arXiv subjects

Yue Wu

Publications and source records attributed to Yue Wu.

At least 145 records · Page 8Linked to original sources

arXiv2025

SimLOB: Learning Representations of Limited Order Book for Financial Market Simulation

Financial market simulation (FMS) serves as a promising tool for understanding market anomalies and the underlying trading behaviors. To ensure high-fidelity simulations, it is crucial to calibrate the FMS model for generating data closely resembling the observed market data. Previous efforts primarily focused on calibrating the mid-price data, leading to essential information loss of the market activities and thus biasing the calibrated model. The Limit Order Book (LOB) data is the fundamental data fully capturing the market micro-structure and is adopted by worldwide exchanges. However, LOB is not applicable to existing calibration objective functions due to its tabular structure not suitable for the vectorized input requirement. This paper proposes to explicitly learn the vectorized representations of LOB with a Transformer-based autoencoder. Then the latent vector, which captures the major information of LOB, can be applied for calibration. Extensive experiments show that the learned latent representation not only preserves the non-linear auto-correlation in the temporal axis, but the precedence between successive price levels of LOB. Besides, it is verified that the performance of the representation learning stage is consistent with the downstream calibration tasks. Thus, this work also progresses the FMS on LOB data, for the first time.

cs.CE↗

arXiv2025

Beyond Bradley-Terry Models: A General Preference Model for Language Model Alignment

Modeling human preferences is crucial for aligning foundation models with human values. Traditional reward modeling methods, such as the Bradley-Terry (BT) reward model, fall short in expressiveness, particularly in addressing intransitive preferences. In this paper, we introduce preference embedding, an approach that embeds responses into a latent space to capture intricate preference structures efficiently, achieving linear query complexity. Additionally, we propose preference score-based General Preference Optimization (GPO), which generalizes reward-based reinforcement learning from human feedback (RLHF). Experimental results show that our General Preference embedding Model (GPM) consistently outperforms the BT reward model on the RewardBench benchmark and effectively models cyclic preferences where any BT reward model behaves like a random guess. Furthermore, evaluations on downstream tasks such as AlpacaEval2.0, following the language model post-training with GPO and our general preference model, reveal performance improvements over BT models. These findings indicate that our method may enhance the alignment of foundation models with nuanced human values. The code is available at https://github.com/general-preference/general-preference-model.

cs.AI↗

arXiv2025

Online Learning Control Strategies for Industrial Processes with Application for Loosening and Conditioning

This paper proposes a novel adaptive Koopman Model Predictive Control (MPC) framework, termed HPC-AK-MPC, designed to address the dual challenges of time-varying dynamics and safe operation in complex industrial processes. The framework integrates two core strategies: online learning and historically-informed safety constraints. To contend with process time-variance, a Recursive Extended Dynamic Mode Decomposition (rEDMDc) technique is employed to construct an adaptive Koopman model capable of updating its parameters from real-time data, endowing the controller with the ability to continuously learn and track dynamic changes. To tackle the critical issue of safe operation under model uncertainty, we introduce a novel Historical Process Constraint (HPC) mechanism. This mechanism mines successful operational experiences from a historical database and, by coupling them with the confidence level of the online model, generates a dynamic "safety corridor" for the MPC optimization problem. This approach transforms implicit expert knowledge into explicit, adaptive constraints, establishing a dynamic balance between pursuing optimal performance and ensuring robust safety. The proposed HPC-AK-MPC method is applied to a real-world tobacco loosening and conditioning process and systematically validated using an "advisor mode" simulation framework with industrial data. Experimental results demonstrate that, compared to historical operations, the proposed method significantly improves the Process Capability Index (Cpk) for key quality variables across all tested batches, proving its substantial potential in enhancing control performance while guaranteeing operational safety.

eess.SY↗

arXiv2025

Tensor-to-Tensor Models with Fast Iterated Sum Features

Data in the form of images or higher-order tensors is ubiquitous in modern deep learning applications. Owing to their inherent high dimensionality, the need for subquadratic layers processing such data is even more pressing than for sequence data. We propose a novel tensor-to-tensor layer with linear cost in the input size, utilizing the mathematical gadget of ``corner trees'' from the field of permutation counting. In particular, for order-two tensors, we provide an image-to-image layer that can be plugged into image processing pipelines. On the one hand, our method can be seen as a higher-order generalization of state-space models. On the other hand, it is based on a multiparameter generalization of the signature of iterated integrals (or sums). The proposed tensor-to-tensor concept is used to build a neural network layer called the Fast Iterated Sums (FIS) layer which integrates seamlessly with other layer types. We demonstrate the usability of the FIS layer with both classification and anomaly detection tasks. By replacing some layers of a smaller ResNet architecture with FIS, a similar accuracy (with a difference of only 0.1\%) was achieved in comparison to a larger ResNet while reducing the number of trainable parameters and multi-add operations. The FIS layer was also used to build an anomaly detection model that achieved an average AUROC of 97.3\% on the texture images of the popular MVTec AD dataset. The processing and modelling codes are publicly available at https://github.com/diehlj/fast-iterated-sums.

