Search arXiv⌕ Search

arXiv subjects

Nan Li

Publications and source records attributed to Nan Li.

At least 19 recordsLinked to original sources
arXiv2026

SpeakerTurn: Target-Speaker Semantic Turn Detection in Multi-Speaker Environments

Semantic completeness alone cannot determine when an assistant should respond in a multi-speaker environment: a completed utterance may belong to an interfering speaker, while the designated user is still speaking, acknowledging, or requesting time. We therefore study semantic turn inference conditioned on speaker identity. We propose SpeakerTurn, a framework that jointly predicts the target transcript and turn state from a speech mixture and an independent target-speaker reference. Built on CocktailASR-1, it links semantic decisions to the corresponding target content through joint supervision, distinguishing complete, incomplete, backchannel, wait, and target-absent states, with a separate interruption task. We also examine whether structured chain-of-thought (CoT) supervision improves decisions by representing speaker presence and semantic cues. On a synthetic multi-speaker test set, SpeakerTurn achieves five-state macro F1 of 0.811 and target-transcription character error rate (CER) of 4.20%, correctly resolving all ten reference-swapped interruption pairs. Joint-format transcription and native-interface recognition nevertheless behave differently, and CoT improves validation transcription without improving turn macro F1. These results show why target attribution, semantic turn discrimination, and recognition retention require separate assessment when adapting speech language models for speaker-conditioned interaction.

eess.AS↗
arXiv2026

HC-AINet: An Auditory-Inspired Network with Harmonic Compensation for Low-Complexity Speech Enhancement

Speech enhancement on resource-constrained devices requires noise suppression with limited computation and minimal loss of spectral detail. Auditory-inspired subband processing reduces computation, but its smooth gains have limited ability to distinguish harmonic peaks from neighboring noise. We propose a harmonic-compensated auditory-inspired network (HC-AINet) for low-complexity speech enhancement. A triangular equivalent rectangular bandwidth (ERB) filterbank supplies compact features to a lightweight network comprising inverted-residual units, temporal Conformer layers, and parallel frequency-gated convolutions. The network predicts global and harmonic gains together with fusion weights. A harmonic-location map derived from the noisy spectrum confines the harmonic contribution to selected bins on the original frequency grid, while the global branch controls the broader spectral envelope. The compensated magnitude, noisy phase, and a magnitude-derived minimum-phase cue jointly condition a compact phase estimator for waveform reconstruction. On VoiceBank-DEMAND, the 64-band model achieves a PESQ of 3.20 and a STOI of 0.95 with approximately 0.27 million parameters.

eess.AS↗
arXiv2026

BitFlat: Error-Localized Bitstream Design for Robust Diffusion Image Compression

Zero-shot diffusion image compression based on reverse channel coding achieves high perceptual quality at low bitrates without retraining, yet its bitstream remains vulnerable to bit flips. Prior work has shown that a joint combinatorial representation can amplify a single bit flip into substitutions of multiple atoms and that indexing each atom independently confines this error propagation. However, independent indexing reduces the number of atoms that fit within the bit budget and gives the decoder no indication of which atoms are corrupted. To address these issues, we propose BitFlat, a training-free error-localizing bitstream framework with two components. Blockwise Locality Alignment (BLA) decomposes the globally coupled atom selection at each diffusion step into independent selection units, each describing one signed atom from a dedicated codebook with a fixed-width field, so that any bit error affects only the unit in which it occurs. Reliability-Aware Diffusion Control (RADC) uses the bits saved by BLA to impose structured valid-codeword constraints within each field and converts the decoding state of each field into a binary reliability gate, which turns detected corrupted atoms into erasures at known positions and excludes them from noise synthesis. BitFlat requires neither target residuals nor additional network forward passes and leaves the diffusion model unchanged. Experiments on Kodak, DIV2K, and CLIC2020 show that BitFlat outperforms conventional, learned, and diffusion-based codecs at bit error rates from $10^{-4}$ to $10^{-2}$ and, even with $26.7\%$ fewer bits, surpasses Robust Turbo-DDCM.

