Search arXiv⌕ Search

arXiv subjects

Feng Li

Publications and source records attributed to Feng Li.

At least 19 recordsLinked to original sources
arXiv2026

Feasibility of Augmented Reality-Guided Robotic Ultrasound with Cone-Beam CT Integration for Spine Procedures

Accurate needle placement in spine interventions is critical for effective pain management, yet it depends on reliable identification of anatomical landmarks and careful trajectory planning. Conventional imaging guidance often relies on both computed tomography (CT) and X-ray fluoroscopy, exposing patients and staff to high doses of radiation while providing limited real-time 3D feedback. We present an optical see-through augmented reality (OST-AR)-guided robotic system for spine procedures that provides in situ visualization of spinal structures to support needle trajectory planning. We integrate a cone-beam CT (CBCT)-derived 3D spine model, which is co-registered with live ultrasound, enabling users to combine global anatomical context with local, real-time imaging. We evaluated the system in a phantom user study involving two representative spine procedures: facet joint injection and lumbar puncture. Sixteen participants performed insertions under two visualization conditions: conventional screen vs. AR. Results show that AR significantly reduces execution time and across-task placement error, while also improving usability, trust, and spatial understanding, and lowering cognitive workload. These findings demonstrate the feasibility of AR-guided robotic ultrasound for spine interventions, highlighting its potential to enhance accuracy, efficiency, and user experience in image-guided procedures.

cs.HC↗
arXiv2026

KITE: Retrieval as a Decision Procedure for Long-Term Conversational Memory

Many long-term memory systems for LLM agents are built around embedding-based retrieval. Al- though effective for semantic matching, similarity ranking alone does not establish whether re- trieved memories satisfy the conditions implied by a question. In this paper, we introduce KITE (Knowledge-Indexed Temporal Evidence), a vector-free framework that formulates memory re- trieval as an explicit decision procedure. KITE organizes multi-session conversations as structured knowledge indexed by a governed topic vocabulary, which evolves through controlled expansion and consolidation. At query time, questions are compiled into inspectable retrieval plans over the same knowledge index that guides memory construction. The plans are then executed through fixed lookup and ranking operations, while sparse lexical retrieval recovers surface details omitted from the structured representation. Experiments on LoCoMo and LongMemEval-S show that KITE achieves 93.5% and 86.0% accuracy while using only about 1.6k reader-context tokens per ques- tion. These results demonstrate that conversational memory can move beyond similarity ranking by unifying memory construction and query compilation around a governed index, turning retrieval into an inspectable decision procedure for determining which evidence satisfies the question.

cs.IR↗
arXiv2026

WFST Follow-up of S251112cm: Searching for an Optical Counterpart to a Subsolar-mass Compact-binary Merger Candidate

Electromagnetic counterparts to gravitational-wave (GW) sources probe the properties, environments, and evolution of compact-object mergers. S251112cm belongs to an emerging class of GW candidates with possible subsolar-mass components. We present an optical counterpart search for S251112cm with the Wide Field Survey Telescope (WFST). Observations began 20.2 hr after the GW trigger and lasted three nights, covering approximately 780 deg$^2$ and 51% of the localization probability in the updated skymap. Our search for newly emerging, rapidly evolving, off-nuclear optical transients yielded four candidates with host-galaxy distances broadly consistent with the GW distance estimate. All four evolve substantially more slowly than AT 2017gfo, ruling out an AT 2017gfo-like origin and disfavoring their association with S251112cm as rapidly evolving kilonova counterparts. Combining WFST and DECam increases the localization probability coverage to approximately 67%. Assuming the counterpart lies within this footprint, we constrain a grid of binary-neutron-star kilonova models. For viewing angles $θ_{\rm obs}<60^\circ$, with other parameters fixed to the AT 2017gfo best-fit values, models with dynamical ejecta mass $M_{\rm dyn}\gtrsim0.01 M_\odot$ or wind ejecta mass $M_{\rm wind}\gtrsim0.05 M_\odot$ are disfavored over most of the covered GW probability. Our phenomenological analysis further constrains rapidly evolving optical transients with $T_{\rm rise,1/2}\leq2$ days to peak absolute magnitudes fainter than approximately -13 mag. To our knowledge, WFST provides the strongest optical constraints to date in the northern sky on possible rapidly evolving counterparts to this new class of GW candidates with subsolar-mass components. The comparable depths and complementary sky coverage of WFST and DECam extend these constraints across more of the localization region at similar sensitivity.

