arXiv subjects

Sheng Zhang

Publications and source records attributed to Sheng Zhang.

At least 91 records · Page 5Linked to original sources

arXiv2025

Efficient Real-Time Aircraft ETA Prediction via Feature Tokenization Transformer

Estimated time of arrival (ETA) for airborne aircraft in real-time is crucial for arrival management in aviation, particularly for runway sequencing. Given the rapidly changing airspace context, the ETA prediction efficiency is as important as its accuracy in a real-time arrival aircraft management system. In this study, we utilize a feature tokenization-based Transformer model to efficiently predict aircraft ETA. Feature tokenization projects raw inputs to latent spaces, while the multi-head self-attention mechanism in the Transformer captures important aspects of the projections, alleviating the need for complex feature engineering. Moreover, the Transformer's parallel computation capability allows it to handle ETA requests at a high frequency, i.e., 1HZ, which is essential for a real-time arrival management system. The model inputs include raw data, such as aircraft latitude, longitude, ground speed, theta degree for the airport, day and hour from track data, the weather context, and aircraft wake turbulence category. With a data sampling rate of 1HZ, the ETA prediction is updated every second. We apply the proposed aircraft ETA prediction approach to Singapore Changi Airport (ICAO Code: WSSS) using one-month Automatic Dependent Surveillance-Broadcast (ADS-B) data from October 1 to October 31, 2022. In the experimental evaluation, the ETA modeling covers all aircraft within a range of 10NM to 300NM from WSSS. The results show that our proposed method method outperforms the commonly used boosting tree based model, improving accuracy by 7\% compared to XGBoost, while requiring only 39\% of its computing time. Experimental results also indicate that, with 40 aircraft in the airspace at a given timestamp, the ETA inference time is only 51.7 microseconds, making it promising for real-time arrival management systems.

cs.LG↗

arXiv2025

PDLogger: Automated Logging Framework for Practical Software Development

Logging is indispensable for maintaining the reliability and diagnosability of modern software, yet developers still struggle to decide where and how to log effectively. Existing automated logging techniques focus on isolated sub-tasks - predicting a single log position, level, or message - and therefore cannot produce complete, high-quality log statements that reflect real-world practice in which multiple logs often appear inside one method. They also neglect deeper semantic dependencies among methods and consider only a narrow set of candidate variables, leading to superficial or incomplete logs. In this paper, we present PDLogger, the first end-to-end log generation technique expressly designed for practical, multi-log scenarios. PDLogger operates in three phases. (1) Log position prediction: block-type-aware structured prompts guide a large language model (LLM) to suggest candidate positions across all control-flow blocks of a method. (2) Log generation: backward program slicing supplies precise inter-procedural control and data-dependency context, while an expanded variable extractor captures both member and external function expressions; the enriched prompt enables the LLM to emit a full log statement (position, level, message, variables). (3) Log refinement: level correction and context-sensitive deduplication prune false positives and redundant logs. We evaluate PDLogger on 3,113 log statements drawn from two widely used Java projects. Compared with the strongest prior systems, PDLogger improves log-position precision by 139.0 percent, F1 by 69.2 percent, level accuracy by 82.3 percent, variable precision by 131.8 percent, and message quality (BERTScore) by 65.7 percent. The framework consistently performs well with different mainstream LLMs, demonstrating robustness and generality. PDLogger's implementation is available as open source to foster future research and adoption.

cs.SE↗

arXiv2025

FlexiTex: Enhancing Texture Generation via Visual Guidance

Recent texture generation methods achieve impressive results due to the powerful generative prior they leverage from large-scale text-to-image diffusion models. However, abstract textual prompts are limited in providing global textural or shape information, which results in the texture generation methods producing blurry or inconsistent patterns. To tackle this, we present FlexiTex, embedding rich information via visual guidance to generate a high-quality texture. The core of FlexiTex is the Visual Guidance Enhancement module, which incorporates more specific information from visual guidance to reduce ambiguity in the text prompt and preserve high-frequency details. To further enhance the visual guidance, we introduce a Direction-Aware Adaptation module that automatically designs direction prompts based on different camera poses, avoiding the Janus problem and maintaining semantically global consistency. Benefiting from the visual guidance, FlexiTex produces quantitatively and qualitatively sound results, demonstrating its potential to advance texture generation for real-world applications.

cs.CV↗

arXiv2025

RetinaLogos: Fine-Grained Synthesis of High-Resolution Retinal Images Through Captions

