arXiv subjects

Feng Liu

Publications and source records attributed to Feng Liu.

At least 199 records · Page 11Linked to original sources

arXiv2025

SCP: Accelerating Discovery with a Global Web of Autonomous Scientific Agents

We introduce SCP: the Science Context Protocol, an open-source standard designed to accelerate discovery by enabling a global network of autonomous scientific agents. SCP is built on two foundational pillars: (1) Unified Resource Integration: At its core, SCP provides a universal specification for describing and invoking scientific resources, spanning software tools, models, datasets, and physical instruments. This protocol-level standardization enables AI agents and applications to discover, call, and compose capabilities seamlessly across disparate platforms and institutional boundaries. (2) Orchestrated Experiment Lifecycle Management: SCP complements the protocol with a secure service architecture, which comprises a centralized SCP Hub and federated SCP Servers. This architecture manages the complete experiment lifecycle (registration, planning, execution, monitoring, and archival), enforces fine-grained authentication and authorization, and orchestrates traceable, end-to-end workflows that bridge computational and physical laboratories. Based on SCP, we have constructed a scientific discovery platform that offers researchers and agents a large-scale ecosystem of more than 1,600 tool resources. Across diverse use cases, SCP facilitates secure, large-scale collaboration between heterogeneous AI systems and human researchers while significantly reducing integration overhead and enhancing reproducibility. By standardizing scientific context and tool orchestration at the protocol level, SCP establishes essential infrastructure for scalable, multi-institution, agent-driven science.

cs.AI↗

arXiv2025

Two-stage Respiratory Motion-resolved Radial MR Image Reconstruction Using an Interpretable Deep Unrolled Network

Due to the prolonged MRI encoding process, respiratory motion can cause undesired artifacts and image blurring, degrading image quality and limiting clinical applications in abdominal and pulmonary imaging. In this work, we develop a two-stage respiratory motion-resolved radial MR image reconstruction pipeline using an interpretable deep unrolled network (MoraNet), enabling high-quality imaging under free-breathing conditions. Firstly, low-resolution images are reconstructed from the central region of successive golden-angle radial k-space to extract respiratory motion signals. The binned k-space data based on the respiratory signal are then used to reconstruct the motion-resolved high-resolution image for each motion state. The MoraNet applies nonuniform fast Fourier transform (NUFFT) to operate radial encoding and convolutional neural network (CNN) modules to conduct image regularizations. The MoraNet was trained on retrospectively acquired lung MRI images for both fully sampled and undersampled acquisitions. The performance of the proposed method was evaluated on digital CT/MRI breathing XCAT (CoMBAT) phantom data, QUASAR motion phantom data acquired from a 1.0T MRI scanner and volunteer chest data acquired from a 1.5T MRI scanner. The MoraNet pipeline was compared with motion-averaged reconstruction and a conventional compressed sensing (CS)-based method in terms of SSIM, RMSE and computation time. Simulation and experimental results demonstrated that the proposed network could provide accurate respiratory signal estimation and enable effective motion correction. Compared with the CS method, the MoraNet preserved better structural details with lower RMSE and higher SSIM values at acceleration factor of 4, and meanwhile took ten-fold faster inference time.

physics.med-ph↗

arXiv2025

Flamelet Model with Epsilon Tracking in a Turbine Stator

Combustion within a two-dimensional turbine stator passage is numerically investigated in the context of the turbine-burner concept using a Reynolds-Averaged Navier-Stokes framework coupled with a novel flamelet model. The formulation links resolved-scale turbulence quantities with subgrid flamelet dynamics through the local turbulent kinetic energy dissipation rate, $ε$, which determines the flamelet inflow strain rate. For the first time, combustion of JP-5 is considered in a turbine stator passage as a practical fuel. This is achieved by solving transport equations for 14 major species on the resolved scale, while chemical source terms are obtained from precomputed flamelet libraries based on the HyChem A3 mechanism comprising 119 species and 841 elementary reactions. Model performance is assessed against methane combustion using both a one-step kinetics model and an $ε$-based flamelet formulation employing a 13-species skeletal mechanism. The $ε$-based formulation predicts lower peak flame temperatures due to dissociation effects and approximately 50\% lower net chemical energy addition per unit mass compared with the one-step model, as a result of flame stand-off and downstream strain-rate-induced quenching. For JP-5, the simulations capture combined endothermic pyrolysis and exothermic oxidation processes, leading to vertically displaced reaction zones, increased near-wall temperatures, and larger resolved-scale reaction regions due to the higher flamelet flammability limit relative to methane.