astro-ph.HE↗
arXiv2026

Deriving the anomalous Lorentz transformation and side jump using a trace method

The side jump in the anomalous Lorentz transformation, arising from the spin-orbit interactions, plays important roles in various intriguing physics, such as chiral vortical effects and spin polarization. In this work, the side jump of the spin-half particles is visualized and evaluated ab initio within Dirac theory, through a comprehensive study of the density $ψ^\daggerψ$ and position $\int d^3xψ^\dagger \mathbf{x}ψ$ of a wave packet under Lorentz transformation. A compact gamma-matrix representation of the Lorentz boost matrix of a Dirac spinor, $S(\boldsymbolη)= h_{\boldsymbolη}^μγ_μ\check{u}^νγ_ν$, has been found. Based on this expression, a trace method has been developed to derive the anomalous Lorentz transformation of the center of the probability density of a spin-half fermion wave packet, and a compact analytical expression for the side jump has been obtained through a transparent and tractable derivation. The momentum width plays an important role in the side jump. For example, for Gaussian wave packets, increasing the width suppresses the displacement, while the side jump at fixed width depends nonmonotonically on mass, reaching a maximum at a finite mass. In the zero-width limit, the side jump takes a compact form perpendicular to both the Pauli-Lubanski vector and the boost direction, recovering the known result for a chiral particle.

nucl-th↗
arXiv2026

A global stochastic maximum principle for delayed forward-backward stochastic control systems

In this paper, we study a delayed forward-backward stochastic control system in which all the coefficients depend on the state and control terms, and the control domain is an arbitrary nonempty set. To handle the terms involving $y$ and $z$ in the second-order expansion, we derive two decompositions of $\big(\hat{y}^\e(\cd), \hat{z}^\e(\cd)\big)$. More precisely, we use the second decomposition to handle the terms involving $f^\e_{yy}, f^\e_{yz}$ and use both decompositions to handle the term involving $f^\e_{zz}$. Finally, a global stochastic maximum principle is obtained.

math.OC↗
arXiv2026

Rethinking Data Imbalance in Class Incremental Surgical Instrument Segmentation

In surgical instrument segmentation, the increasing variety of instruments over time poses a significant challenge for existing neural networks, as they are unable to effectively learn such incremental tasks and suffer from catastrophic forgetting. When learning new data, the model experiences a sharp performance drop on previously learned data. Although several continual learning methods have been proposed for incremental understanding tasks in surgical scenarios, the issue of data imbalance often leads to a strong bias in the segmentation head, resulting in poor performance. Data imbalance can occur in two forms: (i) class imbalance between new and old data, and (ii) class imbalance within the same time point of data. Such imbalances often cause the dominant classes to take over the training process of continual semantic segmentation (CSS). To address this issue, we propose SurgCSS, a novel plug-and-play CSS framework for surgical instrument segmentation under data imbalance. Specifically, we generate realistic surgical backgrounds through inpainting and blend instrument foregrounds with the generated backgrounds in a class-aware manner to balance the data distribution in various scenarios. We further propose the Class Desensitization Loss by employing contrastive learning to correct edge biases caused by data imbalance. Moreover, we dynamically fuse the weight parameters of the old and new models to achieve a better trade-off between the biased and unbiased model weights. To investigate the data imbalance problem in surgical scenarios, we construct a new benchmark for surgical instrument CSS by integrating datasets. Extensive experiments demonstrate the effectiveness of the proposed framework, achieving significant performance improvement against existing baselines.

cs.CV↗
arXiv2026

EviGround-CT: Sentence-to-Volume Grounding for Verifying LLM-Generated Chest CT Reports

Chest computed tomography (CT) reports generated by large language models (LLMs) can describe positive findings that lack localized evidence in the scan. We propose EviGround-CT to verify these findings after report generation. A deterministic extractor identifies positive finding sentences, and a 3D grounding model predicts an evidence mask for each sentence. Using the full sentence retains anatomical location, laterality, and descriptive modifiers in the grounding query. We evaluate report generation on CT-RATE, and grounding and verification on a held-out 100-case ReXGroundingCT subset. Using the available annotations, sentence-grounded verification raises evidence-supported precision (ESP) from 0.263 to 0.365 across 137 extracted in-scope positives, compared with category conditioning. The corresponding unsupported positive finding rate falls from 0.737 to 0.635. The paired case-level bootstrap ESP difference is +0.102 (95% confidence interval: [0.028, 0.181]). The predicted masks associate individual report statements with spatial evidence that can be inspected alongside the CT.