The scarcity of high-quality, labelled retinal imaging data, which presents a significant challenge in the development of machine learning models for ophthalmology, hinders progress in the field. Existing methods for synthesising Colour Fundus Photographs (CFPs) largely rely on predefined disease labels, which restricts their ability to generate images that reflect fine-grained anatomical variations, subtle disease stages, and diverse pathological features beyond coarse class categories. To overcome these challenges, we first introduce an innovative pipeline that creates a large-scale, captioned retinal dataset comprising 1.4 million entries, called RetinaLogos-1400k. Specifically, RetinaLogos-1400k uses the visual language model(VLM) to describe retinal conditions and key structures, such as optic disc configuration, vascular distribution, nerve fibre layers, and pathological features. Building on this dataset, we employ a novel three-step training framework, RetinaLogos, which enables fine-grained semantic control over retinal images and accurately captures different stages of disease progression, subtle anatomical variations, and specific lesion types. Through extensive experiments, our method demonstrates superior performance across multiple datasets, with 62.07% of text-driven synthetic CFPs indistinguishable from real ones by ophthalmologists. Moreover, the synthetic data improves accuracy by 5%-10% in diabetic retinopathy grading and glaucoma detection. Codes are available at https://github.com/uni-medical/retina-text2cfp.

eess.IV↗

arXiv2025

Optical Excitations of Flat Bands Induced by Exciton Condensation in Ta$_2$Pd$_3$Te$_{5}$

We report on the charge dynamics of Ta$_2$Pd$_3$Te$_5$ using temperature-dependent optical spectroscopy with polarized light. We observe a metal-insulator transition characterized by the collapse of Drude response and the emergence of sharp and narrow absorption peaks at low temperatures. Unlike previous excitonic insulator candidates such as TiSe$_2$ and Ta$_2$NiSe$_5$, where the excitonic order is intertwined with charge density wave or structural instabilities, the sharp features in Ta$_2$Pd$_3$Te$_5$ point to intrinsic excitonic excitations associated with ultra-flat bands driven by many-body renormalization of the band structure via spontaneous exciton condensation. Our findings thus provide clear-cut optical evidence for exciton condensation in a bulk crystal and establish Ta$_2$Pd$_3$Te$_5$ as a promising platform for exploring correlated quantum phases and novel excitonic phenomena.

cond-mat.mtrl-sci↗

arXiv2025

Spin-polarized triplet excitonic insulators in Ta3X8 (X=I, Br) monolayers

Bose-Einstein condensation of spin-polarized triplet excitons can give rise to an intriguing spin supercurrent, enabling experimental detection of exciton condensation. In this work, we predict that Ta3X8 (X=I, Br) ferromagnetic monolayers are spin-polarized triplet excitonic insulators (EIs), based on the systematic first-principles GW calculations coupled with the Bethe-Salpeter equation (GW+BSE). The single-particle calculations of spin-polarized band structures reveal that these monolayers are bipolar magnetic semiconductors, where the highest valence band and the lowest conduction band possess opposite spin polarization. The two low-energy bands, primarily originating from Ta $d_{z^2}$ orbitals, are almost flat. The same-orbital parity and opposite-spin natures of the band-edge states effectively suppress dielectric screening, promoting the emergence of the EI state. The GW+BSE calculations reveal that the binding energy of the lowest-energy exciton is 1.499 eV for Ta3I8 monolayer and 1.986 eV for Ta3Br8 monolayer. Since both values exceed the respective GW band gaps, these results indicate a strong excitonic instability in these monolayers. A wavefunction analysis confirms that the lowest-energy exciton is a tightly bound Frenkel-like state, exhibiting a spin-polarized triplet nature with $S_z=1$. Our findings establish a valuable material platform for investigating spin-polarized triplet EIs, offering promising potential for spintronic applications.

cond-mat.mtrl-sci↗

arXiv2025

Hunyuan3D 2.5: Towards High-Fidelity 3D Assets Generation with Ultimate Details

In this report, we present Hunyuan3D 2.5, a robust suite of 3D diffusion models aimed at generating high-fidelity and detailed textured 3D assets. Hunyuan3D 2.5 follows two-stages pipeline of its previous version Hunyuan3D 2.0, while demonstrating substantial advancements in both shape and texture generation. In terms of shape generation, we introduce a new shape foundation model -- LATTICE, which is trained with scaled high-quality datasets, model-size, and compute. Our largest model reaches 10B parameters and generates sharp and detailed 3D shape with precise image-3D following while keeping mesh surface clean and smooth, significantly closing the gap between generated and handcrafted 3D shapes. In terms of texture generation, it is upgraded with phyiscal-based rendering (PBR) via a novel multi-view architecture extended from Hunyuan3D 2.0 Paint model. Our extensive evaluation shows that Hunyuan3D 2.5 significantly outperforms previous methods in both shape and end-to-end texture generation.