physics.flu-dyn↗

arXiv2025

Performance of Flamelet Models with Epsilon Tracking for Diffusion Flame Simulations

This work examines the physical consistency of the conventional Flamelet Progress Variable (FPV) model for diffusion flame simulations and and introduces a new compressible flamelet formulation that employs the turbulent kinetic energy dissipation rate, $ε$, as the tracking variable. Two-dimensional Reynolds-averaged Navier-Stokes (RANS) simulations are conducted for a reacting, transonic, turbulent mixing layer to assess the coupling between resolved-scale and subgrid flamelet quantities, with emphasis on the role of strain rate. The FPV model is found to decouple resolved-scale and subgrid strain rates, leading to the preferential selection of equilibrium flamelet solutions in regions of high strain and resulting in nonphysical predictions of heat release and species composition. The proposed $ε$-based formulation restores physical consistency by relating the subgrid flamelet strain rate to $ε$, allowing the flamelet to respond to the local resolved-scale strain field. The inclusion of resolved-scale species transport enables advective and diffusive redistribution of products across locally quenched regions. The results indicate that $ε$ offers a physically consistent tracking variable that connects the sub-grid flamelet model to resolved-scale RANS computations.

physics.flu-dyn↗

arXiv2025

AG-MPBS: a Mobility-Aware Prediction and Behavior-Based Scheduling Framework for Air-Ground Unmanned Systems

As unmanned systems such as Unmanned Aerial Vehicles (UAVs) and Unmanned Ground Vehicles (UGVs) become increasingly important to applications like urban sensing and emergency response, efficiently recruiting these autonomous devices to perform time-sensitive tasks has become a critical challenge. This paper presents MPBS (Mobility-aware Prediction and Behavior-based Scheduling), a scalable task recruitment framework that treats each device as a recruitable "user". MPBS integrates three key modules: a behavior-aware KNN classifier, a time-varying Markov prediction model for forecasting device mobility, and a dynamic priority scheduling mechanism that considers task urgency and base station performance. By combining behavioral classification with spatiotemporal prediction, MPBS adaptively assigns tasks to the most suitable devices in real time. Experimental evaluations on the real-world GeoLife dataset show that MPBS significantly improves task completion efficiency and resource utilization. The proposed framework offers a predictive, behavior-aware solution for intelligent and collaborative scheduling in unmanned systems.

cs.RO↗

arXiv2025

Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows

Despite advances in scientific AI, a coherent framework for Scientific General Intelligence (SGI)-the ability to autonomously conceive, investigate, and reason across scientific domains-remains lacking. We present an operational SGI definition grounded in the Practical Inquiry Model (PIM: Deliberation, Conception, Action, Perception) and operationalize it via four scientist-aligned tasks: deep research, idea generation, dry/wet experiments, and experimental reasoning. SGI-Bench comprises over 1,000 expert-curated, cross-disciplinary samples inspired by Science's 125 Big Questions, enabling systematic evaluation of state-of-the-art LLMs. Results reveal gaps: low exact match (10--20%) in deep research despite step-level alignment; ideas lacking feasibility and detail; high code executability but low execution result accuracy in dry experiments; low sequence fidelity in wet protocols; and persistent multimodal comparative-reasoning challenges. We further introduce Test-Time Reinforcement Learning (TTRL), which optimizes retrieval-augmented novelty rewards at inference, enhancing hypothesis novelty without reference answer. Together, our PIM-grounded definition, workflow-centric benchmark, and empirical insights establish a foundation for AI systems that genuinely participate in scientific discovery.