cs.CL↗
arXiv2026

Deformable CT-US Registration via Anatomy-Aware Implicit Neural Representations

Slice-to-volume registration between ultrasound (US) and preoperative computed tomography (CT) imaging would enhance many minimally invasive interventions, for example by locating soft tissue structures intra-operatively that are discernible in CT. While optical tracking enables initial rigid registration, contact from the probe induces soft tissue deformations that inhibit accurate alignment. In this work, we introduce a deformable CT-ultrasound registration framework that incorporates anatomical priors derived from CT to improve registration under deformation. Rigid registration is first established using a robot-assisted optical tracking system, after which a deformable transformation is estimated using a sinusoidal implicit neural representation (SIREN) optimized per frame. Tissue stiffness is approximated from CT-based HU values and used as spatially varying regularization, suppressing deformation in rigid structures such as bone while allowing more flexibility in soft tissue. Two additional constraints capture the physics of probe contact: a contact-zone displacement prior that drives the displacement field to compress tissue below the probe face, and a fan-geometry regularization term based on beam direction and convex transducer field of view. Model parameters are optimized with a normalized gradient field (NGF). The proposed approach improves alignment over rigid initialisation by 17% and outperforms classical deformable baselines while maintaining near-zero topological folding.

cs.CV↗
arXiv2026

Complete solution to the weak persistent center and isochronous center problems of cubic polynomial systems

In this paper, we investigate weakly persistent centers for several classes of planar cubic differential systems, including systems with a nondegenerate linear center and systems with a nilpotent center. Necessary parameter relations are obtained by computing singular point quantities or quasi-Lyapunov constants, while their sufficiency is established by suitable analytic constructions. For the general complex cubic system, we obtain necessary and sufficient conditions for the origin to be a weakly persistent center, and the corresponding result for the associated general real cubic system follows by imposing the conjugacy relations between the complex coefficients. We further characterize the weakly persistent isochronous centers of the general complex cubic system by combining the weakly persistent center conditions with the vanishing of the linearization quantities and constructing time-preserving analytic linearizations.

math.DS↗
arXiv2026

Decoupling Spherical Reasoning from Dense Prediction for 360 Depth Estimation

The equirectangular projection (ERP) is widely used for panoramic depth estimation, but its spatially varying distortion makes geometry-consistent feature modeling challenging. We revisit panoramic depth estimation by decoupling contextual modeling in native spherical space from dense ERP prediction. To this end, we propose a Fibonacci Spherical Graph (FSG) as an intermediate reasoning space to lift ERP features onto quasi-uniform Fibonacci nodes on the sphere and capture local and long-range dependencies through complementary spherical neighborhoods. The resulting spherical discretization distributes graph nodes approximately uniformly over the spherical surface, reducing the over-representation of highly stretched regions during relational modeling. Operating on a compact set of Fibonacci nodes also avoids the computational burden of constructing and processing a graph at full ERP resolution. To bridge spherical reasoning and dense prediction, we propose a Spherical Context Conditioning (SCC) module that adaptively modulates dense ERP features with the enhanced spherical representation, allowing spherical context to guide pixel-aligned depth prediction. Extensive experiments on three benchmarks demonstrate that the proposed method consistently achieves superior depth accuracy over existing approaches.

cs.CV↗
arXiv2026

A global stochastic maximum principle for forward-backward stochastic control systems with quadratic convex generator and unbounded terminal condition

In this paper, we study a stochastic optimal control problem for forward-backward stochastic control systems with quadratic convex generator and unbounded terminal condition, where the control domain is not necessarily convex. Since the existing bounded mean oscillation (BMO) martingale approach used in the setting of quadratic BSDEs with bounded terminal conditions is not directly applicable to the present setting, we introduce a new probability measure, under which all subsequent analysis is then carried out. Finally, a global stochastic maximum principle is obtained.

math.OC↗
arXiv2026

Scanning While Imagining: A Scene-Graph World Model for Robotic Ultrasound Navigation