cs.CV↗

arXiv2025

ChatMyopia: An AI Agent for Pre-consultation Education in Primary Eye Care Settings

Large language models (LLMs) show promise for tailored healthcare communication but face challenges in interpretability and multi-task integration particularly for domain-specific needs like myopia, and their real-world effectiveness as patient education tools has yet to be demonstrated. Here, we introduce ChatMyopia, an LLM-based AI agent designed to address text and image-based inquiries related to myopia. To achieve this, ChatMyopia integrates an image classification tool and a retrieval-augmented knowledge base built from literature, expert consensus, and clinical guidelines. Myopic maculopathy grading task, single question examination and human evaluations validated its ability to deliver personalized, accurate, and safe responses to myopia-related inquiries with high scalability and interpretability. In a randomized controlled trial (n=70, NCT06607822), ChatMyopia significantly improved patient satisfaction compared to traditional leaflets, enhancing patient education in accuracy, empathy, disease awareness, and patient-eyecare practitioner communication. These findings highlight ChatMyopia's potential as a valuable supplement to enhance patient education and improve satisfaction with medical services in primary eye care settings.

cs.HC↗

arXiv2025

Neural nanophotonic object detector with ultra-wide field-of-view

Intelligent object detection, which extracts crucial information like targets categories and locations, plays a vital role in emerging technologies including autonomous driving, the Internet of Things, and next-generation mobile communication systems. With the advancement of intelligent object detectors towards higher integration and miniaturization, their portability and adaptability to a broader range of scenarios have been significantly enhanced. However, this progress comes at the cost of reduced detection quality and narrower field-of-view, which severely impacts overall performances. Here we present a neural nanophotonic object detector based on a metalens array, capable of delivering high-quality imaging with an ultra-wide field-of-view of 135°. The combined neural network not only further improves the imaging quality, but also enables the detector to achieve high-precision target recognition and localization. Moreover, we integrated the neural nanophotonic object detector into a miniature unmanned aerial vehicle to enable wide-angle imaging and intelligent recognition of various real-world dynamic objects, demonstrating the high mobility and flexibility of our neural nanophotonic object detector. Our study presents a systematic framework for advancing revolutionary intelligent detection systems, offering significant potential for a wide range of future applications.

physics.optics↗

arXiv2025

Random periodic solutions for stochastic differential equations with non-uniform dissipativity

This paper is concerned with the existence and uniqueness of random periodic solutions for stochastic differential equations (SDEs), where the drift terms involved need not to be uniformly dissipative. On the one hand, via the reflection coupling approach, we investigate the existence of random periodic solutions in the sense of distribution for SDEs without memory, where the drifts are merely dissipative at long distance. On the other hand, via the synchronous coupling strategy, we establish respectively the existence of pathwise random periodic solutions for functional SDEs with a finite time lag and an infinite time lag, in which the drifts are only dissipative on average rather than uniformly dissipative with respect to the time parameters.

math.PR↗

arXiv2025

Alita: Generalist Agent Enabling Scalable Agentic Reasoning with Minimal Predefinition and Maximal Self-Evolution

Recent advances in large language models (LLMs) have enabled agents to autonomously perform complex, open-ended tasks. However, many existing frameworks depend heavily on manually predefined tools and workflows, which hinder their adaptability, scalability, and generalization across domains. In this work, we introduce Alita--a generalist agent designed with the principle of "Simplicity is the ultimate sophistication," enabling scalable agentic reasoning through minimal predefinition and maximal self-evolution. For minimal predefinition, Alita is equipped with only one component for direct problem-solving, making it much simpler and neater than previous approaches that relied heavily on hand-crafted, elaborate tools and workflows. This clean design enhances its potential to generalize to challenging questions, without being limited by tools. For Maximal self-evolution, we enable the creativity of Alita by providing a suite of general-purpose components to autonomously construct, refine, and reuse external capabilities by generating task-related model context protocols (MCPs) from open source, which contributes to scalable agentic reasoning. Notably, Alita achieves 75.15% pass@1 and 87.27% pass@3 accuracy, which is top-ranking among general-purpose agents, on the GAIA benchmark validation dataset, 74.00% and 52.00% pass@1, respectively, on Mathvista and PathVQA, outperforming many agent systems with far greater complexity. More details will be updated at $\href{https://github.com/CharlesQ9/Alita}{https://github.com/CharlesQ9/Alita}$.

cs.AI↗

arXiv2025

Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data?

