arXiv subjects

Fei Chen

Publications and source records attributed to Fei Chen.

At least 19 recordsLinked to original sources

arXiv2026

Constraints on admissible behavior of GMRES applied to tridiagonal Toeplitz systems

The result of Greenbaum, Pták, and Strakoš that for a given set of eigenvalues, any convergence curve is possible [SIMAX 1996] and the subsequent parameterization of such matrix-right-hand side pairs $(A,\mathbf{b})$ of Arioli, Pták, and Strakoš [BIT 1998] demonstrated that the behavior of the GMRES could not be completely characterized by the eigenvalues of $A$ alone. In this paper, we consider how to use this theory to understand the admissible and attainable \gmres behavior for matrices with constrained structure, focussing on non-Hermitian (non-symmetric) tridiagonal Toeplitz matrices. We show that Toeptliz structure necessarily constrains the how the theory from these papers can manifest but that a continuum of admissible behaviors is still attainable.

math.NA↗

arXiv2026

The algebraic theory of non-archimedean intertwining periods

We develop an algebraic theory of local intertwining periods for symmetric pairs $(G,H,θ)$ over non-archimedean local fields $F$ of characteristic different from $2$, and finite-length representations of Levi subgroups of $G$ with coefficients in an algebraically closed field $R$ of characteristic different from the residual characteristic of $F$. For open orbits this algebraic version is essentially contained in the work of Blanc and Delorme. The theory relies on a crucial new uniqueness result, extending a result of Blanc and Delorme for open periods, which asserts that an admissible intertwining period is the only $H$-equivariant linear form extending the corresponding integral on the space of well-supported sections. In the group case it recovers at once the results of Dat on algebraic intertwining operators. Our algebraic construction does not require the unimodularity hypothesis imposed in the work of Matringe--Offen--Yang. When $R=\mathbb{C}$, we also remove this assumption in the classical non-archimedean analytic setting, and prove convergence of intertwining periods for all symmetric spaces. At the same time we extend the context of the whole theory in the following manner: we allow $F$ to be of positive odd characteristic, we allow twisting characters in the periods, and we allow $H$ to lie between $(\mathbb{G}^θ)^\circ(F)$ and $G^θ$. Finally, in the algebraic setting, we obtain explicit polynomial bounds for the singularities of intertwining periods, and compute them in a concrete case.

math.RT↗

arXiv2026

Timed Recovery Safe Gradient Flows for Constrained Nonlinear Programming

This paper studies how to relax pointwise feasibility in continuous-time dynamics for inequality-constrained nonlinear programming while retaining a quantitative feasible-recovery guarantee. Existing safe gradient flows enforce forward invariance of the feasible set, which yields an anytime-feasible dynamics but can be overly restrictive for optimization because it suppresses transient infeasible motion that may be essential for effective descent. To address this limitation, we propose a timed recovery safe gradient flow that replaces pointwise feasibility with fixed-horizon feasible recovery. The proposed construction augments the state with a timer that records the elapsed infeasible duration and computes a minimum-norm correction to the nominal gradient flow through a pointwise convex quadratic program. We show that the resulting augmented safe set is forward invariant and that every trajectory initialized from the feasible set returns to it within every time window of length $τ$. We further show that, in a strict interior inactive regime, the closed-loop dynamics reduces exactly to the nominal gradient flow and recovers the corresponding local convergence behavior. Numerical examples illustrate how the recovery horizon shapes the closed-loop behavior and corroborate the theoretical analysis.

math.OC↗

arXiv2026

In-Context Learning World Models for Robot Dual-Arm Manipulation of Soft Garment with Partial Observations

Robust manipulation of soft objects, such as garments, is a critical skill for service and household robots to adopt, but remains challenging due to its high-dimensional state space, and material-dependent deformations. Humans address this challenge by using mental world models that "imagine" the shape and material properties from partial observations, which enables them to predict how actions affect future states. As such, embedding such world models in robots allows for better generalization in manipulating a wide variety of garments in the real world. However, learned world models typically require large amounts of real world data that is strenuous to collect, and a mechanism to infer latent properties that govern dynamics. We present a Soft-Object World Model that performs generative full-state estimation and action-conditioned dynamics prediction using a transformer backbone trained on large-scale simulated soft object interactions, with measures to mitigate the sim-to-real gap. By learning to infer latent shape and material cues through in-context learning over a variable-length partial point-cloud history, the model generalizes across robot embodiments, material parameters, garment types and shapes, and manipulation coordination modes without weight updates. The world model is then integrated with a Goal-Conditioned action planner for motion synthesis. We validate the approach in simulation and real world for bimanual garment folding, reporting improvements in reconstruction fidelity, prediction accuracy, and task success.

