arXiv subjects

Shuo Sun

Publications and source records attributed to Shuo Sun.

At least 37 records · Page 2Linked to original sources

arXiv2026

Where can AI be used? Insights from a deep ontology of work activities

Artificial intelligence (AI) is poised to profoundly reshape how work is executed and organized, but we do not yet have deep frameworks for understanding where AI can be used. Here we provide a comprehensive ontology of work activities that can help systematically analyze and predict uses of AI. To do this, we disaggregate and then substantially reorganize the approximately 20K activities in the US Department of Labor's widely used O*NET occupational database. Next, we use this framework to classify descriptions of 13,275 AI software applications and a worldwide tally of 20.8 million robotic systems. Finally, we use the data about both these kinds of AI to generate graphical displays of how the estimated units and market values of all worldwide AI systems used today are distributed across the work activities that these systems help perform. We find a highly uneven distribution of AI market value across activities, with the top 1.6% of activities accounting for over 60% of AI market value. Most of the market value is used in information-based activities (72%), especially creating information (36%), and only 12% is used in physical activities. Interactive activities include both information-based and physical activities and account for 48% of AI market value, much of which (26%) involves transferring information. These results can be viewed as rough predictions of the AI applicability for all the different work activities down to very low levels of detail. Thus, we believe this systematic framework can help predict at a detailed level where today's AI systems can and cannot be used and how future AI capabilities may change this.

cs.AI↗

arXiv2026

Testing general relativity with binary black holes: a study on the sensitivity requirements for future space-based detectors

We study the sensitivity required for a future space-based detector to search for beyond general relativity effect in gravitational wave detection. To do this, we use the current design of TianQin, LISA, and $μ$Ares as starting points, and study how their key noise parameters should be improved to adequately detect some target signals, for which we choose a nonlinear ringdown mode, displacement memory, and a putative beyond general relativity signal, all from the merger of massive black hole binaries. We find that the required improvements are strongly dependent on the choice of the target signals and the population model of massive black hole binaries, and $4-9$ orders of magnitude improvement will be needed in the most demanding detection scenarios.

gr-qc↗

arXiv2026

Efficient Application of Tensor Network Operators to Tensor Network States

The performance of tensor network methods has seen constant improvements over the last few years. We add to this effort by introducing a new algorithm that efficiently applies tree tensor network operators to tree tensor network states inspired by the density matrix method and the Cholesky decomposition. This application procedure is a common subroutine in tensor network methods. We explicitly include the special case of tensor train structures and demonstrate how to extend methods commonly used in this context to general tree structures. We compare our newly developed method with the existing ones in a benchmark scenario with random tensor network states and operators. We find our Cholesky-based compression (CBC) performs equivalently to the current state-of-the-art method, while outperforming most established methods by at least an order of magnitude in runtime. We then apply our knowledge to perform circuit simulation of tree-like circuits, in order to test our method in a more realistic scenario. Here, we find that more complex tree structures can outperform simple linear structures and achieve lower errors than those possible with the simple structures. Additionally, our CBC still performs among the most successful methods, showing less dependence on the different bond dimensions of the operator.

quant-ph↗

arXiv2026

Generalization of RLVR Using Causal Reasoning as a Testbed

Reinforcement learning with verifiable rewards (RLVR) has emerged as a promising paradigm for post-training large language models (LLMs) on complex reasoning tasks. Yet, the conditions under which RLVR yields robust generalization remain underexplored. This paper provides an empirical study of RLVR generalization in the setting of probabilistic inference over causal graphical models. This setting offers two natural axes along which to examine generalization: (i) the level of the probabilistic query -- associational, interventional, or counterfactual -- and (ii) the structural complexity of the query, measured by the size of its relevant subgraph. We construct a dataset of causal graphs and queries spanning these difficulty axes and fine-tune Qwen-2.5-Instruct models using RLVR or supervised fine-tuning (SFT). We vary both the model scale (3B-32B) and the query level included in training. We find that RLVR yields stronger within-level and across-level generalization than SFT, but only for specific combinations of model size and training query level. Further analysis shows that RLVR's effectiveness depends on the model's initial reasoning competence. With sufficient initial competence, RLVR improves an LLM's marginalization strategy and reduces errors in intermediate probability calculations, producing substantial accuracy gains, particularly on more complex queries. These results show that RLVR can improve specific causal reasoning subskills, with its benefits emerging only when the model has sufficient initial competence. Our code and data is available at https://github.com/zhichul/rlcausal.

