arXiv subjects

Yang Liu

Publications and source records attributed to Yang Liu.

At least 1,117 records · Page 62Linked to original sources

arXiv2025

Concept Guided Co-salient Object Detection

Co-salient object detection (Co-SOD) aims to identify common salient objects across a group of related images. While recent methods have made notable progress, they typically rely on low-level visual patterns and lack semantic priors, limiting their detection performance. We propose ConceptCoSOD, a concept-guided framework that introduces high-level semantic knowledge to enhance co-saliency detection. By extracting shared text-based concepts from the input image group, ConceptCoSOD provides semantic guidance that anchors the detection process. To further improve concept quality, we analyze the effect of diffusion timesteps and design a resampling strategy that selects more informative steps for learning robust concepts. This semantic prior, combined with the resampling-enhanced representation, enables accurate and consistent segmentation even in challenging visual conditions. Extensive experiments on three benchmark datasets and five corrupted settings demonstrate that ConceptCoSOD significantly outperforms existing methods in both accuracy and generalization.

cs.CV↗

arXiv2025

GraphAU-Pain: Graph-based Action Unit Representation for Pain Intensity Estimation

Understanding pain-related facial behaviors is essential for digital healthcare in terms of effective monitoring, assisted diagnostics, and treatment planning, particularly for patients unable to communicate verbally. Existing data-driven methods of detecting pain from facial expressions are limited due to interpretability and severity quantification. To this end, we propose GraphAU-Pain, leveraging a graph-based framework to model facial Action Units (AUs) and their interrelationships for pain intensity estimation. AUs are represented as graph nodes, with co-occurrence relationships as edges, enabling a more expressive depiction of pain-related facial behaviors. By utilizing a relational graph neural network, our framework offers improved interpretability and significant performance gains. Experiments conducted on the publicly available UNBC dataset demonstrate the effectiveness of the GraphAU-Pain, achieving an F1-score of 66.21% and accuracy of 87.61% in pain intensity estimation.

cs.LG↗

arXiv2025

Robust Multi-bit Text Watermark with LLM-based Paraphrasers

We propose an imperceptible multi-bit text watermark embedded by paraphrasing with LLMs. We fine-tune a pair of LLM paraphrasers that are designed to behave differently so that their paraphrasing difference reflected in the text semantics can be identified by a trained decoder. To embed our multi-bit watermark, we use two paraphrasers alternatively to encode the pre-defined binary code at the sentence level. Then we use a text classifier as the decoder to decode each bit of the watermark. Through extensive experiments, we show that our watermarks can achieve over 99.99\% detection AUC with small (1.1B) text paraphrasers while keeping the semantic information of the original sentence. More importantly, our pipeline is robust under word substitution and sentence paraphrasing perturbations and generalizes well to out-of-distributional data. We also show the stealthiness of our watermark with LLM-based evaluation. We open-source the code: https://github.com/xiaojunxu/multi-bit-text-watermark.

cs.AI↗

arXiv2025

xbench: Tracking Agents Productivity Scaling with Profession-Aligned Real-World Evaluations

We introduce xbench, a dynamic, profession-aligned evaluation suite designed to bridge the gap between AI agent capabilities and real-world productivity. While existing benchmarks often focus on isolated technical skills, they may not accurately reflect the economic value agents deliver in professional settings. To address this, xbench targets commercially significant domains with evaluation tasks defined by industry professionals. Our framework creates metrics that strongly correlate with productivity value, enables prediction of Technology-Market Fit (TMF), and facilitates tracking of product capabilities over time. As our initial implementations, we present two benchmarks: Recruitment and Marketing. For Recruitment, we collect 50 tasks from real-world headhunting business scenarios to evaluate agents' abilities in company mapping, information retrieval, and talent sourcing. For Marketing, we assess agents' ability to match influencers with advertiser needs, evaluating their performance across 50 advertiser requirements using a curated pool of 836 candidate influencers. We present initial evaluation results for leading contemporary agents, establishing a baseline for these professional domains. Our continuously updated evalsets and evaluations are available at https://xbench.org.

