evaluation of Multimodal AI for Inspection (TEMAI) framework, bridging multimodal AI capabilities with industrial inspection implementation. Adapting translational research principles from healthcare to industrial contexts, TEMAI establishes three core dimensions: Capability (technical feasibility), Adoption (organizational readiness), and Utility (value realization). The framework demonstrates that technical capability alone yields limited value without corresponding adoption mechanisms. TEMAI incorporates specialized metrics including the Value Density Coefficient and structured implementation pathways. Empirical validation through retail and photovoltaic inspection implementations revealed significant differences in value realization patterns despite similar capability reduction rates, confirming the framework's effectiveness across diverse industrial sectors while highlighting the importance of industry-specific adaptation strategies.

cs.HC↗