cs.AI↗
arXiv2026

A Wireless World Model for AI-Native 6G Networks

Integrating AI into the physical layer is a cornerstone of 6G networks. However, current data-driven approaches struggle to generalize across dynamic environments because they lack an intrinsic understanding of electromagnetic wave propagation. We introduce the Wireless World Model (WWM), a multi-modal foundation framework predicting the spatiotemporal evolution of wireless channels by internalizing the causal relationship between 3D geometry and signal dynamics. Pre-trained on a massive ray-traced multi-modal dataset, WWM overcomes the data authenticity gap, further validated under real-world measurement data. Using a joint-embedding predictive architecture with a multi-modal mixture-of-experts Transformer, WWM fuses channel state information, 3D point clouds, and user trajectories into a unified representation. Across the five key downstream tasks supported by WWM, it achieves remarkable performance in seen environments, unseen generalization scenarios, and real-world measurements, consistently outperforming SOTA uni-modal foundation models and task-specific models. This paves the way for physics-aware 6G intelligence that adapts to the physical world.

cs.NI↗
arXiv2026

RPCA: a Resolved PSF reconstruction method for undersampled images

The Point-Spread Function (PSF) is a critical component in various astrophysical research areas, including galaxy morphology, photometric redshift determination, and weak lensing studies. As the next generation of space telescopes prepares for operations, including the China Space Station Telescope (CSST), accurate PSF modeling has become increasingly important. However, accurately modeling the PSF remains challenging, particularly for poorly sampled images. To construct reliable PSF models based on star images, we aim to develop a novel and robust method, which accounts for the pixel integration effect in modeling for reconstructing high-resolution PSFs from undersampled or poorly resolved images. In this paper, we present Resolved Principal Components Analysis (RPCA), a novel approach that accounts for pixel integration effects to enable the direct reconstruction of resolved PSFs from undersampled images via an Expectation-Maximization PCA (EMPCA) technique. Our method has been tested on a simulated PSF dataset for the China Space Station Telescope (CSST), where both observational and detector-induced effects were considered during simulation. The results demonstrate that RPCA achieves superior precision in PSF shape parameters compared to existing methods such as Multi-CCD (MCCD), Resolved Components Analysis (RCA), and PSFEx. Notably, RPCA {could reduce the bias of $ΔR^2/R^2$ by approximately one order of magnitude with respect to MCCD, RCA and PSFEx. RPCA exhibits robust stability under realistic observational conditions, including varying signal-to-noise ratios (SNRs) and contamination from cosmic rays and bad pixels. This suggests that RPCA could be a promising candidate for future CSST PSF modeling efforts.

astro-ph.IM↗
arXiv2026

A finite-element-inspired bipartite graph learned simulator for manufacturability assessment in large-deformation sheet forming

Explicit dynamic finite element (FE) simulations are widely used for large-deformation analysis but remain expensive for design-space exploration. In explicit FE analysis, nodal kinematics and element-level deformation measures evolve through a coupled node-element update process. An FE-inspired learned simulator can preserve this structure and learn nodal kinematics and elemental deformation on their native domains. Nodal displacement describes geometry evolution, while elemental thinning identifies local deformation and critical regions. Feeding both outputs back during rollout allows each field to inform subsequent updates of the other. This work proposes CAtt-BiGNN, a cross-attention-based bipartite graph neural network for coupled nodal-elemental learning. The bipartite graph encodes FE-guided state organisation and information flow without imposing equilibrium or constitutive constraints. Mesh nodes and elements are represented as distinct graph entities connected by directed node-element edges, enabling prediction of nodal displacement increments and elemental deformation on their native domains. An edge-aware cross-attention processor dynamically updates edge representations and weights messages using the receiving state and evolving local relations. For larger graphs, CAtt-BiUGNN uses separate nodal and elemental downsampling and upsampling to enhance long-range propagation while preserving their interaction across graph levels. The method is evaluated on dome-shaped cold-forming and corner-shaped hot-forming benchmarks. Comparisons with node-centred baselines, an FE-inspired hypergraph model, a Physics-Attention-based neural operator, a graph Transformer, and attention ablations show improved joint accuracy in nodal displacement and elemental thinning prediction during autoregressive rollout.

