Searcharxiv⌕ Search

arXiv subjects

Lu Lu

Publications and source records attributed to Lu Lu.

At least 19 recordsLinked to original sources

Derivative-Informed Training of Neural Operators On-the-Fly via Sketched Tangent Consistency

Derivative-informed training improves neural operators by directly supervising their input-output sensitivities, which is crucial when neural operators are used as differentiable surrogates for inverse problems, PDE-constrained optimization, design, and control. However, existing methods rely on offline-generated derivative labels, making data generation slow, storage-intensive, and difficult to adapt across datasets, resolutions, or perturbation bases. We propose sketched tangent consistency loss (sTCL), an on-the-fly derivative-informed training objective that, for PDEs with a known and differentiable residual, enforces sensitivity consistency directly from the governing equation without offline tangent labels or neural-operator architecture changes. sTCL uses randomly sketched input perturbations to provide a lightweight derivative-level physics constraint during training. However, raw forward-sensitivity residual penalties can fail for stiff, ill-conditioned, indefinite, or coupled saddle-point tangent operators. To address this, we introduce lightweight operator-aware loss-conditioning mechanisms selected by a simple tangent-operator decision rule. Across Helmholtz, nonlinear diffusion-reaction, Burgers, Allen-Cahn, and Navier-Stokes, with the same neural-operator backbone for all methods, the PDE-specific sTCL losses achieve solution and Jacobian accuracy comparable to offline derivative-informed training (DIFNO) while eliminating the offline derivative-data generation and storage pipeline. These results show that on-the-fly derivative-informed training need not merely amortize offline tangent-solve cost into training; with appropriate sketching and loss design, sTCL provides an effective drop-in path to derivative-informed neural operators. Code is available at https://github.com/Mou-group-UMN/Derivative-informed-training-on-the-fly.

cs.LG↗

Foundation Models for Wireless Communications: From PHY Intelligence to Network Autonomy

6G networks will introduce unprecedented complexity, which calls for a paradigm shift in network optimization and management. Artificial intelligence (AI)-based solutions, especially those enabled by the recently developed foundation models, have been recognized as promising candidates. Foundation models are large-scale AI models with general-purpose feature extraction capabilities, and once trained on massive amounts of data, they can be adapted to solve a wide range of downstream tasks, either in a zero-shot manner or with few-shot fine-tuning. This article provides a comprehensive overview of how foundation models are reshaping physical-layer processing and wireless resource management across three progressive paradigms. First, we examine the adaptation of off-the-shelf pre-trained foundation models to various wireless tasks. Second, we explore wireless-native foundation models, built from scratch on wireless data to bridge cross-domain modality gaps and capture universal wireless-domain physical characteristics. Third, we highlight agentic foundation models, which elevate static data processing into autonomous, reasoning-driven network orchestration. Furthermore, we discuss the impact of applying foundation models to emerging 6G frontiers, including integrated sensing and communications (ISAC), new multiple-input multiple-output (MIMO) architectures, semantic communications, and system-level network autonomy. Finally, we identify critical open challenges and opportunities, charting a promising path toward fully intelligent and adaptive wireless networks.

eess.SP↗

FoundPDE: A generative foundation model for data-driven symbolic discovery of partial differential equations

Discovering governing partial differential equations (PDEs) from observed data is a central inverse problem in computational science and engineering: the goal is not only to predict trajectories, but to identify interpretable symbolic laws that can be analyzed and reused. Existing PDE discovery methods often depend on hand-designed libraries, accurate numerical derivatives, or per-equation symbolic search, making them fragile under sparse observations, noisy data, broad equation families, and unseen symbolic compositions. Here, we introduce FoundPDE, a pretrained data-to-symbol foundation model for PDE discovery. FoundPDE maps discretized spatio-temporal trajectories to symbolic equations with a transformer, uses Fourier and first-order spatial-derivative augmentation to expose complementary trajectory information, refines numerical coefficients, and supports downstream extension with improved generalization through few-shot fine-tuning and hierarchical discovery. On a clean in-domain benchmark spanning 20 PDE families, our model reaches 97.50% type recognition. Under coefficient shifts beyond the training support, type recognition remains 90.53%; under multiplicative Gaussian noise on the model input, it is 94.43% at a 2% noise level but falls to 52.09% at 10%. For unseen composite equations, few-shot fine-tuning reaches over 90% exact recovery on four held-out families, and we further develop a hierarchical discovery algorithm that recovers two-term composites without fine-tuning FoundPDE. By amortizing symbolic discovery across equation families, FoundPDE shifts PDE discovery from per-dataset search toward a reusable pretrained model that extends to new physics with limited additional data, a step toward foundation models that uncover interpretable governing laws directly from scientific data.