cs.LG↗

arXiv2025

BLITZSCALE: Fast and Live Large Model Autoscaling with O(1) Host Caching

Model autoscaling is the key mechanism to achieve serverless model-as-a-service, but it faces a fundamental trade-off between scaling speed and storage/memory usage to cache parameters, and cannot meet frequent scaling requirements across multiple hosts. The key problem is that data plane performance is slow, and scaled instances remain stopped while parameters are loading. In this paper, we first show that the data plane can be made fast with no or O(1) caching by loading parameters through the compute network between GPUs because: (1) its speed is comparable to host cache and is underutilized, and (2) scaling multiple instances requires no or O(1) caching with network-optimized multicast. Second, autoscaling can be made live by breaking the scaling abstraction for inference from a coarse-grained instance-level to a fine-grained layer-level. This allows us to offload the layer computation from the overloaded serving instances to the scaled ones without waiting for the parameters to be fully loaded. Under real-world workloads, our system BLITZSCALE achieves up to 94 % lower tail latency reductions compared to state-of-the-art autoscaling system (ServerlessLLM), and it reduces the GPU time used for serving by 49 % when compared with serving systems that do not support autoscaling like DistServe and vLLM with the same service-level-agreement.

cs.DC↗

arXiv2025

SWAG: Long-term Surgical Workflow Prediction with Generative-based Anticipation

While existing approaches excel at recognising current surgical phases, they provide limited foresight and intraoperative guidance into future procedural steps. Similarly, current anticipation methods are constrained to predicting short-term and single events, neglecting the dense, repetitive, and long sequential nature of surgical workflows. To address these needs and limitations, we propose SWAG (Surgical Workflow Anticipative Generation), a framework that combines phase recognition and anticipation using a generative approach. This paper investigates two distinct decoding methods - single-pass (SP) and auto-regressive (AR) - to generate sequences of future surgical phases at minute intervals over long horizons. We propose a novel embedding approach using class transition probabilities to enhance the accuracy of phase anticipation. Additionally, we propose a generative framework using remaining time regression to classification (R2C). SWAG was evaluated on two publicly available datasets, Cholec80 and AutoLaparo21. Our single-pass model with class transition probability embeddings (SP*) achieves 32.1% and 41.3% F1 scores over 20 and 30 minutes on Cholec80 and AutoLaparo21, respectively. Moreover, our approach competes with existing methods on phase remaining time regression, achieving weighted mean absolute errors of 0.32 and 0.48 minutes for 2- and 3-minute horizons. SWAG demonstrates versatility across generative decoding frame works and classification and regression tasks to create temporal continuity between surgical workflow recognition and anticipation. Our method provides steps towards intraoperative surgical workflow generation for anticipation. Project: https://maxboels.com/research/swag.

cs.CV↗

arXiv2025

Graph Positional Autoencoders as Self-supervised Learners

Graph self-supervised learning seeks to learn effective graph representations without relying on labeled data. Among various approaches, graph autoencoders (GAEs) have gained significant attention for their efficiency and scalability. Typically, GAEs take incomplete graphs as input and predict missing elements, such as masked nodes or edges. While effective, our experimental investigation reveals that traditional node or edge masking paradigms primarily capture low-frequency signals in the graph and fail to learn the expressive structural information. To address these issues, we propose Graph Positional Autoencoders (GraphPAE), which employs a dual-path architecture to reconstruct both node features and positions. Specifically, the feature path uses positional encoding to enhance the message-passing processing, improving GAE's ability to predict the corrupted information. The position path, on the other hand, leverages node representations to refine positions and approximate eigenvectors, thereby enabling the encoder to learn diverse frequency information. We conduct extensive experiments to verify the effectiveness of GraphPAE, including heterophilic node classification, graph property prediction, and transfer learning. The results demonstrate that GraphPAE achieves state-of-the-art performance and consistently outperforms baselines by a large margin.

cs.LG↗

arXiv2025

Fine-tuning problems in type IIA string theory

We demonstrate a unified resolution to the strong CP, hierarchy, and cosmological constant problems in type IIA flux compactifications, via 4-form fluxes and KL stabilization. We show that the strong CP problem can be effectively "solved" in type IIA orientifold constructions, particularly in the type IIA $T^6/(\mathbb{Z}_2 \times \mathbb{Z}_2)$ model. Building on this, we explore whether the remaining two fine-tuning problems can also be resolved within the same setup. To obtain a small cosmological constant, we adopt the KL scenario and find that, in order to avoid conflicts with the swampland distance conjecture and to eliminate the need for fine-tuning, the perturbative superpotential $ΔW$ must take the form $f_0 U^3$. Additionally, we compute the gravitino mass. This allows for a resolution of the hierarchy problem without introducing fine-tuning if gravitino mass lies below 100 TeV. Taken together, these results suggest that the type IIA $T^6/(\mathbb{Z}_2 \times \mathbb{Z}_2)$ orientifold model provides a promising framework in which all three fine-tuning problems may be addressed simultaneously.