cs.CV↗

arXiv2025

Hunyuan3D 2.1: From Images to High-Fidelity 3D Assets with Production-Ready PBR Material

3D AI-generated content (AIGC) is a passionate field that has significantly accelerated the creation of 3D models in gaming, film, and design. Despite the development of several groundbreaking models that have revolutionized 3D generation, the field remains largely accessible only to researchers, developers, and designers due to the complexities involved in collecting, processing, and training 3D models. To address these challenges, we introduce Hunyuan3D 2.1 as a case study in this tutorial. This tutorial offers a comprehensive, step-by-step guide on processing 3D data, training a 3D generative model, and evaluating its performance using Hunyuan3D 2.1, an advanced system for producing high-resolution, textured 3D assets. The system comprises two core components: the Hunyuan3D-DiT for shape generation and the Hunyuan3D-Paint for texture synthesis. We will explore the entire workflow, including data preparation, model architecture, training strategies, evaluation metrics, and deployment. By the conclusion of this tutorial, you will have the knowledge to finetune or develop a robust 3D generative model suitable for applications in gaming, virtual reality, and industrial design.

cs.CV↗

arXiv2025

Remote entanglement generation via enhanced quantum state transfer

Achieving robust and scalable remote quantum entanglement is a fundamental challenge for the development of distributed quantum networks and modular quantum computing systems. Along this, perfect state transfer (PST) and fractional state transfer (FST) have emerged as promising schemes for quantum state transfer and remote entanglement generation using only nearest-neighbor couplings. However, the current implementations suffer from quantum loss and limited parameter tunability. In this work, we propose a new quantum state transfer scheme based on a zig-zag configuration, which introduces a controlling parameter for PST and FST. We show that this new parameter can suppress the population in the intermediate qubits, thereby reducing losses. We experimentally demonstrate the dynamics of different configurations on a superconducting quantum processor, achieving an $18\%$ reduction in error for remote Bell state generation in a 1D ($1\times5$) qubit chain, and exhibit robustness against certain types of noise. Then we extend our approach to a 2D network, successfully generating a W state among the four corner qubits. These results highlight the potential of our enhanced quantum state transfer scheme for scalable and noise-resilient quantum communication and computing.

quant-ph↗

arXiv2025

From Motion to Behavior: Hierarchical Modeling of Humanoid Generative Behavior Control

Human motion generative modeling or synthesis aims to characterize complicated human motions of daily activities in diverse real-world environments. However, current research predominantly focuses on either low-level, short-period motions or high-level action planning, without taking into account the hierarchical goal-oriented nature of human activities. In this work, we take a step forward from human motion generation to human behavior modeling, which is inspired by cognitive science. We present a unified framework, dubbed Generative Behavior Control (GBC), to model diverse human motions driven by various high-level intentions by aligning motions with hierarchical behavior plans generated by large language models (LLMs). Our insight is that human motions can be jointly controlled by task and motion planning in robotics, but guided by LLMs to achieve improved motion diversity and physical fidelity. Meanwhile, to overcome the limitations of existing benchmarks, i.e., lack of behavioral plans, we propose GBC-100K dataset annotated with a hierarchical granularity of semantic and motion plans driven by target goals. Our experiments demonstrate that GBC can generate more diverse and purposeful high-quality human motions with 10* longer horizons compared with existing methods when trained on GBC-100K, laying a foundation for future research on behavioral modeling of human motions. Our dataset and source code will be made publicly available.

cs.RO↗

arXiv2025

Offset Unlearning for Large Language Models

Despite the strong capabilities of Large Language Models (LLMs) to acquire knowledge from their training corpora, the memorization of sensitive information in the corpora such as copyrighted, biased, and private content has led to ethical and legal concerns. In response to these challenges, unlearning has emerged as a potential remedy for LLMs affected by problematic training data. However, previous unlearning techniques are either not applicable to black-box LLMs due to required access to model internal weights, or violate data protection principles by retaining sensitive data for inference-time correction. We propose δ-Unlearning, an offset unlearning framework for black-box LLMs. Instead of tuning the black-box LLM itself, δ-Unlearning learns the logit offset needed for unlearning by contrasting the logits from a pair of smaller models. Experiments demonstrate that δ- Unlearning can effectively unlearn target data while maintaining similar or even stronger performance on general out-of-forget-scope tasks. δ-Unlearning also effectively incorporates different unlearning algorithms, making our approach a versatile solution to adapting various existing unlearning algorithms to black-box LLMs.