cs.CE↗
arXiv2026

Constraints on the cosmic reheating history from PTA data

The cosmic reheating is an important epoch in the very early Universe, and has significant impacts on the primordial black hole (PBH) abundance and the scalar-induced gravitational wave (SIGW) spectrum. The relevant energy scale and the constituents of cosmic medium are encoded in the reheating frequency $f_{\mathrm{reh}}$ and the equation of state parameter $w$. In this work, we perform a full parameter space Bayesian inference, using the NANOGrav 15-yr dataset to constrain the thermal history of reheating. Treating $f_{\mathrm{reh}}$ and $w$ as free parameters, we systematically investigate the Dirac $δ$, narrow and broad log-normal primordial power spectra. Current pulsar timing array data can effectively constrain the peak frequency of the SIGW spectrum as $f_{\rm p}\sim 10^{-7.6}$--$10^{-7.0}$ Hz, along with $f_{\rm reh}\sim 10^{-9.0}$--$10^{-8.3}$ Hz and $w\sim 0.19$--$0.79$ (the $68\%$ confidence level), when the power spectrum has a relatively narrow width $Δ\lesssim 1$. A broader power spectrum introduces a smoothing effect that obscures the characteristic frequency knee in the SIGW spectrum, leading to the loss of information about cosmic reheating. Furthermore, for the Dirac $δ$ and narrow spectra, the PBH masses associated with the SIGWs are anchored at the planetary mass scale around $10^{-6}$--$10^{-4} M_{\odot}$. This establishes a consistent physical framework that naturally bridges the nanohertz gravitational wave background with the dark matter candidates implied by the Optical Gravitational Lensing Experiment microlensing events.

astro-ph.CO↗
arXiv2026

DRMOT: A Dataset and Framework for RGBD Referring Multi-Object Tracking

Referring Multi-Object Tracking (RMOT) aims to track specific targets based on language descriptions, playing a vital role in interactive AI systems such as robotics and autonomous driving. However, existing RMOT methods rely exclusively on 2D RGB observations. Since similar 2D projections can correspond to different 3D configurations, the available observations may not uniquely determine the referred targets. This creates a fundamental mismatch between the task requirements and the available input. To advance research on the DRMOT task, we construct DRSet, a dataset tailored for the DRMOT task. DRSet comprises 2,076 referring expressions over 186 RGB-D source sequences. It features synchronized RGB images and depth maps paired with language descriptions, including explicit depth-dependent descriptions, to systematically evaluate spatial-semantic detection and tracking capabilities. Furthermore, we propose DRTrack, an MLLM-guided depth-referring tracking framework. DRTrack leverages a Geometric-Aware GRPO fine-tuned Multimodal Large Language Model (MLLM) to achieve precise spatial-semantic detection from joint L+RGB+D inputs, while incorporating explicit depth cues to enforce robust trajectory association. Extensive experiments on the DRSet dataset demonstrate the effectiveness of our framework. Our dataset and code will be available at https://github.com/chen-si-jia/DRMOT.

cs.CV↗
arXiv2026

BAT-NO: A Boundary-Condition-Aware Transformer Neural Operator for Crashworthiness Prediction of Vehicle Components

High-fidelity finite-element simulations provide accurate crashworthiness predictions, but their cost limits iterative design exploration. Deep learning surrogates can reduce this cost, but many component-level models are developed under a single prescribed boundary condition, limiting generalisation to boundary variations. This work proposes a Boundary-Condition-Aware Transformer Neural Operator (BAT-NO) for autoregressive prediction of transient displacement fields and scalar crashworthiness responses under variations in geometry and boundary conditions. A B-pillar simulation framework evaluates generalisation across variations in geometry, impact position and velocity, and support stiffness. BAT-NO combines recurrent mesh processing with latent-grid Fourier operator processing. Boundary-condition information is transferred to the latent grid through a hybrid local--global mechanism. Slice-based attention models interactions among physically related regions, while direct boundary-to-grid projection preserves local spatial structure. Across the validation sets for the shape-only, shape-and-loading, and shape-loading-boundary cases, BAT-NO achieves the lowest mean final-step mean nodal Euclidean displacement error among the evaluated baselines. In the most challenging case, it reduces the mean error by 32.6% relative to the second-best model. Hyperparameter tuning reduces the validation error from 0.451 to 0.269 mm, with a comparable error of 0.267 mm on 300 unseen test simulations sampled within the investigated design space. An attention-based scalar decoder jointly predicts six response trajectories with a mean relative error of 2.46%. Most derived crashworthiness indicators have median errors below 3%. These results show that explicit local and global boundary-condition representations improve crashworthiness prediction over expanded component-level design spaces.