Ultrasound (US) acquisition depends on the operator's ability to interpret anatomy and anticipate how the view will change with probe motion. Many robotic US navigation methods select actions without explicitly predicting these anatomical changes. We propose SonoGraph-WM, an action- and goal-conditioned world model for anticipatory probe navigation. The model represents anatomy as scene graphs (SGs), capturing visible structures, their geometry, and spatial relationships without synthesizing US images. Given a history of SGs and probe poses, a unified Transformer jointly predicts future SGs and poses. A receding-horizon planner recursively imagines candidate trajectories, selects the shortest predicted path reaching a goal graph, and follows it over a short execution horizon before replanning from new observations. To reduce reliance on tracked and anatomically annotated US sequences, we generate aligned SG--pose training data from computed tomography (CT) label maps along surface-constrained probe trajectories. On four held-out CT cases, spatial relation F1 remains above 93% over 20 prediction steps, and closed-loop navigation achieves 77.50% and 75.00% success for the gallbladder and pancreas, respectively, using annotation-derived SGs. In robot--phantom navigation experiments with label-map-derived SGs, the planner reached the target view in 73.7% of trials. These findings support CT-supervised anatomical world modeling for probe planning and highlight the importance of frequent observation updates for reliable navigation. Project Page: https://noseefood.github.io/us-sonograph-wm/

cs.RO↗
arXiv2026

Evaluating Sycophancy in Chinese Large Language Models on Factual Questions Derived from Online Search Queries

As large language models increasingly mediate information access, factually accurate and independent answers are critical. However, these models can exhibit sycophancy by aligning their responses with users' stated beliefs even when those beliefs are incorrect, potentially presenting misinformation as independently verified and reinforcing users' confidence in false claims. Prior work leaves unresolved whether introducing user beliefs causes correct responses to become incorrect or uncertain, or causes uncertain responses to become belief-aligned incorrect answers. It also remains unclear whether anti-sycophancy interventions preserve or restore factual accuracy or merely shift responses toward uncertainty. We analyze factual sycophancy in Chinese-language information seeking using yes/no fact-checking questions. Our analysis covers 364,941 responses from three frontier Chinese-based LLMs (DeepSeek, Qwen, and Doubao) to 12,165 factual questions derived from real-world Chinese search queries. We evaluate the models with and without reasoning across baseline, belief-conditioned, and anti-sycophancy prompting, tracing matched shifts among correct, incorrect, and uncertain responses. Under incorrect user beliefs, we distinguish belief-aligned errors from losses of factual confidence, in which initially correct answers become uncertain. Patterns vary across models and reasoning settings: reasoning is not a consistent safeguard, and anti-sycophancy instructions can reduce incorrect agreement while increasing uncertainty. In Chinese-language factual question answering, avoiding agreement with false beliefs is therefore not equivalent to preserving factual accuracy, highlighting the value of transition-level evaluation. Such behavior may undermine the reliability of LLM-mediated information access by reinforcing misinformation or weakening users' confidence in factually correct answers.

cs.CL↗
arXiv2026

Spectral divide-and-conquer MCMC for long stationary time series

The temporal dependence inherent in time series models poses a fundamental challenge for distributed Bayesian inference, as it precludes embarrassingly parallel algorithms based on naive independence assumptions in the time domain. We propose a frequency-domain framework for scalable Bayesian inference in stationary time series that exploits the asymptotic independence underlying the Whittle likelihood. To exploit parallel computing resources, we develop a distributed fast Fourier transform and integrate it with embarrassingly parallel Markov chain Monte Carlo (MCMC) algorithms within a modern cluster-computing framework. This enables the analysis of time series that exceed the memory capacity of a single computational node or for which computation time is a bottleneck. The proposed methodology is compatible with a broad class of existing divide-and-conquer algorithms for independent data by applying them to frequency-domain rather than time-domain partitions. We establish that the error of the spectral divide-and-conquer MCMC posterior approximation relative to the exact time-domain posterior converges to zero in probability in a shrinking neighbourhood of the full-data Whittle posterior mode. The corresponding convergence rate is also derived. Across several experiments, we demonstrate that our approach provides accurate approximations to the full-data Whittle posterior. The proposed method is shown to outperform the current state-of-the-art time-domain divide-and-conquer methodology, particularly for highly persistent processes. The methodology is further illustrated by fitting a semi-long range model to a long meteorological time series.

stat.ME↗
arXiv2026

TripScore: Aligning LLMs for Real-World Travel Planning via Expert-Calibrated Reward