cs.RO↗

arXiv2026

What Would Removing This Corruption Change? Failure Attribution for Vision-Language-Action Models

Vision-language-action (VLA) models are sensitive to visual corruptions, but knowing that a corruption is typically harmful does not establish whether removing it would benefit the current episode. Furthermore, when several corruptions co-occur, deciding what to correct requires understanding which ones contribute to failure risk and how much their removal would help. We define this problem as failure attribution. Detecting corruption presence alone cannot answer this question, as corruptions can be present but relatively harmless, while directly measuring removal benefits requires costly paired policy rollouts with and without the corruption present. To address this, we introduce a factorized risk model that learns separate representations of the scene and corruptions, allowing us to estimate removal benefits through latent intervention from the current image and task instruction, without paired clean images or additional counterfactual rollouts. We evaluate our approach on OpenVLA and $π_{0.5}$ in simulation and $π_{0.5}$-DROID on a Franka robot. Our method outperforms monolithic and vision-language-model (VLM) baselines, including achieving approximately 3x lower attribution error than frontier VLMs. We also demonstrate our method adapts to execution context and corruption intensity, and can be used for online failure monitoring on hardware.

cs.RO↗

arXiv2026

A Step Harder, Not a Step Too Far: The Benefits and Limits of Curriculum Difficulty Progression in GRPO

Curriculum learning typically organizes training samples from easy to hard. In GRPO, medium-difficulty samples are attractive for online selection because they are more likely to yield informative group-relative learning signals, and prioritizing them can improve training efficiency. However, it remains unclear whether persistently selecting such samples also leads to the strongest final model performance, or whether training can benefit from progressing toward harder samples. Meanwhile, sample difficulty changes as the policy evolves, so fixed difficulty estimates can become misaligned with the current policy. We therefore re-estimate sample difficulty under the current policy and, inspired by the easy-to-hard principle of curriculum learning, design and evaluate a staged curriculum that progressively shifts the active difficulty band toward harder samples. Experiments on GSM8K show that persistent medium-difficulty selection does not achieve the strongest observed performance. Across three random seeds, progressing to a moderately harder difficulty band improves test accuracy to $0.6591 \pm 0.0077$, compared with $0.6449 \pm 0.0024$ for the fixed-medium curriculum. However, further progression to a harder difficulty band reduces accuracy to $0.6405 \pm 0.0053$. These results show that staged difficulty progression can outperform persistent medium-difficulty selection, but its benefit is non-monotonic. Effective GRPO curricula can therefore benefit from progressing beyond medium difficulty, while avoiding excessive progression toward overly difficult samples.}

cs.AI↗

arXiv2026

GCUL: Ambiguity Identification in Text Emotion Classification via Cluster-Guided Learning

Selective classification enables a model to abstain from predictions on uncertain instances, but existing approaches typically reject them through confidence scores, predefined coverage constraints or instance-level distance measures. These approaches may overlook the collective geometric structure of difficult samples in learned representation spaces. We propose Guided Clustering-based Uncertain Learning (GCUL), a geometric-guided selective classification framework that identifies misclassified and ambiguous instances as a potential confusion attractor in the representation space. GCUL uses a three-phase procedure to initialize, cluster, and explicitly relabel this uncertain region, allowing the rejection boundary to emerge from the underlying representation geometry rather than from a prescribed rejection rate. We further derive a selectivity score and a geometric sufficient condition that characterizes when rejection can provide positive operational utility, enabling pre-deployment feasibility assessment. GCUL improves DistilBERT accuracy from 89.37 percent to 94.98 percent with less than 9 percent rejection. Beyond accuracy, our selectivity score correctly pre-detects the only dataset (GoEmotion) where all baselines fail, and controlled simulations yield 6.1 percent Type-I and 0 percent Type-II errors, validating the sufficient condition's conservatism. These results suggest that collective representation geometry provides a useful alternative perspective for selective prediction.

stat.ML↗

arXiv2026

Beyond Point-Attached Semantics: Stable Object-Centric Semantic Fields for Robust Manipulation