cs.LG↗
arXiv2026

Explainable and Generalisable LLM-based Cognitive Decline Detection with Spontaneous Speech

Alzheimer's disease (AD) and mild cognitive impairment (MCI), which may precede AD, manifest early through subtle linguistic and acoustic alterations. Traditional diagnostics, however, are often resource-intensive and lack scalability for mass screening. To address these challenges, we introduce a novel bilingual speech large language model framework for automated, explainable cognitive screening. Unlike conventional pipelines that rely on error-prone automatic speech recognition, our system directly processes raw speech to learn joint acoustic-semantic representations, preserving critical prosodic cues often lost in transcription. Utilising our newly collected PUTH-AD dataset alongside multiple open-source corpora, we implemented a multi-task learning objective that simultaneously performs cognitive status classification and generates clinician-understandable natural language explanations. Our system achieved the highest average accuracy and AUROC across six dataset/task conditions, comparing three representative baselines. The system demonstrated cross-task transfer to held-out PUTH-AD task subsets, maintaining classification accuracy on an entirely unseen cognitive task without task-specific fine-tuning. Furthermore, clinician evaluation confirms that the generated explanations are both clinically relevant and largely consistent with the underlying speech evidence, supporting their potential utility in clinical interpretation. This study provides a scalable, objective, and explainable framework for speech-based cognitive screening, combining cognitive status classification with natural language explanations that clinicians can assess and verify, bridging the gap between advanced AI and clinical utility.

eess.AS↗
arXiv2026

Untangling Input Language from Reasoning Language: A Diagnostic Framework for Cross-Lingual Moral Alignment in LLMs

When LLMs judge moral dilemmas, do they reach different conclusions in different languages, and if so, why? Two factors could drive such differences: the language of the dilemma itself, or the language in which the model reasons. Standard evaluation conflates these by testing only matched conditions (e.g., English dilemma with English reasoning). We introduce a methodology that separately manipulates each factor, covering also mismatched conditions (e.g., English dilemma with Chinese reasoning), enabling decomposition of their contributions. To study \emph{what} changes, we propose an approach to interpret the moral judgments in terms of Moral Foundations Theory. As a side result, we identify evidence for splitting the Authority dimension into a family-related and an institutional dimension. Applying this methodology to English-Chinese moral judgment with 13 LLMs, we demonstrate its diagnostic power: (1) the framework isolates reasoning-language effects as contributing twice the variance of input-language effects; (2) it detects context-dependency in nearly half of models that standard evaluation misses; and (3) a diagnostic taxonomy translates these patterns into deployment guidance. We release our code and datasets at https://anonymous.4open.science/r/CrossCulturalMoralJudgement.

cs.CL↗
arXiv2026

Curvature integral, volume ratio, bi-Lipschitz for spaces with curvature bounded below

By the paper \cite{Pet2009upper}, \cite{LiNan2026}, we know that there exists $C(n)>0$, for any complete compact or non-compact Riemannian n manifold $M$ with non-negative sectional curvature, without boundary and any $R>0$, \begin{equation} R^{2-n}\int_{B(p,R)} Scal \le C(n). \end{equation} Based on this result, we will prove that (1) There exists constant $C(n)$. If $M$ is a complete, n dimensional, non-compact Riemannian manifold with non-negative sectional curvature, then for any $p\in M$, $R>0$, \begin{equation} R^{2-n}\int_{B(p,R)} Scal \ dvol \le C(n)(1-v(M)), \end{equation} where $Scal$ is the scalar curvature and $v(M)=\lim\limits_{R\to \infty} \frac{volB(p,R)}{volB(0,R)}$ is the asymptotic volume ratio. (2) There exists constant $C(n)$. If $M$ is a complete, n dimensional Riemannian manifold with sectional curvature $\ge 1$, then \begin{equation} \int_M (Scal-n(n-1)) \ dvol \le C(n)(1-\frac{vol(M)}{vol(S^n(1))}). \end{equation}

math.DG↗
arXiv2026

Primordial black hole clustering from spectator fields for interpreting the JWST observations