Aligning large language models (LLMs) with human preferences remains a key challenge in AI. Preference-based optimization methods, such as Reinforcement Learning with Human Feedback (RLHF) and Direct Preference Optimization (DPO), rely on human-annotated datasets to improve alignment. In this work, we identify a crucial property of the existing learning method: the distinguishing signal obtained in preferred responses is often concentrated in the early tokens. We refer to this as shallow preference signals. To explore this property, we systematically truncate preference datasets at various points and train both reward models and DPO models on the truncated data. Surprisingly, models trained on truncated datasets, retaining only the first half or fewer tokens, achieve comparable or even superior performance to those trained on full datasets. For example, a reward model trained on the Skywork-Reward-Preference-80K-v0.2 dataset outperforms the full dataset when trained on a 40\% truncated dataset. This pattern is consistent across multiple datasets, suggesting the widespread presence of shallow preference signals. We further investigate the distribution of the reward signal through decoding strategies. We consider two simple decoding strategies motivated by the shallow reward signal observation, namely Length Control Decoding and KL Threshold Control Decoding, which leverage shallow preference signals to optimize the trade-off between alignment and computational efficiency. The performance is even better, which again validates our hypothesis. The phenomenon of shallow preference signals highlights potential issues in LLM alignment: existing alignment methods often focus on aligning only the initial tokens of responses, rather than considering the full response. This could lead to discrepancies with real-world human preferences, resulting in suboptimal alignment performance.

cs.CL↗

arXiv2025

Granular Loco-Manipulation: Repositioning Rocks Through Strategic Sand Avalanche

Legged robots have the potential to leverage obstacles to climb steep sand slopes. However, efficiently repositioning these obstacles to desired locations is challenging. Here we present DiffusiveGRAIN, a learning-based method that enables a multi-legged robot to strategically induce localized sand avalanches during locomotion and indirectly manipulate obstacles. We conducted 375 trials, systematically varying obstacle spacing, robot orientation, and leg actions in 75 of them. Results show that the movement of closely-spaced obstacles exhibits significant interference, requiring joint modeling. In addition, different multi-leg excavation actions could cause distinct robot state changes, necessitating integrated planning of manipulation and locomotion. To address these challenges, DiffusiveGRAIN includes a diffusion-based environment predictor to capture multi-obstacle movements under granular flow interferences and a robot state predictor to estimate changes in robot state from multi-leg action patterns. Deployment experiments (90 trials) demonstrate that by integrating the environment and robot state predictors, the robot can autonomously plan its movements based on loco-manipulation goals, successfully shifting closely located rocks to desired locations in over 65% of trials. Our study showcases the potential for a locomoting robot to strategically manipulate obstacles to achieve improved mobility on challenging terrains.

cs.RO↗

arXiv2025

34 Examples of LLM Applications in Materials Science and Chemistry: Towards Automation, Assistants, Agents, and Accelerated Scientific Discovery

Large Language Models (LLMs) are reshaping many aspects of materials science and chemistry research, enabling advances in molecular property prediction, materials design, scientific automation, knowledge extraction, and more. Recent developments demonstrate that the latest class of models are able to integrate structured and unstructured data, assist in hypothesis generation, and streamline research workflows. To explore the frontier of LLM capabilities across the research lifecycle, we review applications of LLMs through 34 total projects developed during the second annual Large Language Model Hackathon for Applications in Materials Science and Chemistry, a global hybrid event. These projects spanned seven key research areas: (1) molecular and material property prediction, (2) molecular and material design, (3) automation and novel interfaces, (4) scientific communication and education, (5) research data management and automation, (6) hypothesis generation and evaluation, and (7) knowledge extraction and reasoning from the scientific literature. Collectively, these applications illustrate how LLMs serve as versatile predictive models, platforms for rapid prototyping of domain-specific tools, and much more. In particular, improvements in both open source and proprietary LLM performance through the addition of reasoning, additional training data, and new techniques have expanded effectiveness, particularly in low-data environments and interdisciplinary research. As LLMs continue to improve, their integration into scientific workflows presents both new opportunities and new challenges, requiring ongoing exploration, continued refinement, and further research to address reliability, interpretability, and reproducibility.