hep-th↗

arXiv2025

The Trip to ZigBee Backscatter across a Decade, a Systematic Review

The field of backscatter communication has undergone a profound transformation, evolving from a niche technology for radio-frequency identification (RFID) into a sophisticated paradigm poised to enable a truly battery-free Internet of Things (IoT). This evolution is built upon a deepening understanding of the fundamental principles governing these ultra-low-power links. Modern backscatter systems are no longer simple reflectors of continuous waves but are increasingly designed to interact with complex, data-carrying ambient signals from ubiquitous sources like WiFi, ZigBee, and cellular networks. This review systematically charts the journey of ambient backscatter, particularly focusing on its interaction with ZigBee and other commodity wireless protocols over the last decade. We analyze the progression from foundational proof-of-concept systems that established productive backscatter to modern high-throughput, concurrent, and cross-technology communication architectures. Key advancements in fine-grained modulation, robust synchronization, cross-technology physical layer emulation, and multi-tag coordination are detailed. A comparative analysis of state-of-the-art systems highlights the core trade-offs between performance metrics like data rate and range, power consumption, and compatibility with commodity hardware. Finally, we synthesize the primary challenges, including networking scalability, security vulnerabilities, the near-far problem, and practical deployment hurdles, and outline future research directions, such as integration with Reconfigurable Intelligent Surfaces (RIS) and 6G networks, that promise to further expand the capabilities of this transformative technology.

cs.NI↗

arXiv2025

Balancing Preservation and Modification: A Region and Semantic Aware Metric for Instruction-Based Image Editing

Instruction-based image editing, which aims to modify the image faithfully according to the instruction while preserving irrelevant content unchanged, has made significant progress. However, there still lacks a comprehensive metric for assessing the editing quality. Existing metrics either require high human evaluation costs, which hinder large-scale evaluation, or are adapted from other tasks and lose task-specific concerns, failing to comprehensively evaluate both instruction-based modification and preservation of irrelevant regions, resulting in biased evaluation. To tackle this, we introduce a new metric called Balancing Preservation and Modification (BPM), tailored for instruction-based image editing by explicitly disentangling the image into editing-relevant and irrelevant regions for specific consideration. We first identify and locate editing-relevant regions, followed by a two-tier process to assess editing quality: Region-Aware Judge evaluates whether the position and size of the edited region align with the instruction, and Semantic-Aware Judge further assesses the instruction content compliance within editing-relevant regions as well as content preservation within irrelevant regions, yielding comprehensive and interpretable quality assessment. Moreover, the editing-relevant region localization in BPM can be integrated into image editing approaches to improve editing quality, demonstrating its broad applicability. We verify the effectiveness of the BPM metric on comprehensive instruction-editing data, and the results show the highest alignment with human evaluation compared to existing metrics, indicating its efficacy. Code is available at: https://joyli-x.github.io/BPM/

cs.GR↗

arXiv2025

Causality-aware Safety Testing for Autonomous Driving Systems

Simulation-based testing is essential for evaluating the safety of Autonomous Driving Systems (ADSs). Comprehensive evaluation requires testing across diverse scenarios that can trigger various types of violations under different conditions. While existing methods typically focus on individual diversity metrics, such as input scenarios, ADS-generated motion commands, and system violations, they often fail to capture the complex interrelationships among these elements. This oversight leads to gaps in testing coverage, potentially missing critical issues in the ADS under evaluation. However, quantifying these interrelationships presents a significant challenge. In this paper, we propose a novel causality-aware fuzzing technique, Causal-Fuzzer, to enable efficient and comprehensive testing of ADSs by exploring causally diverse scenarios. The core of Causal-Fuzzer is constructing a causal graph to model the interrelationships among the diversities of input scenarios, ADS motion commands, and system violations. Then the causal graph will guide the process of critical scenario generation. Specifically, Causal-Fuzzer proposes (1) a causality-based feedback mechanism that quantifies the combined diversity of test scenarios by assessing whether they activate new causal relationships, and (2) a causality-driven mutation strategy that prioritizes mutations on input scenario elements with higher causal impact on ego action changes and violation occurrence, rather than treating all elements equally. We evaluated Causal-Fuzzer on an industry-grade ADS Apollo, with a high-fidelity. Our empirical results demonstrate that Causal-Fuzzer significantly outperforms existing methods in (1) identifying a greater diversity of violations, (2) providing enhanced testing sufficiency with improved coverage of causal relationships, and (3) achieving greater efficiency in detecting the first critical scenarios.

