Searcharxiv⌕ Search

arXiv subjects

Jie Lu

Publications and source records attributed to Jie Lu.

At least 19 recordsLinked to original sources
arXiv2026

Evidence-Aligned Entity Verification for Hallucination Detection in Retrieval-Augmented Generation

Hallucination detection is crucial for large language models (LLMs), as hallucinated content creates significant barriers in applications requiring factual accuracy. Current detection methods mainly depend on internal signals like uncertainty and self-consistency checks, using the model's pre-trained knowledge to identify unreliable outputs. However, pre-trained knowledge may become outdated and has coverage limitations, especially for specialized or recent information. To address these limitations, retrieval-augmented generation (RAG) has emerged as a promising solution by retrieving relevant evidence at inference time, grounding outputs beyond the model's parametric knowledge. In this paper, we target a critical and practical learning problem RAG-based hallucination detection (RHD), where RAG is employed to enhance hallucination detection by addressing information updating challenges. To address RHD, we propose a novel method Evidence-Aligned Entity Verification (EAEV), which detects entity-level hallucinations by leveraging RAG to align generated entities with retrieved evidence contexts. Specifically, EAEV evaluates entity-evidence alignment through three complementary dimensions and introduces counterfactual stability analysis to ensure robust alignments under evidence perturbations. Experiments across multiple RAG benchmarks demonstrate that EAEV achieves consistent improvements over existing methods with strong generalization capabilities.

cs.AI↗
arXiv2026

Generalizable 6D Pose Estimation of Textureless Objects with Planar-based Gaussian Splatting

Estimating the 6D pose of textureless objects without prior CAD models remains a critical challenge due to the lack of appearance features. While recent generalizable approaches alleviate the dependence on object-specific models, their performance on low-texture objects is often limited by insufficient geometric constraints in the underlying representations. In this work, we propose PG-Pose, a geometry-aware framework combining Planar-based Gaussian Splatting (PGS) reconstruction and Geometry-driven pose optimization. In the offline representation extraction stage, three distinct representations of the object are extracted from multi-view reference RGB images with known poses. PG-Pose reconstructs a 3D Gaussian representation and renders high-fidelity depth maps to generate 3D point clouds through back projection. In the online pose inference stage, the initial pose of the input image is estimated by 2D-3D correspondence matching between the input image and the reconstructed 3D point clouds, followed by a PGS-Refiner for iterative pose optimization. Evaluations on the OnePose-LowTexture datasets, PG-Pose achieves an average accuracy of 94.2% ADD(S)@0.1d, with a 2.1% improvement average accuracy compared with the state-of-the-art (SOTA) GS-based approach. To further demonstrate the effectiveness of PG-Pose for industrial robots in grasping tasks, we deploy it on a dual-arm industrial robot and successfully realize the grasping task on an unseen object.

cs.RO↗
arXiv2026

Analysis of the two-body strong decays of the hidden-charm pentaquark states in QCD sum rules

In the present work, we study the two-body strong decays of the hidden-charm pentaquark states with the quark content $uudc\bar c$ and the quantum numbers $I(J^P)=\frac{1}{2}(\frac{1}{2}^-)$ in the framework of the three-point QCD sum rules. The initial pentaquark states are described by four local diquark-diquark-antiquark type interpolating currents with definite isospin. We construct the three-point correlation functions for the decay channels $P_c\to \eta_c p$, $J/\psi p$, $\Lambda_c\bar D$, $\Lambda_c\bar D^{*}$ and $\Sigma_c\bar D$, and derive the corresponding QCD sum rules for the strong coupling constants. At the hadron side, the correlation functions are expressed in terms of the hadron masses, pole residues, decay constants and strong coupling constants. At the QCD side, they are calculated by carrying out the operator product expansion with the full quark propagators, where the vacuum condensates up to dimension 10 are taken into account. After matching the two representations and performing the double Borel transformations, we extract the strong coupling constants from the selected Lorentz structures. With the obtained coupling constants, we evaluate the partial decay widths and discuss the possible assignments of the corresponding pentaquark states. The numerical results indicate that two of the compact hidden-charm pentaquark states can be related to the $P_c(4312)$ and $P_c(4457)$, respectively, while the other two lower-mass states may be regarded as possible hidden-charm pentaquark candidates to be searched for in future experiments. The present results may be useful for identifying the hidden-charm pentaquark states in future experiments.