The observations by the James Webb Space Telescope (JWST) have revealed unexpectedly massive galaxy candidates at high redshifts, posing a significant challenge to the $Λ$CDM model. In this work, we investigate whether primordial black holes (PBHs) with spatial clustering, generated by a light spectator field during inflation, can accelerate early structure formation. We adopt the galaxy candidates with inferred stellar mass $10^9\,M_\odot\leq M_*^{\rm obs}\leq10^{11}\,M_\odot$ at redshift $7 \leq z \leq 10$ reported by the CEERS program as a benchmark. Two different mechanisms are considered, through which PBH clustering can influence structure formation: the PBH-induced isocurvature perturbations that enhance the matter power spectrum on linear scales, and the localized seed formation and accretion by compact PBH clusters on nonlinear scales. We find that, when adopting the cosmic microwave background (CMB) isocurvature constraint $β_{\rm iso}<0.035$ at the benchmark pivot scale $k_*=0.002\,{\rm Mpc}^{-1}$, PBH clustering can produce a cumulative stellar mass density consistent with the JWST observations while satisfying the relevant isocurvature constraint. However, the allowed enhancement of structure formation is strongly suppressed when the constraint at $k_*=0.1\,{\rm Mpc}^{-1}$ is imposed, indicating a significant dependence on the choice of the pivot scale. In contrast, the localized seed effect of compact PBH clusters is strongly constrained by the CMB isocurvature bounds, while isolated supermassive PBHs produce stellar mass densities far below those inferred from the JWST observations. Our results show that PBH clustering induced by a spectator field can substantially accelerate early structure formation, but whether it can fully account for the JWST-inferred stellar mass density depends sensitively on the pivot scale adopted for the CMB isocurvature constraint.

astro-ph.CO↗
arXiv2026

Gaze as Evidence for Common Grounding: A Cross-Corpus Analysis of MapTask and MUNDEX

In collaborative tasks with asymmetric information, participants coordinate their understanding through interaction. We ask whether gaze provides evidence about grounding across two such tasks. Working from discrete behavioral annotations, we map HCRC MapTask (Anderson et al., 1991) and MUNDEX (Türk et al., 2023) into a shared partner/task/away vocabulary and compute gaze features around task-relevant dialogue units. In both corpora, aligned reference interpretations (MapTask) and UND (understood) judgments (MUNDEX) are associated with more task-directed gaze and with less partner-directed gaze, lower gaze entropy, and fewer gaze transitions. The associations are clearest for the participant leading the task: in giver-produced references, and in explainer judgments, which also co-vary with the explainee's gaze. In same-speaker MapTask reference chains, the speaker's gaze entropy is lower at the mention where a previously non-aligned referent becomes aligned. The best gaze feature groups improve modestly over controls under grouped cross-validation: temporal features in MapTask and raw proportions in MUNDEX. Because effects are small and several weaken when recurring participants rather than dialogues are the unit of inference, we treat gaze as one contributing cue to grounding, to be interpreted alongside task and dialogue context.

cs.CL↗
arXiv2026

Agri-Sim: Agricultural Simulation Platform for Embodied Intelligence Evaluation in Greenhouse Robotics

Agricultural-robot development requires simulation environments that can jointly support realistic scene construction, virtual sensing, autonomous navigation, motion planning, and manipulation-task execution. This paper presents Agri-Sim, a Unity and ROS2-based simulation platform for the closed-loop development and functional evaluation of agricultural robots. The platform contains a configurable tomato-greenhouse environment, a mobile dual-arm harvesting robot, virtual RGB-D, LiDAR, IMU, and joint sensors, and a bidirectional communication interface between Unity and ROS2. Unity is responsible for scene rendering, rigid-body dynamics, collision detection, virtual sensing, and task-state execution, whereas ROS2 and MoveIt 2 provide localization, navigation, collision-aware motion planning, inverse kinematics, and trajectory generation. Autonomous greenhouse navigation and dual-arm tomato harvesting were used to evaluate the complete simulation workflow. The experiments covered virtual sensor publication, ROS2-based navigation, collision-aware motion planning, mobile-base control, tomato acquisition, inter-arm handover, and box placement. The results demonstrate that Agri-Sim supports closed-loop integration and repeatable functional evaluation of navigation and manipulation workflows in a controlled virtual greenhouse, providing a practical foundation for subsequent algorithm development and Sim-to-Real studies.