cs.LG↗

arXiv2025

A High-Performance Thermal Infrared Object Detection Framework with Centralized Regulation

Thermal Infrared (TIR) technology involves the use of sensors to detect and measure infrared radiation emitted by objects, and it is widely utilized across a broad spectrum of applications. The advancements in object detection methods utilizing TIR images have sparked significant research interest. However, most traditional methods lack the capability to effectively extract and fuse local-global information, which is crucial for TIR-domain feature attention. In this study, we present a novel and efficient thermal infrared object detection framework, known as CRT-YOLO, that is based on centralized feature regulation, enabling the establishment of global-range interaction on TIR information. Our proposed model integrates efficient multi-scale attention (EMA) modules, which adeptly capture long-range dependencies while incurring minimal computational overhead. Additionally, it leverages the Centralized Feature Pyramid (CFP) network, which offers global regulation of TIR features. Extensive experiments conducted on two benchmark datasets demonstrate that our CRT-YOLO model significantly outperforms conventional methods for TIR image object detection. Furthermore, the ablation study provides compelling evidence of the effectiveness of our proposed modules, reinforcing the potential impact of our approach on advancing the field of thermal infrared object detection.

cs.CV↗

arXiv2025

AI-powered virtual eye: perspective, challenges and opportunities

We envision the "virtual eye" as a next-generation, AI-powered platform that uses interconnected foundation models to simulate the eye's intricate structure and biological function across all scales. Advances in AI, imaging, and multiomics provide a fertile ground for constructing a universal, high-fidelity digital replica of the human eye. This perspective traces the evolution from early mechanistic and rule-based models to contemporary AI-driven approaches, integrating in a unified model with multimodal, multiscale, dynamic predictive capabilities and embedded feedback mechanisms. We propose a development roadmap emphasizing the roles of large-scale multimodal datasets, generative AI, foundation models, agent-based architectures, and interactive interfaces. Despite challenges in interpretability, ethics, data processing and evaluation, the virtual eye holds the potential to revolutionize personalized ophthalmic care and accelerate research into ocular health and disease.

q-bio.TO↗

arXiv2025

Induced Diffusion of Internal Gravity Waves: Directionality and Role in Ocean Mixing

Induced diffusion (ID), an important mechanism of spectral energy transfer in the internal gravity wave (IGW) field, plays a significant role in driving turbulent dissipation in the ocean interior. In this study, we revisit the ID mechanism to elucidate its directionality and role in ocean mixing under varying IGW spectral forms, with particular attention to deviations from the standard Garrett-Munk (GM) spectrum. The original interpretation of ID as an action diffusion process, as proposed by McComas et al., suggests that ID is inherently bidirectional, with its direction governed by the vertical-wavenumber spectral slope $σ$ of the IGW action spectrum, $n \propto m^σ$. In contrast, by evaluating the wave kinetic equation, we reveal a more complete depiction of ID, comprising both diffusive and scale-separated transfers that are rooted in energy conservation within wave triads. Although the action diffusion may reverse direction depending on the sign of $σ$ (i.e., between red and blue spectral cases), the combined ID transfer consistently leads to a forward energy cascade at the dissipation scale, thereby contributing positively to turbulent dissipation. This supports the viewpoint of ID as a dissipative mechanism in physical oceanography. This study presents a physically grounded overview of ID and offers insights into the specific types of wave-wave interactions responsible for turbulent dissipation.

physics.ao-ph↗

arXiv2025

Phi-4-reasoning Technical Report

We introduce Phi-4-reasoning, a 14-billion parameter reasoning model that achieves strong performance on complex reasoning tasks. Trained via supervised fine-tuning of Phi-4 on carefully curated set of "teachable" prompts-selected for the right level of complexity and diversity-and reasoning demonstrations generated using o3-mini, Phi-4-reasoning generates detailed reasoning chains that effectively leverage inference-time compute. We further develop Phi-4-reasoning-plus, a variant enhanced through a short phase of outcome-based reinforcement learning that offers higher performance by generating longer reasoning traces. Across a wide range of reasoning tasks, both models outperform significantly larger open-weight models such as DeepSeek-R1-Distill-Llama-70B model and approach the performance levels of full DeepSeek-R1 model. Our comprehensive evaluations span benchmarks in math and scientific reasoning, coding, algorithmic problem solving, planning, and spatial understanding. Interestingly, we observe a non-trivial transfer of improvements to general-purpose benchmarks as well. In this report, we provide insights into our training data, our training methodologies, and our evaluations. We show that the benefit of careful data curation for supervised fine-tuning (SFT) extends to reasoning language models, and can be further amplified by reinforcement learning (RL). Finally, our evaluation points to opportunities for improving how we assess the performance and robustness of reasoning models.