hep-ph↗
arXiv2026

Agent-Enhanced Heterogeneous Graph RAG for Academic Question Answering

Academic question answering requires reasoning over heterogeneous scholarly graphs, where queries range from simple attribute lookups to multi-hop inference across author--paper--venue structures. Existing retrieval-augmented generation (RAG) systems struggle in this setting due to three limitations: (1) fixed retrieval strategies that do not adapt to varying query complexity, (2) the absence of sufficiency evaluation leading to incomplete or misaligned evidence, and (3) a lack of structured verification against graph facts. To address these issues, we propose an agentic heterogeneous graph RAG method that transforms the three core stages of the RAG pipeline into explicit agentic decision steps. A query-aware retrieval agent analyzes query type and selects an appropriate graph traversal strategy; a sufficiency-aware reranking agent assesses evidence completeness and adaptively expands the retrieved subgraph; and a graph-grounded verification agent checks entity, relation, and attribute correctness before finalizing the answer. Experiments on heterogeneous graphs constructed from OpenAlex and DBLP suggest that our method consistently outperforms strong LLM, graph-augmented RAG, and agent-based baselines.

cs.SI↗
arXiv2026

FreKoo++: Learning Continuous Spectral Dynamics for Temporal Domain Generalization

Temporal Domain Generalization (TDG) aims to learn from historical domains and generalize to unseen future distributions under concept drift. Nevertheless, prevailing TDG methods struggle with complex real-world streaming scenarios involving both multi-scale drift patterns (e.g., long-term periodicity intertwined with short-term incremental changes) and local uncertainties, especially in continuous settings where observations arrive irregularly. To address this limitation, we propose FreKoo++, a novel continuous spectral-dynamical framework that pioneers the unification of continuous Koopman modal dynamics with adaptive spectral disentanglement. Specifically, FreKoo++ maps source-domain parameters into a compact latent space, modeling their evolution as a superposition of learnable continuous modes where complex eigenvalues jointly encode oscillatory frequency and temporal growth or decay. This formulation naturally accommodates irregular timestamps and supports arbitrary horizon extrapolation without rigid discrete stepping. Furthermore, we propose a new adaptive soft spectral weighting mechanism backed by stability and spectral regularization, which automatically isolates persistent dominant dynamics from transient noise without relying on manual frequency thresholds. We derive modal approximation and generalization bounds that characterize how amplitude and eigenvalue estimation errors propagate with the prediction horizon. Extensive experiments on both discrete and continuous TDG benchmarks demonstrate that FreKoo++ achieves state-of-the-art performance under complex multi-scale drifts and irregular sampling.

cs.LG↗
arXiv2026

Deep Reinforcement Learning for 6G AI-RAN: A Comprehensive Survey

The evolution toward sixth-generation (6G) networks is transforming the radio access network (RAN) into a programmable and intelligent control platform that must continuously adapt to heterogeneous services, dynamic environments, and competing performance objectives. Open Radio Access Network (O-RAN) provides the open interfaces, disaggregated architecture, and multi-timescale control loops needed to support this transformation, while deep reinforcement learning (DRL) offers a natural framework for optimizing sequential decisions under uncertainty. However, existing surveys either address artificial intelligence (AI) and machine learning (ML) in O-RAN broadly or focus on isolated DRL use cases, leaving a gap in the systematic connection between DRL methodology, O-RAN architecture, and operational deployment. To the best of our knowledge, this article presents the first dedicated and comprehensive survey of DRL for Open AI-RAN. We review the foundations of model-free, model-based, offline, safe, multi-agent, federated, and transfer learning, and provide an O-RAN-aware framework for formulating RAN control problems through states, observations, actions, rewards, constraints, and temporal structure. We classify DRL applications across radio resource management, mobility management, interference control, traffic steering, energy efficiency, network slicing, integrated sensing and communication, security, and massive MIMO. We further examine multi-agent and federated coordination, foundation models and agentic AI, trustworthy DRL, sim-to-real transfer, continual adaptation, resource-efficient inference, and reinforcement learning operations. Finally, we review experimental platforms, benchmarks, standards, and industry activities, and identify research directions toward sample-efficient, safe, scalable, interoperable, and deployable DRL control for 6G Open AI-RAN.