cs.LG↗

arXiv2026

Unlocking Cognitive Capabilities and Analyzing the Perception-Logic Trade-off

Recent advancements in Multimodal Large Language Models (MLLMs) pursue omni-perception capabilities, yet integrating robust sensory grounding with complex reasoning remains a challenge, particularly for underrepresented regions. In this report, we introduce the research preview of MERaLiON2-Omni (Alpha), a 10B-parameter multilingual omni-perception tailored for Southeast Asia (SEA). We present a progressive training pipeline that explicitly decouples and then integrates "System 1" (Perception) and "System 2" (Reasoning) capabilities. First, we establish a robust Perception Backbone by aligning region-specific audio-visual cues (e.g., Singlish code-switching, local cultural landmarks) with a multilingual LLM through orthogonal modality adaptation. Second, to inject cognitive capabilities without large-scale supervision, we propose a cost-effective Generate-Judge-Refine pipeline. By utilizing a Super-LLM to filter hallucinations and resolve conflicts via a consensus mechanism, we synthesize high-quality silver data that transfers textual Chain-of-Thought reasoning to multimodal scenarios. Comprehensive evaluation on our newly introduced SEA-Omni Benchmark Suite reveals an Efficiency-Stability Paradox: while reasoning acts as a non-linear amplifier for abstract tasks (boosting mathematical and instruction-following performance significantly), it introduces instability in low-level sensory processing. Specifically, we identify Temporal Drift in long-context audio, where extended reasoning desynchronizes the model from acoustic timestamps, and Visual Over-interpretation, where logic overrides pixel-level reality. This report details the architecture, the data-efficient training recipe, and a diagnostic analysis of the trade-offs between robust perception and structured reasoning.

cs.AI↗

arXiv2026

Improving Generalizability of Hip Fracture Risk Prediction via Domain Adaptation Across Multiple Cohorts

Clinical risk prediction models often fail to be generalized across cohorts because underlying data distributions differ by clinical site, region, demographics, and measurement protocols. This limitation is particularly pronounced in hip fracture risk prediction, where the performance of models trained on one cohort (the source cohort) can degrade substantially when deployed in other cohorts (target cohorts). We used a shared set of clinical and DXA-derived features across three large cohorts - the Study of Osteoporotic Fractures (SOF), the Osteoporotic Fractures in Men Study (MrOS), and the UK Biobank (UKB), to systematically evaluate the performance of three domain adaptation methods - Maximum Mean Discrepancy (MMD), Correlation Alignment (CORAL), and Domain - Adversarial Neural Networks (DANN) and their combinations. For a source cohort with males only and a source cohort with females only, domain-adaptation methods consistently showed improved performance than the no-adaptation baseline (source-only training), and the use of combinations of multiple domain adaptation methods delivered the largest and most stable gains. The method that combines MMD, CORAL, and DANN achieved the highest discrimination with the area under curve (AUC) of 0.88 for a source cohort with males only and 0.95 for a source cohort with females only), demonstrating that integrating multiple domain adaptation methods could produce feature representations that are less sensitive to dataset differences. Unlike existing methods that rely heavily on supervised tuning or assume known outcomes of samples in target cohorts, our outcome-free approaches enable the model selection under realistic deployment conditions and improve generalization of models in hip fracture risk prediction.

cs.LG↗

arXiv2026

IMPACT: Behavioral Intention-aware Multimodal Trajectory Prediction with Adaptive Context Trimming