physics.comp-ph↗

Full-Duplex Interaction with Speech, Expressions and Gestures

Human face-to-face conversation requires coordinating speech, gestures and expressions across both speaking and listening. We present ELLSA 2, an end-to-end full-duplex dialogue model that jointly optimizes speech interaction and streaming gesture-expression generation. An autoregressive, chunk-wise synthesizer combines pretrained acoustic features with distinct listening and speaking hidden states from the dialogue backbone and speech synthesizer, enabling continuous non-verbal generation even when the model is verbally silent. To translate dialogue understanding into vivid semantic gestures, we introduce contextual semantic calls and template guidance, separating whether to invoke an available semantic gesture from how to realize it. We also establish a curated data and evaluation pipeline for dialog-aware co-speech gesture generation and investigate reference-based multimodal large language models (MLLMs) as automatic judges. Experiments show that ELLSA 2 remains highly competitive with open-source full-duplex speech interaction models and outperforms cascaded baselines across dialog-aware gesture and expression metrics. Semantic template guidance further significantly improves semantic gesture quality. Strong system-level correlations with human judgments support these reference-based scores as useful preliminary metrics for full-duplex and semantic gesture assessment. Together, these results advance dialogue modeling from spoken responses toward coordinated multimodal interaction.

eess.AS↗

Geometric Alignment without Functional Equivalence: A Layer-wise Analysis of the Speech-Text Modality Gap

End-to-end speech large language models (LLMs) often answer the same question less accurately from speech than from text, even when the spoken content matches the text prompt. Existing analyses study this modality gap through the geometry of representations and measure how closely speech representations align with text. Geometric alignment gives the gap a measurable form, but it does not show whether the model uses aligned representations in the same way. This work connects representation geometry with answer formation and asks whether geometric alignment implies functional equivalence. We compare cross-layer Centered Kernel Alignment (CKA) with layer-wise answer margins for four open-weight speech LLMs on SpeechMMLU and VoiceBench BBH. In Qwen2.5-Omni and MiniCPM-o, speech and text representations align in middle layers while their late-layer answer margins still differ, so mid-layer alignment does not imply functional equivalence. Qwen2-Audio instead shows weak alignment, which indicates a different failure mode. An attention intervention at fixed input and token count identifies a causal effect of late attention allocation on answer-code separation, a quantity distinct from answer correctness. Compressing the speech signal or its token sequence repairs a subset of the errors that occur only with speech.

cs.CL↗

GeoFunFlow: Geometric function flow matching for joint probabilistic inference of physical fields and complex geometries

Inverse problems governed by partial differential equations (PDEs) arise widely in science and engineering, but are often ill-posed and limited by sparse, noisy observations. In many applications, measurements reveal only part of the physical state, while the domain geometry may also be unknown even though it shapes the observed response. Joint field and geometry inference across varying computational domains and discretizations remains challenging, whereas many existing machine learning approaches are designed for known geometries and deterministic field reconstruction. Here, we introduce GeoFunFlow, a probabilistic framework that unifies field reconstruction on known domains and joint field and geometry inference on unknown domains. GeoFunFlow combines a geometric function autoencoder (GeoFAE) with flow matching in the latent space to model a joint distribution over physical fields and geometries. GeoFAE establishes a common representation across spatial discretizations that captures the relationship between physical fields and domain geometries, with unknown geometry represented by a signed distance function. The resulting representation allows observations to guide both field reconstruction and geometry recovery, while latent rectified flow enables efficient conditional sampling and spatially resolved uncertainty quantification. A calibration procedure further provides geometry uncertainty estimates with interpretable empirical coverage. Across seven benchmarks spanning porous media flow, fluid mechanics, and optical tomography, GeoFunFlow accurately recovers fields and geometries across complex, variable, and unknown domains while quantifying spatially resolved conditional uncertainty.