cs.RO↗
arXiv2026

Acquire, Repair, Preserve: A Diagnosis-Guided Post-Training Recipe for Small-Model Dialogue Game Agents

Interactive dialogue games test a capability that static benchmarks largely leave implicit: a model must carry state across turns, interpret feedback, and choose valid actions under changing constraints. We study this setting in the LM Playschool Challenge with a 2B open-weight model, and find that many failures are not only broad knowledge failures but also local decision failures: repeated guesses, malformed actions, and violations of feedback that the model has just seen. These diagnostics motivate a training recipe organized around three steps: acquire broad game participation through supervised fine-tuning, repair mechanically verifiable failures within one targeted dialogue-game family using turn-local preference pairs, and preserve general capabilities beyond these dialogue games. In the official final evaluation, our submission improves public clemscore from 10.67 to 38.92 and closed in-domain score from 13.41 to 41.17, while approximately preserving aggregate static performance (44.14 vs. 44.24 for the baseline). Out-of-domain clemscore remains low at 7.88, with the largest gains concentrated in unseen variants of the targeted family. Our results suggest that broad SFT brings most of the model's capability improvement; turn-local supervision can be effective when failure detection is precise, with observed transfer concentrated primarily within-family.

cs.CL↗
arXiv2026

Anisotropic dynamical reconstruction of quantum geometry in quenched Chern insulators

Under unitary dynamics, the Chern number of an evolving quantum state remains conserved even when a quench drives the Hamiltonian across a topological phase transition. In sharp contrast, we reveal an anisotropic dynamical reconstruction of the quantum metric. Following a sudden quench in a two-dimensional Chern insulator, the metric develops a principal frame in which one eigenvalue grows in time whereas the other remains nearly unchanged. At long times, the associated axes align with the energy-gradient direction and the tangent direction of the constant-energy contours of the post-quench Hamiltonian, respectively. This dynamically selected frame is distinct from that of the static post-quench ground-state metric. We identify momentum-dependent relative dynamical phases as its origin: they enhance the distinguishability of neighboring states separated along the energy-gradient direction, while states along an equal-energy contour remain nearly phase locked. Consequently, local and global metric observables acquire characteristic long-time signatures of the post-quench Hamiltonian. Our results establish a nonequilibrium mechanism by which coherent dynamics reorganizes quantum geometry, suggesting new possibilities for its dynamical control.

quant-ph↗
arXiv2026

Valhalla: A Layered Knowledge-State and Service-Governance Framework for Long-Term Scientific Knowledge Work

As large language model (LLM) agents are increasingly adopted in scientific research, external knowledge bases, knowledge graphs, and long-term memory have improved information retrieval and task continuity. However, most structured knowledge systems remain node-centric, representing files, concepts, results, and judgments as nodes and relations in a graph. While suitable for personal knowledge management, such structures often depend on individual organizational practices, limiting knowledge sharing, integration, and reorganization across users. This paper presents Valhalla, a layered knowledge-state and service-governance framework for long-term scientific knowledge work. Valhalla replaces flat graphs with layered encapsulation and stable semantic boundaries through a five-layer File-Resource-Entity-Relationship-Graph (FREG) model. File and Resource preserve source identity and provenance, Entity represents knowledge objects, Relationship captures semantic judgments, and Graph provides task-oriented knowledge views, enabling knowledge states from different researchers to be exchanged and reorganized under a unified structure. We further introduce a Router-Contract-Workflow service-governance architecture, inspired by the microkernel paradigm, to constrain how language models access, modify, and extend knowledge states while maintaining structural consistency and auditable operational boundaries. We implement a Valhalla prototype and validate knowledge ingestion, cross-member integration, and scientific writing support through an antibody-design review task comprising 26 paper resources, 80 knowledge entities, and 92 semantic relations. Rather than proposing a new knowledge-extraction algorithm, Valhalla offers a paradigm for organizing collaborative scientific knowledge, transforming individualized knowledge structures into transferable and reorganizable shared knowledge states.

q-bio.NC↗