Robotic manipulation often requires identifying functional parts, such as a mug handle or a hammer head. However, features attached to observed 3D points can vary with viewpoint and sensor noise, giving a policy inconsistent representations of the same part. We propose an object-centric semantic field to provide more consistent part-aware features for manipulation. We use the observed object cloud to build a continuous field, then read features from this field at 3D locations independently resampled from the cloud. Each feature uses the sampled object support as context, rather than directly reusing an individual point descriptor. Part classification distinguishes functional regions, cross-instance alignment brings corresponding part features together, and perturbation consistency encourages similar features under observation changes. The queried coordinates and features form semantic point clouds that are supplied to a DP3-based policy. We evaluate the approach on four RoboTwin simulation tasks and four real-world bimanual tasks, achieving average success rates of 69.3\% and 67.5\%, respectively. These improve on Utonia Point-wise by 7.0 and 32.5 percentage points, respectively, with real-world tests on held-out objects. A point-wise control with matched part supervision scores 63.5\% in simulation, compared with our 69.3\%. These results highlight the value of stable, object-conditioned semantic fields for manipulation across object instances and varying observations. Project Page: \href{https://zainzh.github.io/beyond-point-attached-semantics}{https://zainzh.github.io/beyond-point-attached-semantics}.

cs.RO↗

arXiv2026

ReliGRec: Reliability-Oriented LLM-Based Generative Recommendation via User-Risk-Aware Prompt Routing

User behavior in real-world recommender systems is heterogeneous. While some users exhibit coherent preferences, others show abrupt interest shifts, bursty interactions, excessive repetition, or inconsistency with collaborative neighborhoods. Such deviations may arise from benign variation or manipulation, including shilling attacks, but do not alone establish malicious intent. Existing robust recommenders exploit user-risk signals through training-time reweighting or graph aggregation, whereas adapting generation to estimated user-level weak risk remains underexplored in LLM-based generative recommendation. We propose ReliGRec (Reliability-oriented Generative Recommendation), a weakly supervised framework whose name denotes its design goal rather than a supervised reliability variable. ReliGRec derives user-level weak-risk proxy labels from review-feedback signals for a subset of users and represents sequential behavior and collaborative context using a Behavior Token and temporal Graph Tokens, respectively. A Dual-View Weak-Risk Estimator fuses the representations to produce a user-level weak-risk score that selects a Simple or Cautious Prompt at inference. The Cautious Prompt is designed to encourage attention to stable, collaboratively supported evidence while reducing overreliance on isolated, short-term, or repeated interactions. The Behavior Token affects generation through weak-risk estimation and routing, whereas the aggregated Graph Token provides collaborative context for next-item Semantic ID generation. ReliGRec thus turns weak-risk estimation from an auxiliary prediction into a generation-time control signal. Experiments report competitive recommendation and weak-risk proxy-label prediction, while routing analyses characterize the recommendation-quality and inference-cost behavior of weak-risk-guided prompting.

cs.IR↗

arXiv2026

WholeBodyWAM: Generalizing Pre-trained World-Action Priors to Humanoid Loco-Manipulation via WBC-Grounded Coordination

World Action Models (WAMs) offer a promising approach to general-purpose robot manipulation by jointly modeling visual dynamics and actions. However, most WAM studies focus on tabletop or arm-centric manipulation, while humanoid loco-manipulation remains less explored. To address this gap, we introduce WholeBodyWAM, which jointly predicts future visual dynamics, manipulation actions, and whole-body control intents for generalizable humanoid loco-manipulation. It preserves pre-trained world-action priors while grounding heterogeneous whole-body controller (WBC) semantics and coordinating whole-body behavior. Extensive experiments show that WholeBodyWAM achieves an overall simulation task success rate of 91.9%, with a 0.23 improvement in real-world out-of-distribution task progress and a 70% reduction in success-rate variance across WBCs relative to the respective baselines. These results suggest a path toward scalable humanoid whole-body intelligence by extending pre-trained world-action priors through structured WBC grounding and coordination, rather than relearning whole-body behavior from scratch. Project page: https://wholebodywam.github.io/.

cs.RO↗

arXiv2026

Reasoning Without Inference Cost: Latent Semantic Scaffolding for Robot VLA Policies