cs.CL↗

arXiv2025

Dynamic Snake Upsampling Operater and Boundary-Skeleton Weighted Loss for Tubular Structure Segmentation

Accurate segmentation of tubular topological structures (e.g., fissures and vasculature) is critical in various fields to guarantee dependable downstream quantitative analysis and modeling. However, in dense prediction tasks such as semantic segmentation and super-resolution, conventional upsampling operators cannot accommodate the slenderness of tubular structures and the curvature of morphology. This paper introduces a dynamic snake upsampling operators and a boundary-skeleton weighted loss tailored for topological tubular structures. Specifically, we design a snake upsampling operators based on an adaptive sampling domain, which dynamically adjusts the sampling stride according to the feature map and selects a set of subpixel sampling points along the serpentine path, enabling more accurate subpixel-level feature recovery for tubular structures. Meanwhile, we propose a skeleton-to-boundary increasing weighted loss that trades off main body and boundary weight allocation based on mask class ratio and distance field, preserving main body overlap while enhancing focus on target topological continuity and boundary alignment precision. Experiments across various domain datasets and backbone networks show that this plug-and-play dynamic snake upsampling operator and boundary-skeleton weighted loss boost both pixel-wise segmentation accuracy and topological consistency of results.

cs.CV↗

arXiv2025

Demonstrating Coherent Quantum Routers for Bucket-Brigade Quantum Random Access Memory on a Superconducting Processor

Quantum routers (QRouters) are essential components of bucket-brigade quantum random access memory (QRAM), enabling quantum applications such as Grover's search and quantum machine learning. Despite significant theoretical advances, achieving scalable and coherent QRouters experimentally remains challenging. Here, we demonstrate coherent quantum routers using a superconducting quantum processor, laying a practical foundation for scalable QRAM systems. The quantum router at the core of our implementation utilizes the transition composite gate (TCG) scheme, wherein auxiliary energy levels temporarily mediate conditional interactions, substantially reducing circuit depth compared to traditional gate decompositions. Moreover, by encoding routing addresses in the non-adjacent qutrit states $|0\rangle$ and $|2\rangle$, our design inherently enables eraser-detection capability, providing efficient post-selection to mitigate routing errors. Experimentally, we achieve individual QRouter fidelities up to 95.74%, and validate scalability through a two-layer quantum routing network achieving an average fidelity of 82.40%. Our results represent a significant advancement in quantum routing technology, providing enhanced fidelity, built-in error resilience, and practical scalability crucial for the development of future QRAM and large-scale quantum computing architectures.

quant-ph↗

arXiv2025

DSMentor: Enhancing Data Science Agents with Curriculum Learning and Online Knowledge Accumulation

Large language model (LLM) agents have shown promising performance in generating code for solving complex data science problems. Recent studies primarily focus on enhancing in-context learning through improved search, sampling, and planning techniques, while overlooking the importance of the order in which problems are tackled during inference. In this work, we develop a novel inference-time optimization framework, referred to as DSMentor, which leverages curriculum learning -- a strategy that introduces simpler task first and progressively moves to more complex ones as the learner improves -- to enhance LLM agent performance in challenging data science tasks. Our mentor-guided framework organizes data science tasks in order of increasing difficulty and incorporates a growing long-term memory to retain prior experiences, guiding the agent's learning progression and enabling more effective utilization of accumulated knowledge. We evaluate DSMentor through extensive experiments on DSEval and QRData benchmarks. Experiments show that DSMentor using Claude-3.5-Sonnet improves the pass rate by up to 5.2% on DSEval and QRData compared to baseline agents. Furthermore, DSMentor demonstrates stronger causal reasoning ability, improving the pass rate by 8.8% on the causality problems compared to GPT-4 using Program-of-Thoughts prompts. Our work underscores the importance of developing effective strategies for accumulating and utilizing knowledge during inference, mirroring the human learning process and opening new avenues for improving LLM performance through curriculum-based inference optimization.

cs.AI↗

arXiv2025

STAR-Rec: Making Peace with Length Variance and Pattern Diversity in Sequential Recommendation