While most prior research has focused on improving the precision of multimodal trajectory predictions, the explicit modeling of multimodal behavioral intentions (e.g., yielding, overtaking) remains relatively underexplored. This paper proposes a unified framework that jointly predicts both behavioral intentions and trajectories to enhance prediction accuracy, interpretability, and efficiency. Specifically, we employ a shared context encoder for both intention and trajectory predictions, thereby reducing structural redundancy and information loss. Moreover, we address the lack of ground-truth behavioral intention labels in mainstream datasets (Waymo, Argoverse) by auto-labeling these datasets, thus advancing the community's efforts in this direction. We further introduce a vectorized occupancy prediction module that infers the probability of each map polyline being occupied by the target vehicle's future trajectory. By leveraging these intention and occupancy prediction priors, our method conducts dynamic, modality-dependent pruning of irrelevant agents and map polylines in the decoding stage, effectively reducing computational overhead and mitigating noise from non-critical elements. Our approach ranks first among LiDAR-free methods on the Waymo Motion Dataset and achieves first place on the Waymo Interactive Prediction Dataset. Remarkably, even without model ensembling, our single-model framework improves the soft mean average precision (softmAP) by 10 percent compared to the second-best method in the Waymo Interactive Prediction Leaderboard. Furthermore, the proposed framework has been successfully deployed on real vehicles, demonstrating its practical effectiveness in real-world applications.

cs.RO↗

arXiv2026

Knowledge Distillation Driven Semantic NOMA for Image Transmission with Diffusion Model

As a promising 6G enabler beyond conventional bit-level transmission, semantic communication can considerably reduce required bandwidth resources, while its combination with multiple access requires further exploration. This paper proposes a knowledge distillation-driven and diffusion-enhanced (KDD) semantic non-orthogonal multiple access (NOMA), named KDD-SemNOMA, for multi-user uplink wireless image transmission. Specifically, to ensure robust feature transmission across diverse transmission conditions, we firstly develop a ConvNeXt-based deep joint source and channel coding architecture with enhanced adaptive feature module. This module incorporates signal-to-noise ratio and channel state information to dynamically adapt to additive white Gaussian noise and Rayleigh fading channels. Furthermore, to improve image restoration quality without inference overhead, we introduce a two-stage knowledge distillation strategy, i.e., a teacher model, trained on interference-free orthogonal transmission, guides a student model via feature affinity distillation and cross-head prediction distillation. Moreover, a diffusion model-based refinement stage leverages generative priors to transform initial SemNOMA outputs into high-fidelity images with enhanced perceptual quality. Extensive experiments on CIFAR-10 and FFHQ-256 datasets demonstrate superior performance over state-of-the-art methods, delivering satisfactory reconstruction performance even at extremely poor channel conditions. These results highlight the advantages in both pixel-level accuracy and perceptual metrics, effectively mitigating interference and enabling high-quality image recovery.

cs.IT↗

arXiv2026

Self-Aligned Heterogeneous Quantum Photonic Integration

Integrated quantum photonics holds significant promise for scalable photonic quantum information processing, quantum repeaters, and quantum networks, but its development is hindered by the mismatch between materials hosting high-quality quantum emitters and those compatible with mature photonic technologies. Heterogeneous integration offers a potential solution to this challenge, yet practical implementations have been limited by inevitable insertion losses at material interfaces. Here, we present a self-aligned heterogeneous quantum photonic integration approach that can deterministically achieve near-unity coupling efficiency at the interface. To showcase our approach, we demonstrate Purcell enhancement of a silicon vacancy (SiV) center in diamond induced by a heterogeneous photonic crystal cavity defined by titanium dioxide (TiO2), as well as optical spin control and readout via a TiO2 photonic circuit. We further show that, when combined with inverse photonic design, our approach enables efficient and broadband collection of single photons from a color center into a heterogeneous waveguide. Our approach is not restricted to SiV centers or TiO2; it can be broadly applied to integrate diverse solid-state quantum emitters with thin-film photonic devices where conformal deposition is possible. Together, these results establish a practical route to scalable quantum photonic integrated circuits that combine high-quality quantum emitters with technologically mature photonic platforms.