cs.AI↗

arXiv2025

Controlled Evolution-Based Day-Ahead Robust Dispatch Considering Frequency Security with Frequency Regulation Loads and Curtailable Loads

With the extensive integration of volatile and uncertain renewable energy, power systems face significant challenges in primary frequency regulation due to instantaneous power fluctuations. However, the maximum frequency deviation constraint is inherently non-convex, and commonly used two-stage dispatch methods overlook causality, potentially resulting in infeasible day-ahead decisions. This paper presents a controlled evolution-based day-ahead robust dispatch method to address these issues. First, we suggest the convex relaxation technique to transform the maximum frequency deviation constraint to facilitate optimization. Then, an evolution-based robust dispatch framework is introduced to align day-ahead decisions with intraday strategies, ensuring both frequency security and power supply reliability. Additionally, a novel controlled evolution-based algorithm is developed to solve this framework efficiently. Case studies on a modified IEEE 14-bus system demonstrate the superiority of the proposed method in enhancing frequency security and system reliability.

eess.SY↗

arXiv2025

How Do Graph Signals Affect Recommendation: Unveiling the Mystery of Low and High-Frequency Graph Signals

Spectral graph neural networks (GNNs) are highly effective in modeling graph signals, with their success in recommendation often attributed to low-pass filtering. However, recent studies highlight the importance of high-frequency signals. The role of low-frequency and high-frequency graph signals in recommendation remains unclear. This paper aims to bridge this gap by investigating the influence of graph signals on recommendation performance. We theoretically prove that the effects of low-frequency and high-frequency graph signals are equivalent in recommendation tasks, as both contribute by smoothing the similarities between user-item pairs. To leverage this insight, we propose a frequency signal scaler, a plug-and-play module that adjusts the graph signal filter function to fine-tune the smoothness between user-item pairs, making it compatible with any GNN model. Additionally, we identify and prove that graph embedding-based methods cannot fully capture the characteristics of graph signals. To address this limitation, a space flip method is introduced to restore the expressive power of graph embeddings. Remarkably, we demonstrate that either low-frequency or high-frequency graph signals alone are sufficient for effective recommendations. Extensive experiments on four public datasets validate the effectiveness of our proposed methods. Code is avaliable at https://github.com/mojosey/SimGCF.

cs.LG↗

arXiv2025

Self-Reinforced Deep Priors for Reparameterized Full Waveform Inversion

Full waveform inversion (FWI) has become a widely adopted technique for high-resolution subsurface imaging. However, its inherent strong nonlinearity often results in convergence toward local minima. Recently, deep image prior-based reparameterized FWI (DIP-FWI) has been proposed to alleviate the dependence on massive training data. By exploiting the spectral bias and implicit regularization in the neural network architecture, DIP-FWI can effectively avoid local minima and reconstruct more geologically plausible velocity models. Nevertheless, existing DIP-FWI typically use a fixed random input throughout the inversion process, which fails to utilize the mapping and correlation between the input and output of the network. Moreover, under complex geological conditions, the lack of informative prior in the input can exacerbate the ill-posedness of the inverse problem, leading to artifacts and unstable reconstructions. To address these limitations, we propose a self-reinforced DIP-FWI (SRDIP-FWI) framework, in which a steering algorithm alternately updates both the network parameters and the input at each iteration using feedback from the current network output. This design allows adaptive structural enhancement and improved regularization, thereby effectively mitigating the ill-posedness in FWI. Additionally, we analyze the spectral bias of the network in SRDIP-FWI and quantify its role in multiscale velocity model building. Synthetic tests and field land data application demonstrate that SRDIP-FWI achieves superior resolution, improved accuracy and greater depth penetration compared to multiscale FWI. More importantly, SRDIP-FWI eliminates the need for manual frequency-band selection and time-window picking, substantially simplifying the inversion workflow. Overall, the proposed method provides a novel, adaptive and robust framework for accurate subsurface velocity model reconstruction.