cs.LG↗

SALMONN-duo: Adaptive Dual-System Coordination for Full-Duplex Voice Agents

Full-duplex speech large language models (LLMs) enable low-latency, natural voice interaction. However, real-world agents must also use tools and perform deliberative reasoning-operations whose variable latency and computational cost conflict with the stringent timing requirements of real-time conversation. To reconcile these demands, we propose SALMONN-duo, an adaptive dual-system voice agent inspired by dual-process theories of cognition. SALMONN-duo separates real-time interaction from deliberative computation by pairing an always-on, fast-thinking full-duplex speech LLM (system 1) with a powerful asynchronous slow-thinking LLM agent (system 2). Beyond handling real-time interaction, system 1 learns when to answer directly and when to delegate, remaining responsive during backend execution and seamlessly integrating returned information into the ongoing dialogue without exposing tool traces or losing conversational context. Evaluations on single-turn spoken question answering (QA) and multi-turn conversations demonstrate that adaptive delegation substantially improves accuracy on knowledge-intensive and multi-hop reasoning questions, while knowledge-boundary-aware training avoids unnecessary system 2 invocations. On a customized version of $τ$-Voice, SALMONN-duo further demonstrates its ability to complete environment-grounded, policy-constrained tasks through multi-turn interactions in realistic business scenarios. Finally, cost-aware reinforcement learning further enhances the trade-off between task performance and backend usage across the QA and conversation tasks, while improving task success and response safety on $τ$-Voice with an acceptable increase in the delegation rate.

cs.CL↗

FlexiSLM: A Spoken Language Model with Dynamic and Controllable Frame Rates

Spoken language models (SLMs) extend LLMs to speech input and output, but existing systems use fixed frame rates (e.g., 25 or 12.5 Hz), overlooking speech's time-varying information density and limiting inference-time quality-speed tradeoffs. Recent dynamic-frame-rate audio tokenizers enable very low average frame rates and controllability, yet had not been applied to SLMs. We introduce FlexiSLM, the first SLM with dynamic, controllable frame rates, using pretrained FlexiCodec for dynamic speech output tokens. It integrates this representation into a multi-task speech-to-speech SLM, extends it with input-side frame compression, and adds direct frame-rate conditioning for accurate control during inference. FlexiSLM outperforms fixed-frame-rate 7B models, including Qwen2.5-Omni and Kimi-Audio, at 12.5 and 6.25 Hz; it can be steered down to 4.0 Hz, and at 6.25 Hz roughly halves inference time relative to 12.5 Hz while retaining strong speech-to-speech quality. Audio samples: https://flexislm.github.io; code and data: https://github.com/AmphionTeam/FlexiSLM.

cs.SD↗

Gaussian-trigonometric functional link artificial neural network: design and analysis

This paper proposes a Gaussian function-based trigonometric functional link artificial neural network (GTFLN) filter for linear-in-the-parameters nonlinear filtering. Compared with the adaptive exponential TFLN (AETFLN) filter, the GTFLN filter provides smooth and localized basis functions with reduced computational complexity, where modeling advantages are theoretically established through the smoothness, reproducing kernel Hilbert space, approximation error, and operator theory properties. To maximize the modeling performance, an optimized scaling parameter for the GTFLN filter is derived, yielding the optimized GTFLN (OGTFLN) filter. Least mean square (LMS) adaptation is applied to the GTFLN and OGTFLN filters for nonlinear system identification, resulting in the GTFLMS and OGTFLMS algorithms, respectively. Moreover, the theoretical steady-state excess mean-square error of the GTFLN filter is analyzed. Simulations validate the effectiveness of the theoretical analysis and demonstrate the improved performance of the GTFLN and OGTFLN filters over the linear-in-the-parameters benchmarks in nonlinear system identification and nonlinear acoustic echo cancellation. Based on the GTFLN filter, the filtered-g LMS (FgLMS) algorithm is proposed for nonlinear active noise control. Simulations demonstrate improved stability and noise reduction performance compared to the benchmarks.