cs.NI↗
arXiv2026

Spin Splitter without Spin-Split Bands: A Reconfigurable Altermagnetic Texture

The altermagnetic spin-splitter effect converts an electric field into a transverse pure spin current, with no net magnetization and no charge-Hall counterpart. In established materials this function is tied to crystal-fixed spin-split bands that lock the polarization axis to the lattice. We show that the noncoplanar counter-spiral ground state of a frustrated honeycomb magnet instead carries the altermagnetic operation through a $\mathbf Q$-locked helicity mirror $g$. The mirror selects the spin-current polarization and forbids the perpendicular one, while an antitranslation $\Theta$ forbids even-parity spin splitting. Band splitting and spin-splitter response therefore rest on different symmetry elements. Either element alone enforces the charge-Hall zero---a redundancy absent from other spin--orbit-free noncollinear routes---and a charge Hall appears only when both elements are removed. Hole doping then realizes a \emph{spin splitter without spin-split bands}---the symmetry-allowed odd-parity residual below $2\times10^{-7}$ of the hopping $t$ at the Fermi level---with $\sigma_H^{(s_y)}=0.082\,e^2/h$ without spin--orbit coupling and with zero charge Hall response. Selecting among the three degenerate $\mathbf{Q}$ orientations rotates the polarization axis in exact $120^\circ$ steps at fixed magnitude and charge-Hall zero; the selection rules persist in a $32$-site cell accessible to programmable photonic and circuit lattices.

cond-mat.str-el↗
arXiv2026

GAUGE: Granularity-Adaptive Counterfactual Gating of Evidence for Incomplete Multimodal Classification

Multimodal classification typically assumes all modalities are available, yet real-world inputs are often incomplete. Imputation and dynamic fusion can mitigate such incompleteness, but existing methods operate at a coarse modality level and thus cannot retain reliable components while suppressing misleading ones within the same recovered modality, compromising prediction reliability. To address this issue, we propose GAUGE, a lightweight counterfactual gating framework for incomplete multimodal classification. GAUGE first imputes missing modalities with a frozen imputer and encodes observed and recovered inputs uniformly as fine-grained evidence units. Rather than intervening on each unit explicitly, GAUGE scores the counterfactual effect of replacing every unit with a reference representation through prediction-aware Taylor evidence scores, all obtained in a single forward-backward pass. These scores are mapped to continuous gates, which are converted into additive attention-logit biases for unit-wise evidence modulation without altering the backbone architecture. Experiments across six benchmarks demonstrate that GAUGE outperforms strong baselines across diverse incomplete-input settings. Furthermore, a Taylor remainder theoretical analysis characterizes the error of the first-order approximation relative to the exact counterfactual effect, establishing GAUGE as a principled and scalable framework for fine-grained evidence control under modality incompleteness.

cs.LG↗
arXiv2026

The semileptonic decays of $\mathcal{B}_{Q_{1}Q_{2}}(\frac{1}{2}^{+})\rightarrow\mathcal{B}_{Q_{1}}^{*}(\frac{3}{2}^{+})$ in QCD sum rules

In the framework of QCD sum rules, we systematically analyze the weak transition process $\mathcal{B}_{Q_{1}Q_{2}}(\frac{1}{2}^{+})\rightarrow\mathcal{B}_{Q_{1}}^{*}(\frac{3}{2}^{+})$. When doing the operator product expansion in the QCD side, we consider the contributions of perturbative part and vacuum condensate terms up to dimension 6. In the phenomenological side, we eliminate the interferences of the low spin states and negative parity states by employing 16 different dirac structures. As an application, these form factors are finally used to analyze the semileptonic decays of $\mathcal{B}_{Q_{1}Q_{2}}(\frac{1}{2}^{+})\rightarrow\mathcal{B}_{Q_{1}}^{*}(\frac{3}{2}^{+})l\nu$, where these decays are driven by the transition processes $c\rightarrow d/s+l^{+}+\nu_{l}$ and $b\rightarrow u+l^{-}+\overline{\nu}_{l}$. The predicted physical quantities include not only the partial widths, ratios of $\Gamma_{L}/\Gamma_{T}$ and the branching fractions, but also some observables such as the forward-backward asymmetry parameter $A_{FB}^{l}$ of lepton, the $P_z^{F}$ component of the polarization vector for daughter baryon and the longitudinal polarization of the lepton $P_z^{l}$. We hope all of these theoretical predictions about the weak decays will be helpful for studying the properties of doubly heavy baryons in experiments in the future.