Vision-language-action (VLA) models are trained by imitation and capture what action to take but not why; adding causal reasoning improves manipulation, but current methods pay for it at inference time - generating reasoning tokens or rolling out predicted future states at every step, a cost that compounds over long horizons. We ask whether this benefit can instead be captured during training and discarded before deployment. We introduce Latent Semantic Scaffolding (LSS), an auxiliary loss applied during human-demonstration pretraining that aligns a VLA's action-token representations to text embeddings of physical-reasoning rationales through a small projection head. The head is dropped at inference, leaving the unmodified base policy with zero added cost. Our central finding concerns alignment granularity: aligning each action token to the rationale of its own manipulation phase (Dense LSS) rather than to a single pooled episode-level embedding (Pooled LSS) yields representations that transfer markedly better to held-out tasks. Dense LSS attains both the best in-distribution success and the best transfer to tasks unseen during alignment, whereas pooled alignment over-specializes to the training task. A representational probe shows Dense LSS induces roughly twice the per-phase separability in the backbone, supporting that phase-local alignment is the operative mechanism.

cs.RO↗

arXiv2026

Order-Adaptive Distributed Integral Control

We address a structural tradeoff in distributed dynamic coordination: when the target complexity is unknown, a low controller order saves states but may leave a persistent tracking error, whereas a high order improves tracking but may burden every agent with unnecessary dynamics. To remove this choice without resorting to computationally more involved nonlinear feedback or chattering-prone nonsmooth feedback, we develop an order-adaptive distributed integral controller (OADIC). Specifically, we start with proportional feedback and add integral states only when locally measurable relative errors show that the current order is inadequate. Meanwhile, we organize the candidate controllers in a nested form, thereby preserving the existing states and gains and maintaining continuous control inputs during order transitions. To provide a theoretical basis for this design, we first characterize the consistency of prescribed relative displacements on the augmented agent--target graph. Next, we construct gains that stabilize all admissible fixed-order subsystems and establish a uniform input-to-state stability bound for the variable-dimension closed loop. Furthermore, we prove that OADIC rejects every insufficient order after finitely many decision intervals and explicitly bound the rejection time of the critical order.

eess.SY↗

arXiv2026

Auditable agentic AI for evidence-grounded thyroid ultrasound diagnosis and reporting

Thyroid ultrasound diagnosis requires coordinated lesion localization, measurement, risk stratification and reporting, yet most AI systems address these tasks in isolation and provide limited support for clinical review. We present ThyroidXAgent, a clinician-interactive agentic AI system that coordinates specialized diagnostic tools and stores their outputs as an auditable case-level evidence record. The system was developed using OpenThyroidDB, a multicentre, multitask resource integrating approximately 0.3 million ultrasound images and 24,000 paired reports, and was evaluated on 28,458 non-overlapping test cases, including 8,721 cases from 35 centres in the private NHC-MISD-TUS cohort. Across heterogeneous datasets, ThyroidXAgent achieved a mean Dice score of 87.21 percent for nodule segmentation and a mean AUROC of 0.9466 for benign-malignant classification. The same workflow supported lymph-node metastasis prediction and follicular versus papillary thyroid carcinoma classification, with AUROCs of 0.864 and 0.805, respectively. For report generation, evidence-grounded assembly outperformed multimodal language-model baselines across three cohorts. ThyClinScore, a lesion-level clinical semantic metric introduced here, showed the strongest correlation with a location-aware language-model judge. ThyroidXAgent improved physician classification accuracy, increased report diagnostic consistency from 70.3 percent to 86.2 percent, and reduced segmentation and reporting time by 35.9 percent and 27.4 percent, respectively. These findings support auditable, clinician-correctable agentic AI for thyroid ultrasound diagnosis and reporting.

cs.AI↗

arXiv2026

SGAD: A State-Guided Adaptive Decision Framework for Robust EEG-Based Auditory Attention Switch Decoding

Achieving robust EEG-based auditory attention switch decoding (AASD) is crucial for intelligent hearing aids. However, its application is limited as EEG non-stationarity complicates sequential decision-making, and insufficient control of potential confounding factors may overestimate performance. Therefore, we propose a state-guided adaptive decision (SGAD) framework that infers attention transition states via causal state detection and dynamically modulates temporal smoothing through state-guided adaptive gating. We further introduce six hierarchical evaluation protocols to assess generalization across audio, speaker, and subject dimensions. Experimental results show that SGAD improves decoding accuracy and stability while maintaining low response latency across evaluation scenarios. Performance variations across protocols further suggest data partition-related biases. Together, these findings advance robust AASD for neuro-steered hearing applications.