eess.SP↗

Spectral extremal hypergraphs without long Berge cycles

Let $r\ge 3$ and $k\ge 2r+1$ be fixed integers. We determine, for all sufficiently large $n$, the maximum adjacency-tensor spectral radius of an $n$-vertex $r$-uniform hypergraph containing no Berge cycle of length at least $k$. Write $s=\left\lfloor\frac{k-1}{2}\right\rfloor$. If $k=2s+1$ is odd, the unique extremal hypergraph consists of all $r$-sets containing at most one vertex outside a fixed $s$-set. If $k=2s+2$ is even, one additionally includes all $r$-sets containing a fixed pair outside the $s$-set together with $r-2$ vertices inside it. Consequently, the maximum spectral radius is given as \[ \operatorname{spex}_r(n,k) = \left[ \binom{s}{r-1} \left(\frac{r-1}{s}\right)^{(r-1)/r} +o(1) \right]n^{(r-1)/r}. \]

math.CO↗

Equality Cases for the Face-Degree Majorization Theorem on Simplicial Complexes

The Grone--Merris--Bai theorem states that the Laplacian spectrum of a simple graph is majorized by its conjugate degree sequence. Recently, Zhang, Song, and Fan extended this result to simplicial complexes by establishing a majorization relation between the spectrum of the $(r-1)$-dimensional up-Laplacian and the conjugate $(r-1)$-degree sequence. In this paper, we characterize all equality cases in the partial-sum inequalities of this higher-dimensional majorization theorem. For every $r$-dimensional simplicial complex $X$ with $r\ge2$, we prove that \[ \sum_{i=1}^{q}λ_{r-1,i}(X) = \sum_{i=1}^{q}d_{r-1,i}^{\top}(X) \] if and only if \[ q\ge \max\{\operatorname{rank}B_r(X),Δ_{r-1}(X)\}. \] Thus, unlike the graph case, equality can occur only after both sequences have exhausted all their nonzero terms. As consequences, equality in the first partial sum and equality between the entire sequences are both equivalent to $X$ containing a unique $r$-simplex. The proof is based on the local down-Laplacian decomposition and the equality case of the Ky Fan inequality.

math.CO↗

Neural Operator-enabled Topology-informed Evolutionary Strategy for PDE-Constrained Optimization

The inverse design of physical systems governed by partial differential equations is computationally demanding due to the high dimensionality and non-convexity of design spaces. Generative models for inverse design often lack robustness and transferability, whereas evolutionary strategies are robust but struggle in high-dimensional spaces. This paper introduces a Neural Operator-enabled Topology-informed Evolutionary Strategy (NOTES) that integrates dimensionality reduction, representation learning, and evolutionary optimization for efficient and transferable inverse design. NOTES couples a DeepONet-based neural operator with the Covariance Matrix Adaptation Evolution Strategy (CMA-ES) to perform global optimization in a compact latent space that encodes topology-aware priors while discovering high-performance designs for unseen operating conditions. Applied to nanophotonic beam-deflector inverse design governed by Maxwell's equations, NOTES reduces the design dimensionality from 256 to 25 and consistently achieves over 95 percent efficiency, outperforming CMA-ES, topology optimization, and other baselines. Applied to structural optimization, NOTES discovers designs that achieve compliance down to 246. By decoupling topology learning of a DeepONet from the governing physics in a PDE solver, NOTES provides a flexible and transferable framework for the inverse design of physical systems.