hep-ph↗
arXiv2026

AC-VLA: Robust Out-of-Distribution Action Execution via Compositional Learning

Vision-Language-Action (VLA) models excel at end-to-end robotic manipulation but struggle with out-of-distribution (OOD) generalization when familiar sub-tasks are recombined in unseen configurations. We identify two mutually reinforcing failure modes: \emph{trajectory overfitting}, where models overfit to holistic trajectory patterns rather than compositional sub-skill semantics; and \emph{perceptual shortcut}, where action tokens over-rely on wrist-view textures at the expense of global spatial grounding. To address both, we introduce \textbf{AC-VLA}, a plug-and-play Action Compositional learning framework comprising two architecture-agnostic components: \textbf{(i)} a compositional learning module that uses an LLM-driven instruction decomposer and a proprioceptive trajectory aligner to generate dense sub-task supervision, followed by mixed training on complete demonstrations and decomposed data to endow the model with compositional generalization; and \textbf{(ii)} a state-conditioned asymmetric masking strategy that suppresses wrist-view inputs during closed-gripper phases, enforcing global semantic grounding. All components are architectural modification-free and directly integrable into any VLA backbone. Instantiated on $\pi_{0.5}$ and evaluated on LIBERO and LIBERO-OOD benchmarks, AC-VLA achieves a ~28% absolute improvement on compositional OOD tasks while maintaining near-perfect in-distribution performance.

cs.RO↗
arXiv2026

Beyond-adiabatic flat Chern bands from a double-helix skyrmion crystal

A central challenge in flat-band engineering is suppressing kinetic energy without sacrificing Berry curvature. We show that a double-helix skyrmion crystal (DHSKX)--two sublattice-resolved skyrmion textures locked at opposite helicities, obtained here as the classical ground state of a frustrated honeycomb spin model--provides such a route under double exchange. The key mechanism is a single real-space organization, phase clustering: the $\pi$-locked helicities expel the wave function's phase winding from the skyrmion cores, and the magnetic $C_3$ symmetry pins it into three phase-locked clusters whose distributed destructive interference cancels net transport while preserving the Berry curvature. Ordinary skyrmion crystals, even with the same symmetry, do not develop this organization. Phase clustering yields isolated flat $|C| = 1$ Chern bands over broad coupling windows, one of which surpasses the adiabatic reference in quantum geometry at intermediate coupling. In this beyond-adiabatic window, band-projected exact diagonalization gives finite-size evidence consistent with $\nu = 1/3$ Laughlin-type fractional-Chern-insulator physics; the same texture also hosts a higher-Chern ($C = -2$) flat band. Built from site-resolved complex hoppings alone, the DHSKX architecture is directly programmable in topolectric, acoustic, and photonic platforms.

cond-mat.str-el↗
arXiv2026

Dimension Reduction for Curves: Simplified and Generalized

We revisit random projections for reducing the dimension of high-dimensional polygonal curves. Drawing from the toolbox of randomized linear algebra, we give a considerably simplified proof of the known $O(\varepsilon^{-2}\log(nm))$ bound on the target dimension of a random projection that preserves the continuous Fr\'echet distance of polygonal curves up to a factor $(1\pm\varepsilon)$. Our proof is based on the concept of sparse oblivious subspace embeddings. While previous techniques were limited to the case of the Fr\'echet distance, our techniques are fairly general and extend to all possible distance measures that involve the maximum, a sum or an integral over Euclidean distances between pairs of points on both input curves. We define a generalized dissimilarity measure for curves that includes several popular measures such as Fr\'echet, $q$-DTW, Hausdorff, etc. as special cases and show that the same dimension reduction technique works for this generalized dissimilarity measure. Finally, we apply the same framework for dimension reduction to piecewise linear surfaces, after extending the distance measure suitably to such surfaces.