Recent deep sequential recommendation models often struggle to effectively model key characteristics of user behaviors, particularly in handling sequence length variations and capturing diverse interaction patterns. We propose STAR-Rec, a novel architecture that synergistically combines preference-aware attention and state-space modeling through a sequence-level mixture-of-experts framework. STAR-Rec addresses these challenges by: (1) employing preference-aware attention to capture both inherently similar item relationships and diverse preferences, (2) utilizing state-space modeling to efficiently process variable-length sequences with linear complexity, and (3) incorporating a mixture-of-experts component that adaptively routes different behavioral patterns to specialized experts, handling both focused category-specific browsing and diverse category exploration patterns. We theoretically demonstrate how the state space model and attention mechanisms can be naturally unified in recommendation scenarios, where SSM captures temporal dynamics through state compression while attention models both similar and diverse item relationships. Extensive experiments on four real-world datasets demonstrate that STAR-Rec consistently outperforms state-of-the-art sequential recommendation methods, particularly in scenarios involving diverse user behaviors and varying sequence lengths.

cs.IR↗

arXiv2025

X-Reasoner: Towards Generalizable Reasoning Across Modalities and Domains

Recent proprietary models (e.g., o3) have begun to demonstrate strong multimodal reasoning capabilities. Yet, most existing open-source research concentrates on training text-only reasoning models, with evaluations limited to mainly mathematical and general-domain tasks. Therefore, it remains unclear how to effectively extend reasoning capabilities beyond text input and general domains. This paper explores a fundamental research question: Is reasoning generalizable across modalities and domains? Our findings support an affirmative answer: General-domain text-based post-training can enable such strong generalizable reasoning. Leveraging this finding, we introduce X-Reasoner, a vision-language model post-trained solely on general-domain text for generalizable reasoning, using a two-stage approach: an initial supervised fine-tuning phase with distilled long chain-of-thoughts, followed by reinforcement learning with verifiable rewards. Experiments show that X-Reasoner successfully transfers reasoning capabilities to both multimodal and out-of-domain settings, outperforming existing state-of-the-art models trained with in-domain and multimodal data across various general and medical benchmarks (Figure 1). Additionally, we find that X-Reasoner's performance in specialized domains can be further enhanced through continued training on domain-specific text-only data. Building upon this, we introduce X-Reasoner-Med, a medical-specialized variant that achieves new state of the art on numerous text-only and multimodal medical benchmarks.

cs.AI↗

arXiv2025

Scalable and modular generation of multipartite entangled states through memory-enhanced fusion

Efficient generation of large-scale multipartite entangled states is a critical but challenging task in quantum information processing. Although generation of multipartite entanglement within a small set of individual qubits has been demonstrated, further scale-up in system size requires the connection of smaller entangled states into a larger state in a scalable and modular manner. Here we achieve this goal by implementing memory-enhanced fusion of two multipartite entangled states via photonic interconnects. Through asynchronous preparation of two tripartite W-state entanglements in two spatially-separated modules of atomic quantum memories and on-demand fusion via single-photon interference, we demonstrate the creation of a four-partite W-state entanglement shared by two remote quantum memory modules in a heralded way. We further transfer the W state from the memory qubits to the photonic qubits, and confirm the genuine four-partite entanglement through witness measurements. We then demonstrate memory-enhanced scaling in efficiencies in the entanglement fusion. The demonstrated scalable generation and fusion of multipartite entangled states pave the way towards realization of large-scale distributed quantum information processing in the future.

quant-ph↗

arXiv2025

Realizing Scalable Conditional Operations through Auxiliary Energy Levels

In the noisy intermediate-scale quantum (NISQ) era, flexible quantum operations are essential for advancing large-scale quantum computing, as they enable shorter circuits that mitigate decoherence and reduce gate errors. However, the complex control of quantum interactions poses significant experimental challenges that limit scalability. Here, we propose a transition composite gate scheme based on transition pathway engineering, which digitally implements conditional operations with reduced complexity by leveraging auxiliary energy levels. Experimentally, we demonstrate the controlled-unitary (CU) family and its applications. In entangled state preparation, our CU gate reduces the circuit depth for three-qubit Greenberger-Horne-Zeilinger (GHZ) and W states by approximately 40-44% compared to circuits using only CZ gates, leading to fidelity improvements of 1.5% and 4.2%, respectively. Furthermore, with a 72% reduction in circuit depth, we successfully implement a quantum comparator-a fundamental building block for quantum algorithms requiring conditional logic, which has remained experimentally challenging due to its inherent circuit complexity. These results demonstrate the scalability and practicality of our scheme, laying a solid foundation for the implementation of large-scale quantum algorithms in future quantum processors.

quant-ph↗