cs.AI↗

arXiv2025

EmoAgent: Assessing and Safeguarding Human-AI Interaction for Mental Health Safety

The rise of LLM-driven AI characters raises safety concerns, particularly for vulnerable human users with psychological disorders. To address these risks, we propose EmoAgent, a multi-agent AI framework designed to evaluate and mitigate mental health hazards in human-AI interactions. EmoAgent comprises two components: EmoEval simulates virtual users, including those portraying mentally vulnerable individuals, to assess mental health changes before and after interactions with AI characters. It uses clinically proven psychological and psychiatric assessment tools (PHQ-9, PDI, PANSS) to evaluate mental risks induced by LLM. EmoGuard serves as an intermediary, monitoring users' mental status, predicting potential harm, and providing corrective feedback to mitigate risks. Experiments conducted in popular character-based chatbots show that emotionally engaging dialogues can lead to psychological deterioration in vulnerable users, with mental state deterioration in more than 34.4% of the simulations. EmoGuard significantly reduces these deterioration rates, underscoring its role in ensuring safer AI-human interactions. Our code is available at: https://github.com/1akaman/EmoAgent

cs.AI↗

arXiv2025

A Common Pitfall of Margin-based Language Model Alignment: Gradient Entanglement

Reinforcement Learning from Human Feedback (RLHF) has become the predominant approach for language model (LM) alignment. At its core, RLHF uses a margin-based loss for preference optimization, specifying ideal LM behavior only by the difference between preferred and dispreferred responses. In this paper, we identify a common pitfall of margin-based methods -- the under-specification of ideal LM behavior on preferred and dispreferred responses individually, which leads to two unintended consequences as the margin increases: (1) The probability of dispreferred (e.g., unsafe) responses may increase, resulting in potential safety alignment failures. (2) The probability of preferred responses may decrease, even when those responses are ideal. We demystify the reasons behind these problematic behaviors: margin-based losses couple the change in the preferred probability to the gradient of the dispreferred one, and vice versa, often preventing the preferred probability from increasing while the dispreferred one decreases, and thus causing a synchronized increase or decrease in both probabilities. We term this effect, inherent in margin-based objectives, gradient entanglement. Formally, we derive conditions for general margin-based alignment objectives under which gradient entanglement becomes concerning: the inner product of the gradients of preferred and dispreferred log-probabilities is large relative to the individual gradient norms. We theoretically investigate why such inner products can be large when aligning language models and empirically validate our findings. Empirical implications of our framework extend to explaining important differences in the training dynamics of various preference optimization algorithms, and suggesting potential algorithm designs to mitigate the under-specification issue of margin-based methods and thereby improving language model alignment.

cs.LG↗

arXiv2025

Network-Integrated Decoding System for Real-Time Quantum Error Correction with Lattice Surgery

Existing real-time decoders for surface codes are limited to isolated logical qubits and do not support logical operations involving multiple logical qubits. We present DECONET, a first-of-its-kind decoding system that scales to thousands of logical qubits and supports logical operations implemented through lattice surgery. DECONET organizes compute resources in a network-integrated hybrid tree-grid structure, which results in minimal latency increase and no throughput degradation as the system grows. Specifically, DECONET can be scaled to any arbitrary number of $l$ logical qubits by increasing the compute resources by $O(l \times log(l))$, which provides the required $O(l)$ growth in I/O resources while incurring only an $O(log(l))$ increase in latency-a modest growth that is sufficient for thousands of logical qubits. Moreover, we analytically show that the scaling approach preserves throughput, keeping DECONET backlog-free for any number of logical qubits. We report an exploratory prototype of DECONET, called DECONET/HELIOS, built with five VMK-180 FPGAs, that successfully decodes 100 logical qubits of distance five. For 100 logical qubits, under a phenomenological noise rate of 0.1%, the DECONET/HELIOS has an average latency of 2.40 μs and an inverse throughput of 0.84 μs per measurement round.

quant-ph↗