physics.optics↗

arXiv2026

Single-Atom Tuning of Structural and Optoelectronic Properties in Halogenated Anthracene-Based Covalent Organic Frameworks

Strategies for tuning structural and (opto-)electronic properties are fundamental to the rational design of functional materials. Here, we present a molecular design approach for precisely modulating the optoelectronic properties of covalent organic frameworks (COFs) through single-atom halogen substitution on $π$-extended anthracene linkers. Using a Wurster-type tetratopic amine (W-NH$_2$) and a series of anthracene-based dialdehydes bearing H, Cl, Br, or I at the 2-position, a family of imine-linked COFs, W-A-X (X = H, Cl, Br, I), was synthesized, all displaying well-ordered porous structures. The halogen substituent strongly influences framework formation, with brominated COFs forming substantially larger crystalline domains than their chloro- and iodo-functionalized analogues. UV-vis absorption and photoluminescence measurements reveal a systematic redshift across the series $(\mathrm{H < Cl < Br < I})$, demonstrating that a single-atom modification effectively tunes the optical response. Time-dependent density functional theory calculations on both isolated fragments and extended COF models attribute these trends to halogen-induced changes in the COF band structure and provide a mechanistic understanding of how single-atom substitution influences the optoelectronic properties of the extended $π$-framework. Overall, this study establishes single-atom halogen substitution as a powerful and modular strategy for tailoring the structural and optical properties of anthracene-based COFs.

cond-mat.mtrl-sci↗

arXiv2026

Contact resistance and interfacial engineering: Advances in high-performance 2D-TMD based devices

The development of advanced electronic devices is contingent upon sustainable material development and pioneering research breakthroughs. Traditional semiconductor-based electronic technology faces constraints in material thickness scaling and energy efficiency. Atomically thin two-dimensional (2D) transition metal dichalcogenides (TMDs) have emerged as promising candidates for next-generation nanoelectronics and optoelectronic applications, boasting high electron mobility, mechanical strength, and a customizable band gap. Despite these merits, the Fermi level pinning effect introduces uncontrollable Schottky barriers at metal-2D-TMD contacts, challenging prediction through the Schottky-Mott rule. These barriers fundamentally lead to elevated contact resistance and limited current-delivery capability, impeding the enhancement of 2D-TMD transistor and integrated circuit properties. In this review, we succinctly outline the Fermi pinning effect mechanism and peculiar contact resistance behavior at metal/2D-TMD interfaces. Subsequently, highlights on the recent advances in overcoming contact resistance in 2D-TMDs devices, encompassing interface interaction and hybridization, van der Waals (vdW) contacts, prefabricated metal transfer and charge-transfer doping will be addressed. Finally, the discussion extends to challenges and offers insights into future developmental prospects.

cond-mat.mtrl-sci↗

arXiv2025

FineFT: Efficient and Risk-Aware Ensemble Reinforcement Learning for Futures Trading

Futures are contracts obligating the exchange of an asset at a predetermined date and price, notable for their high leverage and liquidity and, therefore, thrive in the Crypto market. RL has been widely applied in various quantitative tasks. However, most methods focus on the spot and could not be directly applied to the futures market with high leverage because of 2 challenges. First, high leverage amplifies reward fluctuations, making training stochastic and difficult to converge. Second, prior works lacked self-awareness of capability boundaries, exposing them to the risk of significant loss when encountering new market state (e.g.,a black swan event like COVID-19). To tackle these challenges, we propose the Efficient and Risk-Aware Ensemble Reinforcement Learning for Futures Trading (FineFT), a novel three-stage ensemble RL framework with stable training and proper risk management. In stage I, ensemble Q learners are selectively updated by ensemble TD errors to improve convergence. In stage II, we filter the Q-learners based on their profitabilities and train VAEs on market states to identify the capability boundaries of the learners. In stage III, we choose from the filtered ensemble and a conservative policy, guided by trained VAEs, to maintain profitability and mitigate risk with new market states. Through extensive experiments on crypto futures in a high-frequency trading environment with high fidelity and 5x leverage, we demonstrate that FineFT outperforms 12 SOTA baselines in 6 financial metrics, reducing risk by more than 40% while achieving superior profitability compared to the runner-up. Visualization of the selective update mechanism shows that different agents specialize in distinct market dynamics, and ablation studies certify routing with VAEs reduces maximum drawdown effectively, and selective update improves convergence and performance.