cs.SE↗

arXiv2025

Silicon Nitride Microresonator Raman Lasers

Silicon nitride (SiN) has emerged as a promising platform for integrated nonlinear photonics because of its low propagation loss, wide transparency window, and CMOS compatibility. Nonlinear processes arising from photon-electron interactions, such as Kerr frequency comb generation and second harmonic generation, have been extensively explored. In contrast, photon-phonon interaction-based nonlinearities, such as stimulated Raman scattering, remain largely unexplored in this integrated platform, despite their potential for broadband frequency conversion. Here, we demonstrate efficient Raman lasing in ultra-high-Q SiN microresonators by harnessing the strong intracavity field enhancement and engineering the optical mode to overlap with the Raman-active silica cladding. Through dispersion engineering and waveguide geometry optimization, we suppress competing Kerr nonlinearities while enhancing Raman gain, achieving lasing with sub-2 mW thresholds. We further investigate the trade-off between optical confinement and quality factor, revealing its impact on the overall nonlinear efficiency. Moreover, we also demonstrate broadband tunability of the Raman shift exceeding 120 inverse centimeters, enabled by the wide Raman gain spectrum of silica, offering new flexibility in designing integrated tunable Raman lasers. These results position SiN as a viable platform for chip-scale Raman lasers, expanding the nonlinear optics toolbox of the SiN platform and enabling compact, power-efficient light sources for applications in spectroscopy, optical communications, and quantum photonics.

physics.optics↗

arXiv2025

A Survey of Earable Technology: Trends, Tools, and the Road Ahead

Earable devices, wearables positioned in or around the ear, are undergoing a rapid transformation from audio-centric accessories into multifunctional systems for interaction, contextual awareness, and health monitoring. This evolution is driven by commercial trends emphasizing sensor integration and by a surge of academic interest exploring novel sensing capabilities. Building on the foundation established by earlier surveys, this work presents a timely and comprehensive review of earable research published since 2022. We analyze over one hundred recent studies to characterize this shifting research landscape, identify emerging applications and sensing modalities, and assess progress relative to prior efforts. In doing so, we address three core questions: how has earable research evolved in recent years, what enabling resources are now available, and what opportunities remain for future exploration. Through this survey, we aim to provide both a retrospective and forward-looking view of earable technology as a rapidly expanding frontier in ubiquitous computing. In particular, this review reveals that over the past three years, researchers have discovered a variety of novel sensing principles, developed many new earable sensing applications, enhanced the accuracy of existing sensing tasks, and created substantial new resources to advance research in the field. Based on this, we further discuss open challenges and propose future directions for the next phase of earable research.

cs.HC↗

arXiv2025

Simulation of dark photon sensitivity in $η\rightarrow γe^+e^-$ at HIAF

We present a simulation study of dark photon sensitivity in a suggested $η$ factory experiment at Huizhou. The vast number of $η$ mesons are produced by bombarding the high-intensity HIAF proton beam on a multi-layer target of light nucleus. The kinematic energy of the beam is at 1.8 GeV. For a prior experiment of one-month running, about $5.9 \times 10^{11}$ $η$ samples would be collected, providing substantial data for a sound statistical analysis. A compact spectrometer based on the full silicon-pixel tracker is conceptually designed for the detection of the final-state particles. The GiBUU event generator is utilized for the background estimation without the dark photon signal. A spectrometer simulation package ChnsRoot is constructed for evaluating the spectrometer performances in searching the dark photon in $η$ rare decay. The efficiency and resolutions of $η\rightarrow γe^+e^-$ decay channel are studied in detail. The branching-ratio upper limit of dark photon in $η\rightarrow γe^+e^-$ decay and the sensitivity to the model parameter are given from the simulations.