In our deployed travel-planning service, most users give minimal inputs or free-form requests rather than the structured constraint checklists assumed by existing benchmarks. We therefore present TripScore, a behavior-grounded benchmark and evaluation framework built from real user logs and calibrated against 1,468 pairwise judgments by 203 travel experts. TripScore couples a hierarchical feasibility gate (format and commonsense) with a unified, point-wise reward that aggregates soft quality and preference fulfillment. Using TripScore as both evaluator and reward signal, we benchmark direct prompting, test-time compute, neuro-symbolic solvers, code agents, and fine-tuning. We find that reinforcement learning fine-tuning (e.g., GRPO) provides consistent gains over other approaches under the same base model and practical latency.

cs.AI↗
arXiv2026

MarKey: Marginal Utility Guided Greedy Keyframe Selection for Long Video Understanding

Long-video understanding remains challenging for multimodal large language models (MLLMs) because densely encoding long frame sequences is computationally expensive, while uniform sampling under a limited visual budget can miss sparse yet decisive evidence. Recent training-free keyframe selection methods have enabled more efficient inference and yielded promising performance gains. However, many existing methods score frames largely in isolation without explicitly considering how each candidate complements the currently selected subset, potentially resulting in redundant selections and incomplete evidence coverage. To address this limitation, we propose MarKey, a training-free framework that formulates keyframe selection as subset-aware greedy optimization. At each iteration, MarKey scores each candidate using a tractable surrogate that jointly accounts for query relevance, marginal coverage gain, and context-dependent redundancy, and selects the frame with the highest utility. To make this iterative subset-aware evaluation efficient, MarKey uses a compact set of representative anchors to approximate full-video coverage and a bounded window of previously selected frames to limit context-dependent comparisons. Experiments on six benchmarks spanning holistic video understanding, human-centric video understanding, and open-ended video understanding demonstrate that MarKey consistently outperforms existing methods. Further analyses show robust gains across different MLLM backbones, model scales, and frame budgets.

cs.CV↗
arXiv2026

SphereSOD: Geometry-Structure Coupled Learning for 360 Salient Object Detection

360° salient object detection (SOD) aims to accurately segment salient regions across a full field of view. However, equirectangular projection (ERP) introduces severe spatial distortion when mapping the spherical domain onto a planar representation. Existing methods mainly focus on compensating projection distortion while overlooking the interaction between panoramic geometry and salient object structure during feature perception and prediction refinement. To this end, we propose SphereSOD, an ERP-native framework that couples panoramic geometry with evolving salient structures. Specifically, spherical geometry governs feature sampling and spatial weighting, while coarse-grained saliency and contour prediction influence context aggregation during the progressive decoding process. SphereSOD first initializes deformable sampling based on spherical projection geometry and then employs bounded, content-adaptive offsets, yielding features that are better aligned with the underlying panoramic geometry. Subsequently, the decoder performs structure-guided context aggregation and progressive refinement to recover complete salient regions and accurate boundaries. Extensive experiments on three public 360° SOD benchmarks demonstrate state-of-the-art performance and a favorable accuracy-efficiency trade-off, supporting structurepreserving inference directly in ERP space as a promising alternative to projection-heavy panoramic pipelines.

cs.CV↗
arXiv2026

Deploying and Evaluating a Smart-Agriculture Agentic Engine for Full-Season Soybean Farm Operations

This paper presents FAIRY, a full-stack smart-agriculture agent system developed for and deployed to an operating soybean research farm at Harbin Institute of Technology's smart-agriculture site. We develop FAIRY to execute and evaluate agentic agronomic operations on full-season spatiotemporal workflows that span ridge preparation, planting, irrigation, fertilization, pest and disease treatment, harvest, grain handling, drying, and storage. FAIRY integrates APIs and infrastructure across production-grade machinery, fixed soil and canopy sensors, multispectral and thermal drones, satellite vegetation products, a weather station, calibrated crop-process models, agronomic records, and multi-season yield histories. The system is built around the novel "everything is an event" execution paradigm, which represents spatiotemporal world evolution, remote sensing and UAV observations, sensor readings, crop-growth transitions, machinery actions, and management interventions as state-changing events in a shared farm process engine. On top of this event-driven world model, FAIRY implements a complete agentic stack: a knowledge library of atomic agronomic skills; multi-agent controller and orchestration backends; frontier- and edge-model execution; full-path trace logging; and deployment profiling on local nodes. We use FAIRY to evaluate nine state-of-the-art agent controllers across one hundred full-season soybean scenarios that preserve the operational coupling between spatial observations in a 64-ridge field, temporal decision sequences, agronomic constraints, delayed effects, and final yield. We develop an evaluation suite that combines agentic success, full-path spatiotemporal correctness, token cost, and edge-device runtime.

cs.AI↗