cs.DS↗
arXiv2026

Unleashing More Actions via Action Compositional Training for VLA Models

Vision-Language-Action models excel at robotic manipulation, driven by the scale and diversity of demonstration data. However, standard training paradigms often cause VLA models to severely overfit to specific behavioral patterns, rendering them unable to generalize to out-of-distribution scenarios even when those scenarios merely require novel combinations of identical sub-skills. While expanding datasets can mitigate this overfitting, acquiring high-quality robot data remains notoriously labor-intensive and cost-prohibitive. To resolve this impasse without expensive human teleoperation and to truly unleash more actions,i.e., enable VLA models to compose known sub-skills into a much broader set of executable behaviors beyond the original demonstrations-we propose ACT-VLA (Action Compositional Training for VLA Models), an offline data augmentation framework that leverages the model's latent task representations to synthesize novel, physically valid demonstrations directly from existing tasks for policy training. By eliminating additional manual data collection, our method automatically expands the training distribution and mitigates overfitting. We evaluate our approach on challenging manipulation tasks in simulation. Experiments demonstrate that while baseline VLA models generalize poorly due to original distribution overfitting, policies trained with our synthesized data achieve substantially higher success rates, validating that leveraging existing tasks for automated demonstration synthesis provides an effective, scalable, and data-efficient route to broadening VLA generalization.

cs.RO↗
arXiv2026

Field-selected seven-site topological magnons in a classical frustrated triangular-lattice K-$\Gamma$-$\Gamma'$ magnet

Defining magnon topology in strongly frustrated magnets is often hindered by the absence of a simple harmonic magnon vacuum at zero field. Within a classical-spin ground-state search followed by linear spin-wave theory (LSWT), we demonstrate that a representative triangular-lattice K-Gamma-Gamma' model in a dominant-Gamma exchange regime has an in-plane-field-selected compact, noncoplanar seven-site order. This field-selected state provides a controlled classical reference state and hosts magnon bands with field-tunable Chern numbers. Increasing the field drives a Dirac-like band touching that transfers Berry curvature between the fifth and sixth bands, altering the Chern vector from (0, 1, 0, -2, 1, 0, 0) to (0, 1, 0, -2, -1, 2, 0). This topological transition reorganizes the band-resolved thermal Hall conductivity, driving the total $\kappa_{xy}(T)$ through a near-zero crossing once the upper bands are thermally populated. The dynamical structure factor places roughly half of the coherent spectral weight on the Chern-active branches, offering a spectroscopic route to identify the topological branches. These results define a controlled semiclassical benchmark for magnon topology in this pure nearest-neighbor exchange model.

cond-mat.str-el↗
arXiv2026

When Recommendation Denoising Meets Popularity Bias: Understanding and Mitigating Their Interaction

Implicit feedback is the dominant data source for recommender systems, but behavioral logs are often contaminated by false-positive interactions caused by mis-clicks, biased exposure, and interface effects. Denoising recommendation methods improve robustness by down-weighting or filtering interactions suspected to be noisy, often relying on the small-loss heuristic. We revisit this heuristic through the lens of popularity bias. Tail-item positives can be harder to fit because they are sparsely observed, and thus may receive larger losses even when they reflect genuine user preference. Under such popularity-dependent loss patterns, monotone loss-based reweighting can suppress clean-but-hard tail signals and increase the head-tail imbalance in effective supervision. We formalize this interaction through the effective head-tail signal ratio induced by denoising weights and derive a conditional reallocation result: when the loss distribution of tail positives is right-shifted relative to that of head positives, small-loss reweighting increases the effective head-tail signal ratio compared with ERM. Motivated by this analysis, we propose Popularity-Aware Denoising (PAD), a lightweight plug-in framework that modulates denoising strength by item popularity. PAD applies stronger denoising to highly exposed items while being more conservative on tail items, preserving more clean-but-hard long-tail signals. Experiments on three datasets and three backbones show that PAD generally improves over representative denoising baselines and provides favorable accuracy-diversity tradeoffs, especially on MF-style recommenders.