cs.LG↗

A Spectral Hilton--Milner--Frankl Theorem for $t$-Intersecting Families

Keevash, Lenz, and Mubayi proved a spectral Erdős--Ko--Rado theorem, showing that, for sufficiently large $n$, the complete $t$-star uniquely maximizes the adjacency-tensor spectral radius among all $t$-intersecting $k$-uniform families. In this paper, we establish a spectral Hilton--Milner--Frankl theorem for nontrivial $t$-intersecting families in the explicit range $1\le t\le k-2$ and $n\ge 100\cdot 2^k k^7$. More precisely, we prove that, for every nontrivial $t$-intersecting $k$-uniform family $\mathcal F$, the spectral radius satisfies \[ ρ(\mathcal F)\le \max\{ρ(\mathcal H_{n,k,t}),ρ(\mathcal A_{n,k,t})\}, \] where $\mathcal H_{n,k,t}$ and $\mathcal A_{n,k,t}$ are the two extremal families appearing in the classical Hilton--Milner--Frankl theorem. Moreover, equality holds only for the extremal candidates attaining the maximum, up to isomorphism. We further compare the two candidates asymptotically. For each fixed $t$, the unique real solution $x=x_t$ of \[ (t+2)^{x-t-1}(t+1)^{t+1}=(x-t+1)^{x-1} \] determines, as $k$ varies, which of $\mathcal H_{n,k,t}$ and $\mathcal A_{n,k,t}$ has the larger asymptotic spectral radius.

math.CO↗

RESPClinBench: Benchmarking Multimodal Clinical Decision-Making and Longitudinal Disease Management in Respiratory Specialty Care

Background: Respiratory specialty care requires multimodal interpretation, longitudinal risk assessment, guideline-concordant intervention, and whole-course management, which are poorly represented by examination-oriented medical benchmarks. Objective: To develop RESPClinBench, a real-world scenario-based benchmark for respiratory clinical decision-making, and evaluate seven contemporary large language models across AECOPD-PIM and PNBIM. Methods: RESPClinBench cases were adapted from de-identified respiratory clinical data. Three attending-level respiratory physicians revised cases, reference answers, and atomic clinical-action points, while one senior respiratory specialist performed cross-review and final adjudication. AECOPD-PIM comprised 427 open-ended COPD cases, and PNBIM comprised 196 multimodal pulmonary nodule cases combining chest CT with structured clinical information. Seven models generated 4,361 responses through standardized API inference with temperature 0 and a maximum output length of 8192 tokens. An automated framework calculated the final score as the arithmetic mean of atomic-action recall and rubric-based LLM-as-a-Judge assessment. Results: Across 623 cases, the mean final score was 68.58. Qwen3.6-27B ranked first overall at 71.22, Qwen3.5-397B-A17B led PNBIM at 72.48, and Qwen3.6-27B led AECOPD-PIM at 71.11. Imaging hallucination and serious medical risk occurred in 31.85% and 8.16% of PNBIM responses; medication-safety risk and serious medical risk occurred in 26.93% and 1.44% of AECOPD-PIM responses. Conclusions: RESPClinBench identifies task-specific limitations in multimodal pulmonary nodule assessment and longitudinal COPD management. Combining explicit clinical-action coverage, holistic evaluation, and independent safety flags provides a clinically grounded basis for model selection and prospective validation.

cs.CL↗

CardioBench: A Real-World Data Benchmark for Evaluating Large Language Models in Clinically Authentic Cardiovascular Care Scenarios

Background: Most medical large language model (LLM) benchmarks focus on examination knowledge or isolated tasks and may not reflect the longitudinal, multimodal, and safety-critical workflow of cardiovascular care. Objective: To develop CardioBench, a real-world benchmark spanning the cardiovascular care continuum, and assess LLM performance across clinical dimensions and specialist tasks. Methods: CardioBench includes 2,263 items from 13 task-specific datasets derived from de-identified cardiovascular records and examination data. Sixteen cardiology physicians conducted annotation and reference construction, followed by cross-review from two senior cardiologists. Seven LLMs generated 15,841 outputs under standardized zero-shot settings. Open-ended tasks were evaluated using key-point coverage and holistic clinical quality, while CardioEthics was scored by accuracy. Results: GPT-5.4 achieved the highest macro-average (62.55) and item-weighted mean (62.19), followed by Gemini 3.1 Pro (59.95) and Qwen 3.6 27B (59.72). GPT-5.4 ranked first in all three dimensions. CardioAuxReport performed best (86.38), whereas CardioECGRead (17.25) and CardioEthics (17.34) were lowest. The largest gaps between holistic clinical quality and key-point coverage occurred in CardioComm (52.71), CardioEmergRescue (52.05), and CardioTreatPlan (48.80). Conclusions: To our knowledge, CardioBench is the largest real-world, multi-task benchmark for LLM evaluation across the cardiovascular care continuum and offers the broadest coverage of clinically authentic cardiology scenarios reported to date. It provides a rigorous framework for identifying model strengths, clinically important omissions, and priorities for future development.