physics.geo-ph↗

arXiv2025

Rethinking Training Dynamics in Scale-wise Autoregressive Generation

Recent advances in autoregressive (AR) generative models have produced increasingly powerful systems for media synthesis. Among them, next-scale prediction has emerged as a popular paradigm, where models generate images in a coarse-to-fine manner. However, scale-wise AR models suffer from exposure bias, which undermines generation quality. We identify two primary causes of this issue: (1) train-test mismatch, where the model must rely on its own imperfect predictions during inference, and (2) imbalance in scale-wise learning difficulty, where certain scales exhibit disproportionately higher optimization complexity. Through a comprehensive analysis of training dynamics, we propose Self-Autoregressive Refinement (SAR) to address these limitations. SAR introduces a Stagger-Scale Rollout (SSR) mechanism that performs lightweight autoregressive rollouts to expose the model to its own intermediate predictions, thereby aligning train-test patterns, and a complementary Contrastive Student-Forcing Loss (CSFL) that provides adequate supervision for self-generated contexts to ensure stable training. Experimental results show that applying SAR to pretrained AR models consistently improves generation quality with minimal computational overhead. For instance, SAR yields a 5.2% FID reduction on FlexVAR-d16 trained on ImageNet 256 within 10 epochs (5 hours on 32xA100 GPUs). Given its efficiency, scalability, and effectiveness, we expect SAR to serve as a reliable post-training method for visual autoregressive generation.

cs.CV↗

arXiv2025

On the Bayes Inconsistency of Disagreement Discrepancy Surrogates

Deep neural networks often fail when deployed in real-world contexts due to distribution shift, a critical barrier to building safe and reliable systems. An emerging approach to address this problem relies on \emph{disagreement discrepancy} -- a measure of how the disagreement between two models changes under a shifting distribution. The process of maximizing this measure has seen applications in bounding error under shifts, testing for harmful shifts, and training more robust models. However, this optimization involves the non-differentiable zero-one loss, necessitating the use of practical surrogate losses. We prove that existing surrogates for disagreement discrepancy are not Bayes consistent, revealing a fundamental flaw: maximizing these surrogates can fail to maximize the true disagreement discrepancy. To address this, we introduce new theoretical results providing both upper and lower bounds on the optimality gap for such surrogates. Guided by this theory, we propose a novel disagreement loss that, when paired with cross-entropy, yields a provably consistent surrogate for disagreement discrepancy. Empirical evaluations across diverse benchmarks demonstrate that our method provides more accurate and robust estimates of disagreement discrepancy than existing approaches, particularly under challenging adversarial conditions.

cs.LG↗

arXiv2025

From fractional Chern insulators to topological electronic crystals in moiré MoTe2: quantum geometry tuning via remote layer

The quantum geometry of Bloch wavefunctions,encoded in the Berry curvature and quantum metric, is believed to be a decisive ingredient in stabilizing fractional quantum anomalous Hall (FQAH) effect(i.e., fractional Chern insulator, FCI, at zero magnetic field), against competing symmetry-breaking phases.A direct experimental demonstration of quantum geometry-driven switching between distinct correlated topological phases, however, has been lacking. Here, we report experimental evidence of such a switch in a high-quality 3.7 twisted MoTe2 (tMoTe2) device consisting of both A-A bilayer and A-AB trilayer regions. While composite Fermi liquid CFL/FQAH phases are established in A-A tMoTe2,the A-AB region-effectively an A-A moire bilayer proximitized by a remote B layer-develops a series of topological electronic crystal (TEC, also referred to as generalized QAH crystal, QAHC) states with integer quantized Hall conductance at commensurate fractional fillings v=1/2, 2/3, and an incommensurate filling factor v=0.53.The electrostatic phase diagram is mapped out by combined transport and optical measurements, showing that these TEC states emerge within the first moir'e valence band prior to any charge transfer to the B layer. Exact diagonalization (ED) incorporating the remote-layer-induced intralayer potential demonstrates a transition from a CFL-like manifold in the A-A limit to a Chern number C=1 ground-state consistent with a TEC at v=1/2 , accompanied by the further breakdown of ideal band geometry. Our results provide experimental evidence of quantum geometry-tuned competition between FQAH/CFL and TEC phases in a moiré Chern band and pave the way for further exploring correlation-driven topological phenomena by tuning quantum geometry.