cs.IR↗
arXiv2026

UniLab: A Heterogeneous Architecture for Robot RL Beyond GPU-Dominant Paradigms

Simulation-based RL for contemporary robot control is increasingly organized around GPU-resident simulation: physics, rollout collection, and learning are placed on a single GPU-centric execution path. This paradigm has greatly improved training speed, but it has also encouraged a default assumption that efficient training requires physics to reside on the GPU. We revisit this assumption. Our view is that, in simulation-dominated robot control, the essential question is not which processor runs physics, but whether simulation throughput, policy learning, and runtime synchronization form an efficient end-to-end loop. We present UniLab, a heterogeneous CPU-simulation / GPU-learning architecture that decouples CPU-parallel simulation from GPU policy updates through a unified runtime for data movement, buffering, and synchronization. UniLab is implemented as a complete and extensible training system using MuJoCoUni and MotrixSim CPU-batched physics backends, supporting PPO, FastSAC, FlashSAC, and APPO. On representative simulation-based robot control tasks, UniLab improves end-to-end training efficiency by 3--10$\times$ under the same hardware configuration, while reducing dependence on the NVIDIA CUDA-based software stack and supporting cross-platform execution on the Apple macOS platform and the AMD ROCm and Intel XPU accelerator backends. These results show that GPU simulation is an effective path to efficient training, but not a necessary one, broadening the practical system choices available for robot RL training. Project page: https://unilabsim.github.io.

cs.RO↗
arXiv2026

Respecting Modality Gap in Post-hoc Out-of-distribution Detection with Pre-trained Vision-Language Models

Out-of-distribution (OOD) detection has emerged as a popular technique to enhance the reliability of machine learning models by identifying unexpected inputs from unknown classes. Recent progress in pre-trained vision-language models (VLMs) has enabled zero-shot OOD detection without access to in-distribution (ID) training data; in this setting, existing methods commonly treat text embeddings of class names as class prototypes. In this paper, we challenge the widely adopted text-as-prototype paradigm by theoretically showing that off-the-shelf textual prototypes are generally misaligned with the optimal visual prototypes, yielding an intrinsic modality gap that cannot be eliminated by prompt engineering alone. To mitigate this gap under the post-hoc constraint, this paper presents an online pseudo-supervised framework that directly learns class prototypes in the visual feature space using unlabeled test-time data streams and soft predictions from the pre-trained VLMs. We provide theoretical guarantees for the convergence of the online optimization procedure. Extensive experiments empirically demonstrate that our method achieves a new state of the art across a variety of OOD detection setups.

cs.CV↗
arXiv2026

Debiased Negative Mining Improves Out-of-distribution Detection with Pre-trained Vision-Language Models

Aiming at identifying unexpected inputs from unknown classes, out-of-distribution (OOD) detection has emerged as a pivotal approach to enhancing the reliability of machine learning models. This paper focuses on the burgeoning paradigm of post-hoc OOD detection with pre-trained vision-language models (VLMs), where a popular pipeline is to detect OOD inputs by examining their affinities between ID labels and negative labels, i.e., those semantically different from ID labels. Due to the unavailability of target OOD labels, existing works predominantly rely on heuristic rules to mine negative labels from unlabeled wild corpus data. Despite the empirical success, we argue that the power of VLM-based OOD detection has yet to be fully unleashed since the notorious false negative problem is far from addressed in the literature. With this motivation, we are interested in addressing the challenge of mining true negative labels for OOD scoring. To this end, we develop a theoretical framework for correcting the sampling bias of negatives labels by indirectly approximating the distribution of negative labels. Perhaps surprisingly, we show that the debiased negative mining can be naturally converted into Monte-Carlo sampling based on ID labels and the unlabeled wild corpus data. Extensive experiments empirically manifest that our method establishes a new state-of-the-art in a variety of OOD detection setups. Code is publicly available at \href{https://github.com/60pen9/Debiased-Negative-Mining-Improves-OOD-Detection-with-Pre-trained-VLMs}{\textcolor{red}{here}}.

cs.LG↗