cs.LG↗

arXiv2025

Co-Evolution of Types and Dependencies: Towards Repository-Level Type Inference for Python Code

Python's dynamic typing mechanism, while promoting flexibility, is a significant source of runtime type errors that plague large-scale software, which inspires the automatic type inference techniques. Existing type inference tools have achieved advances in type inference within isolated code snippets. However, repository-level type inference remains a significant challenge, primarily due to the complex inter-procedural dependencies that are difficult to model and resolve. To fill this gap, we present \methodName, a novel approach based on LLMs that achieves repository-level type inference through the co-evolution of types and dependencies. \methodName~constructs an Entity Dependency Graph (EDG) to model the objects and type dependencies across the repository. During the inference process, it iteratively refines types and dependencies in EDG for accurate type inference. Our key innovations are: (1) an EDG model designed to capture repository-level type dependencies; (2) an iterative type inference approach where types and dependencies co-evolve in each iteration; and (3) a type-checker-in-the-loop strategy that validates and corrects inferences on-the-fly, thereby reducing error propagation. When evaluated on 12 complex Python repositories, \methodName~significantly outperformed prior works, achieving a \textit{TypeSim} score of 0.89 and a \textit{TypeExact} score of 0.84, representing a 27\% and 40\% relative improvement over the strongest baseline. More importantly, \methodName~removed new type errors introduced by the tool by 92.7\%. This demonstrates a significant leap towards automated, reliable type annotation for real-world Python development.

cs.SE↗

arXiv2025

Interfacial Polarons Driven by Charge Transfer In WSe2/Cuprate Superconductor Systems

Understanding the electronic properties of doped copper-oxygen planes remains a significant challenge in condensed matter physics and is crucial to unraveling the mechanisms behind high-temperature superconductivity in cuprates. Recently, the observation of charge transfer and interfacial polarons in superconducting interface has aroused extensive research interest. However, experimental data to investigate charge transfer on the CuO2 plane and the presence of polarons are still missing. Here we conduct extensive research on the optical and electronic properties of two-dimensional material supported on copper-based superconductors. Unlike monolayer-WSe2 on other substrates, monolayer-WSe2 on La1.85Sr0.15CuO4 (WSe2/LSCO) produces a special band structure. Using high-resolution spectroscopic ellipsometry and density functional theory calculation methods, the special electronic structure can be attributed to the formation of the interfacial small polaron at the WSe2/LSCO interface which is driven by charge transfer between the CuO2 plane of the cuprate superconductor and WSe2. In addition, the structural phase transition of the LSCO substrate was observed to reduce the electron-hole (e-h) interaction of WSe2. These findings may spur future investigations on the effect of the interfacial polaron on the superconductivity of cuprates, and highlight the significant influence of interface effects on the electronic structure of WSe2 films. It provides an effective method to further explore the intrinsic relationship between interfacial polarons and superconductivity.

cond-mat.supr-con↗

arXiv2025

Group-Theoretic Reinforcement Learning of Dynamical Decoupling Sequences

Dynamical decoupling seeks to mitigate phase decoherence in qubits by applying a carefully designed sequence of effectively instantaneous electromagnetic pulses. Although analytic solutions exist for pulse timings that are optimal under specific noise regimes, identifying the optimal timings for a realistic noise spectrum remains challenging. We propose a reinforcement learning (RL)-based method for designing pulse sequences on qubits. Our novel action set enables the RL agent to efficiently navigate this inherently non-convex optimization landscape. The action set, derived from Thompson's group $F$, is applicable to a broad class of sequential decision problems whose states can be represented as bounded sequences. We demonstrate that our RL agent can learn pulse sequences that minimize dephasing without requiring explicit knowledge of the underlying noise spectrum. This work opens the possibility for real-time learning of optimal dynamical decoupling sequences on qubits which are dephasing-limited. The model-free nature of our algorithm suggests that the agent may ultimately learn optimal pulse sequences even in the presence of unmodeled physical effects, such as pulse errors or non-Gaussian noise.