cond-mat.mes-hall↗

arXiv2025

RELIC: Interactive Video World Model with Long-Horizon Memory

A truly interactive world model requires three key ingredients: real-time long-horizon streaming, consistent spatial memory, and precise user control. However, most existing approaches address only one of these aspects in isolation, as achieving all three simultaneously is highly challenging-for example, long-term memory mechanisms often degrade real-time performance. In this work, we present RELIC, a unified framework that tackles these three challenges altogether. Given a single image and a text description, RELIC enables memory-aware, long-duration exploration of arbitrary scenes in real time. Built upon recent autoregressive video-diffusion distillation techniques, our model represents long-horizon memory using highly compressed historical latent tokens encoded with both relative actions and absolute camera poses within the KV cache. This compact, camera-aware memory structure supports implicit 3D-consistent content retrieval and enforces long-term coherence with minimal computational overhead. In parallel, we fine-tune a bidirectional teacher video model to generate sequences beyond its original 5-second training horizon, and transform it into a causal student generator using a new memory-efficient self-forcing paradigm that enables full-context distillation over long-duration teacher as well as long student self-rollouts. Implemented as a 14B-parameter model and trained on a curated Unreal Engine-rendered dataset, RELIC achieves real-time generation at 16 FPS while demonstrating more accurate action following, more stable long-horizon streaming, and more robust spatial-memory retrieval compared with prior work. These capabilities establish RELIC as a strong foundation for the next generation of interactive world modeling.

cs.CV↗

arXiv2025

Design and Construction of a Dedicated Radiolucent 8-element Flexible Radiofrequency (RF) Torso Coil for the 1.0T Australian MRI-Linac System

Magnetic resonance imaging-guided linear accelerators (MRI-Linacs) are an emerging treatment technology that enable online soft-tissue visualisation and adaptive radiotherapy. The Australian 1.0 T MRI-Linac employs a fixed, inline beamline, with treatment angles achieved via patient couch rotation, and currently relies on a radiolucent whole-body radiofrequency (RF) coil. However, the large coil-patient separation limits signal-to-noise ratio (SNR) and constrains the fast imaging required for real-time tumour tracking. Here, we show the design and validation of a dedicated, flexible 8-element receive-only RF torso array tailored to the geometry and beam access requirements of the Australian MRI-Linac. Electromagnetic simulations, bench measurements, and phantom imaging demonstrate approximately three-fold SNR improvement at the centre and eight-fold improvement at superficial regions compared with the whole-body coil. In vivo abdominal imaging confirms enhanced anatomical detail and sharper tissue boundaries, and the increased SNR enables parallel imaging with GRAPPA acceleration factors up to three without severe artefacts. Dosimetry measurements and dynamic beam-on noise analysis confirm that the coil array is effectively radiolucent, with dose differences below 1% and no measurable degradation in image noise. This work demonstrates a practical RF solution for accelerated, high-SNR imaging compatible with patient rotation and beam delivery on the Australian MRI-Linac.