hep-ex↗

arXiv2025

Room temperature quantum metric effect in TbMn6Sn6

Quantum geometry, including Berry curvature and the quantum metric, of the electronic Bloch bands has been studied via nonlinear responses in topological materials. Naturally, these material systems with intrinsic strong nonlinear responses also form the key component in nonlinear electronic devices. However, the previous reported quantum geometry effects are mainly observed at cryogenic temperatures, hindering their application in practical devices. Here we report the tuneable strong room-temperature second-harmonic transport response in a quantum magnet, TbMn6Sn6, which is governed by the quantum metric and can be tuned with applied magnetic fields. We show that around room temperature, which is close to the spontaneous spin-reorientation transition, the magnetic configurations, and therefore the related symmetry breaking phases, are easily controlled via magnetic fields. Our results also show that manipulation of the symmetries of the magnetic structure presents an effective route to tuneable quantum-geometry-based devices.

cond-mat.mtrl-sci↗

arXiv2025

LIFEBench: Evaluating Length Instruction Following in Large Language Models

While large language models (LLMs) can solve PhD-level reasoning problems over long context inputs, they still struggle with a seemingly simpler task: following explicit length instructions-e.g., write a 10,000-word novel. Additionally, models often generate far too short outputs, terminate prematurely, or even refuse the request. Existing benchmarks focus primarily on evaluating generations quality, but often overlook whether the generations meet length constraints. To this end, we introduce Length Instruction Following Evaluation Benchmark (LIFEBench) to comprehensively evaluate LLMs' ability to follow length instructions across diverse tasks and a wide range of specified lengths. LIFEBench consists of 10,800 instances across 4 task categories in both English and Chinese, covering length constraints ranging from 16 to 8192 words. We evaluate 26 widely-used LLMs and find that most models reasonably follow short-length instructions but deteriorate sharply beyond a certain threshold. Surprisingly, almost all models fail to reach the vendor-claimed maximum output lengths in practice, as further confirmed by our evaluations extending up to 32K words. Even long-context LLMs, despite their extended input-output windows, counterintuitively fail to improve length-instructions following. Notably, Reasoning LLMs outperform even specialized long-text generation models, achieving state-of-the-art length following. Overall, LIFEBench uncovers fundamental limitations in current LLMs' length instructions following ability, offering critical insights for future progress.

cs.CL↗

arXiv2025

DCIRNet: Depth Completion with Iterative Refinement for Dexterous Grasping of Transparent and Reflective Objects

Transparent and reflective objects in everyday environments pose significant challenges for depth sensors due to their unique visual properties, such as specular reflections and light transmission. These characteristics often lead to incomplete or inaccurate depth estimation, which severely impacts downstream geometry-based vision tasks, including object recognition, scene reconstruction, and robotic manipulation. To address the issue of missing depth information in transparent and reflective objects, we propose DCIRNet, a novel multimodal depth completion network that effectively integrates RGB images and depth maps to enhance depth estimation quality. Our approach incorporates an innovative multimodal feature fusion module designed to extract complementary information between RGB images and incomplete depth maps. Furthermore, we introduce a multi-stage supervision and depth refinement strategy that progressively improves depth completion and effectively mitigates the issue of blurred object boundaries. We integrate our depth completion model into dexterous grasping frameworks and achieve a $44\%$ improvement in the grasp success rate for transparent and reflective objects. We conduct extensive experiments on public datasets, where DCIRNet demonstrates superior performance. The experimental results validate the effectiveness of our approach and confirm its strong generalization capability across various transparent and reflective objects.

cs.RO↗

arXiv2025

Thermal Management Design and Key Technology Validation for PandaX Underground Experiment

The scale of liquid xenon experiments for rare events searching is expanding, which is planned even to fifty tons level. The detector and distillation tower require a reliable cooling source with large cooling power at liquid xenon temperature range. Pulse tube refrigerators and GM refrigerators, which were widely used in previous detectors, have the disadvantages of small cooling power, large space occupation, and non-standby mutuality, which become bottlenecks of the experiment scale expansion. In this study, an auto-cascade refrigerator with ethanol coolant is developed, and the heat transfer effect is improved by adopting the concentric shaft heat exchanger and after-pumping heat transfer scheme. The 2.5 kW stable cooling power is obtained at 155 K. Further, the feasibility and key technology of the centralized cooling system of 5 kw at 160 K is discussed. The study can simplify liquid xenon experimental auxiliary devices, which will be helpful for the PandaX-xT experiment scheme and its laboratory infrastructure design.

physics.ins-det↗