quant-ph↗

arXiv2025

IFEval-Audio: Benchmarking Instruction-Following Capability in Audio-based Large Language Models

Large language models (LLMs) have demonstrated strong instruction-following capabilities in text-based tasks. However, this ability often deteriorates in multimodal models after alignment with non-text modalities such as images or audio. While several recent efforts have investigated instruction-following performance in text and vision-language models, instruction-following in audio-based large language models remains largely unexplored. To bridge this gap, we introduce IFEval-Audio, a novel evaluation dataset designed to assess the ability to follow instructions in an audio LLM. IFEval-Audio contains 280 audio-instruction-answer triples across six diverse dimensions: Content, Capitalization, Symbol, List Structure, Length, and Format. Each example pairs an audio input with a text instruction, requiring the model to generate an output that follows a specified structure. We benchmark state-of-the-art audio LLMs on their ability to follow audio-involved instructions. The dataset is released publicly to support future research in this emerging area.

cs.CL↗

arXiv2025

Protein Folding with Neural Ordinary Differential Equations

Recent advances in protein structure prediction, such as AlphaFold, have demonstrated the power of deep neural architectures like the Evoformer for capturing complex spatial and evolutionary constraints on protein conformation. However, the depth of the Evoformer, comprising 48 stacked blocks, introduces high computational costs and rigid layerwise discretization. Inspired by Neural Ordinary Differential Equations (Neural ODEs), we propose a continuous-depth formulation of the Evoformer, replacing its 48 discrete blocks with a Neural ODE parameterization that preserves its core attention-based operations. This continuous-time Evoformer achieves constant memory cost (in depth) via the adjoint method, while allowing a principled trade-off between runtime and accuracy through adaptive ODE solvers. Benchmarking on protein structure prediction tasks, we find that the Neural ODE-based Evoformer produces structurally plausible predictions and reliably captures certain secondary structure elements, such as alpha-helices, though it does not fully replicate the accuracy of the original architecture. However, our model achieves this performance using dramatically fewer resources, just 17.5 hours of training on a single GPU, highlighting the promise of continuous-depth models as a lightweight and interpretable alternative for biomolecular modeling. This work opens new directions for efficient and adaptive protein structure prediction frameworks.

cs.LG↗

arXiv2025

An Advanced Two-Stage Model with High Sensitivity and Generalizability for Prediction of Hip Fracture Risk Using Multiple Datasets

Hip fractures are a major cause of disability, mortality, and healthcare burden in older adults, underscoring the need for early risk assessment. However, commonly used tools such as the DXA T-score and FRAX often lack sensitivity and miss individuals at high risk, particularly those without prior fractures or with osteopenia. To address this limitation, we propose a sequential two-stage model that integrates clinical and imaging information to improve prediction accuracy. Using data from the Osteoporotic Fractures in Men Study (MrOS), the Study of Osteoporotic Fractures (SOF), and the UK Biobank, Stage 1 (Screening) employs clinical, demographic, and functional variables to estimate baseline risk, while Stage 2 (Imaging) incorporates DXA-derived features for refinement. The model was rigorously validated through internal and external testing, showing consistent performance and adaptability across cohorts. Compared to T-score and FRAX, the two-stage framework achieved higher sensitivity and reduced missed cases, offering a cost-effective and personalized approach for early hip fracture risk assessment. Keywords: Hip Fracture, Two-Stage Model, Risk Prediction, Sensitivity, DXA, FRAX

cs.LG↗