physics.med-ph↗

arXiv2025

Exploring Weak-to-Strong Generalization for CLIP-based Classification

Aligning large-scale commercial models with user intent is crucial to preventing harmful outputs. Current methods rely on human supervision but become impractical as model complexity increases. When models surpass human knowledge, providing accurate feedback becomes challenging and inefficient. A novel solution proposed recently is using a weaker model to supervise a stronger model. This concept leverages the ability of weaker models to perform evaluations, thereby reducing the workload on human supervisors. Previous work has shown the effectiveness of weak-to-strong generalization in the context of language-only models. Extending this concept to vision-language models leverages these insights, adapting the proven benefits to a multi-modal context. In our study, we explore weak-to-strong generalization for CLIP-based classification. We propose a method, class prototype learning (CPL), which aims to enhance the classification capabilities of the CLIP model, by learning more representative prototypes for each category. Our findings indicate that, despite using a simple loss function under weak supervision, CPL yields robust improvements in targeted scenarios, particularly when pretraining is limited. Extensive experiments demonstrate that our approach is effective under these settings, achieving a 3.67% improvement over strong baseline methods.

cs.CV↗

arXiv2025

HiFi-MambaV2: Hierarchical Shared-Routed MoE for High-Fidelity MRI Reconstruction

Reconstructing high-fidelity MR images from undersampled k-space data requires recovering high-frequency details while maintaining anatomical coherence. We present HiFi-MambaV2, a hierarchical shared-routed Mixture-of-Experts (MoE) Mamba architecture that couples frequency decomposition with content-adaptive computation. The model comprises two core components: (i) a separable frequency-consistent Laplacian pyramid (SF-Lap) that delivers alias-resistant, stable low- and high-frequency streams; and (ii) a hierarchical shared-routed MoE that performs per-pixel top-1 sparse dispatch to shared experts and local routers, enabling effective specialization with stable cross-depth behavior. A lightweight global context path is fused into an unrolled, data-consistency-regularized backbone to reinforce long-range reasoning and preserve anatomical coherence. Evaluated on fastMRI, CC359, ACDC, M4Raw, and Prostate158, HiFi-MambaV2 consistently outperforms CNN-, Transformer-, and prior Mamba-based baselines in PSNR, SSIM, and NMSE across single- and multi-coil settings and multiple acceleration factors, consistently surpassing consistent improvements in high-frequency detail and overall structural fidelity. These results demonstrate that HiFi-MambaV2 enables reliable and robust MRI reconstruction.

cs.CV↗

arXiv2025

Group Equivariant Convolutional Networks for Pathloss Estimation

This paper presents RadioGUNet, a UNet-based deep learning framework for pathloss estimation in wireless communication. Unlike other frameworks, it leverages group equivariant convolutional networks, which are known to increase the expressive capacity of a neural network by allowing the model to generalize to further classes of symmetries, such as rotations and reflections, without the need for data augmentation or data pre-processing. The results of this work are twofold. First, we show that typical UNet-based convolutional models can be easily extended to support group equivariant convolution (g-conv). Secondly, we show that the task of pathloss estimation benefits from such an extension, as the proposed extended model outperforms typical UNet-based models by up to 0.41 dB for a similar number of parameters in the RadioMapSeer dataset. The code is publicly available on the GitHub page: https://github.com/EricssonResearch/radiogunet

cs.NI↗

arXiv2025

Person Recognition in Aerial Surveillance: A Decade Survey

The rapid emergence of airborne platforms and imaging sensors is enabling new forms of aerial surveillance due to their unprecedented advantages in scale, mobility, deployment, and covert observation capabilities. This paper provides a comprehensive overview of 150+ papers over the last 10 years of human-centric aerial surveillance tasks from a computer vision and machine learning perspective. It aims to provide readers with an in-depth systematic review and technical analysis of the current state of aerial surveillance tasks using drones, UAVs, and other airborne platforms. The object of interest is humans, where human subjects are to be detected, identified, and re-identified. More specifically, for each of these tasks, we first identify unique challenges in performing these tasks in an aerial setting compared to the popular ground-based setting and subsequently compile and analyze aerial datasets publicly available for each task. Most importantly, we delve deep into the approaches in the aerial surveillance literature with a focus on investigating how they presently address aerial challenges and techniques for improvement. We conclude the paper by discussing the gaps and open research questions to inform future research avenues.

cs.CV↗