cs.CL↗

An improved range for the maximum critically $t$-intersecting hypergraphs

Let $k>t\ge 1$ be integers and set $d=k-t$. A $k$-uniform hypergraph $\mathcal F$ is called $t$-intersecting if any two edges intersect in at least $t$ vertices, and is called $t$-critical if its minimum $t$-transversal has size $k$. Frankl proved that, for $k\ge d^4$,$|\mathcal F|\le \binom{k+d}{d},$ with equality only for the complete $k$-graph on $k+d$ vertices, and conjectured that the same conclusion should hold when $k>c d^2$ for some constant $c$. In this paper we confirm this conjecture for $c=30$. The proof relies on Frankl's fixed-edge decomposition and Füredi's pseudo-sunflower method.

math.CO↗

On a conjecture regarding the product version of the Hilton-Milner theorem

Recently, Frankl and Wang considered a product version of the classical Hilton-Milner theorem. They conjectured that, if $\mathcal{F} \subset \binom{[n]}{k}$ and $\mathcal{G} \subset \binom{[n]}{\ell}$ are non-trivial cross-intersecting families with $n \geq 2k > 2\ell \geq 4$, the maximum of $|\mathcal{F}||\mathcal{G}|$ is attained by the natural Hilton-Milner-type configurations. In this paper, we present two main results concerning this conjecture. Firstly, we show that the conjecture does not hold in general. By introducing a two-center construction, we prove that for every fixed integer $\ell \geq 3$ and all sufficiently large $k$, the conjecture is false in a linear range $2k+1 \leq n \leq (c_\ell - ε)k$ for any $0 < ε< c_\ell - 2$, where $c_\ell > 2$ is an explicit constant. Secondly, we prove that the conjecture holds when $n > 100\ell k^2$ and $3 \leq \ell < k$, and we completely characterize the extremal families. Our proofs rely on the size of minimal covers and analyzing the structural properties of $2$-cover graphs.

math.CO↗

SkillComm: Skill-Driven Semantic Communication for Sequential Workflows via Incremental Token Transmission

As wireless visual intelligence evolves from isolated task inference to ordered skill workflows, the communication bottleneck shifts from transmitting a single semantic representation to coordinating reusable skill states under channel constraints. Existing DeepJSCC and prompt-guided visual transmitters usually treat each task as an independent full-token transmission, with limited reuse of execution memory across semantic workflows. This is inefficient for workflows such as Detect, Segment, and Keypoint, where later stages often require only state-relevant semantic updates. To this end, we propose SkillComm, a skill-driven semantic communication framework that uses reusable skill states as shared context for workflow-aware token prioritization and memory-assisted token-grid reconstruction. A shared Skill-Book maps a high-level visual intent into a synchronized executable skill sequence at the transmitter and receiver. Conditioned on this workflow, adaptive token selection exploits cross-step memory to transmit only state-active tokens through joint source-channel coding, while the receiver reconstructs a task-ready token grid by combining decoded tokens with local historical memory. Experiments on the MS COCO 2017 validation set for the Detect-Segment-Keypoint workflow show that SkillComm reduces token transmission cost by 51.2% while retaining 99.4% upper-bound-normalized average precision at high SNR. These results demonstrate that reusable skill states enable selective semantic update delivery for future agentic and embodied visual intelligence.

cs.NI↗