eess.SP↗

arXiv2026

SAGE: Switch-Aware EEG-Guided Soft Gating for Target Speaker Extraction with In-Trial Switching

EEG-guided target speaker extraction is challenging under in-trial auditory attention switching, where neural noise and intrinsic latency can delay or destabilize attention tracking. Conventional methods struggle with dynamic switches and often cause discontinuities at switching points. Therefore, we propose SAGE, a switch-aware EEG-guided soft gating framework that treats in-trial switching as dynamic selection. SAGE generates two candidate speech streams with a robust separator and uses an EEG-guided switch-aware gating module to produce smooth fusion weights and suppress transition artifacts. We further integrate latency-compensated alignment and an uncertainty-driven conservative strategy to handle latency discrepancies and fluctuating EEG reliability. SAGE outperforms baselines, achieving 8.67 dB SI-SDR and 88.24% STOI while reducing average switching latency to 2.04 s. By coupling neural decoding with speech separation, it enables robust target extraction in dynamic scenarios.

eess.SP↗

arXiv2026

LeAP: Learnable Adaptive Permutation for Feature Selection in Heterogeneous and Sparse Recommender Systems

Modern industrial recommender systems rely on thousands of heterogeneous features -- ranging from low-dimensional scalars (e.g., statistical value) to high-dimensional embeddings (e.g., user-id embeddings, MLP representations) -- to achieve high-precision predictions. Given the immense computational costs associated with training, efficient feature selection is critical. However, existing methods encounter three primary bottlenecks: (1) they typically assume uniform feature dimensions or require costly mapping to a fixed size; (2) they struggle with extreme sparsity, where the majority of features (e.g., 99%+) remain at default values; and (3) traditional permutation-based approaches are computationally prohibitive in large-scale settings. To address these challenges, we propose LeAP (Learnable Adaptive Permutation), a novel, model-agnostic plug-in module for feature selection. LeAP transforms the inefficient random permutation process into a learnable mechanism, significantly accelerating the evaluation of feature importance. In addition, we introduce an adaptive regularization strategy tailored for heterogeneous dimensions and extreme sparsity, enabling superior feature importance ranking results across asymmetric input spaces. Experiments on four public recommendation datasets demonstrate that LeAP achieves state-of-the-art performance. Furthermore, LeAP has been deployed in a large-scale industrial search ranking model with over a billion daily requests and a 2TB model parameter scale. In this real-world scenario involving 12,000+ total feature dimensions, LeAP successfully identified and removed over 3,600 redundant dimensions without performance degradation, which is 2 to 10 times the ability of compared baseline methods.

cs.LG↗

arXiv2026

Observation of the Inherent Chiral Smith-Purcell Effect via Symmetry Breaking

The Smith-Purcell effect arises when charged particles move near a periodic structure, emitting radiation. Conventional approaches for generating chiral Smith-Purcell radiation rely on metasurface phase engineering or resonant mode interference, typically producing narrow-band, weakly chiral emission. Here, we introduce a resonance-interference-free mechanism that leverages the properties of the charged particles themselves. Using a non-chiral, non-resonant silicon grating, we demonstrate broadband, tunable Smith-Purcell radiation with high chirality, achieving a record-high degree of polarization of 0.87. This is enabled by converting the transverse spin angular momentum of electron-induced evanescent waves into a longitudinal form, producing opposite chirality at different azimuthal angles. Beam twisting or displacement offers precise control over chirality, paving the way for compact chiral light sources, advanced X-ray imaging, and integrated particle diagnostics platforms.

physics.optics↗

arXiv2026

Decoding Speech Envelopes from Electroencephalogram with a Contrastive Pearson Correlation Coefficient Loss

Recent advances in reconstructing speech envelopes from Electroencephalogram (EEG) signals have enabled continuous auditory attention decoding (AAD) in multi-speaker environments. Most Deep Neural Network (DNN)-based envelope reconstruction models are trained to maximize the Pearson correlation coefficients (PCC) between the attended envelope and the reconstructed envelope (attended PCC). While the difference between the attended PCC and the unattended PCC plays an essential role in auditory attention decoding, existing methods often focus on maximizing the attended PCC. We therefore propose a contrastive PCC loss which represents the difference between the attended PCC and the unattended PCC. The proposed approach is evaluated on three public EEG AAD datasets using four DNN architectures. Across many settings, the proposed objective improves envelope separability and AAD accuracy, while also revealing dataset- and architecture-dependent failure cases.

eess.AS↗