arXiv subjects

Ning Liu

Publications and source records attributed to Ning Liu.

At least 37 records · Page 2Linked to original sources

arXiv2026

AgenticVAU: Multi-Agent Explore-Verify Reasoning for Video Anomaly Understanding

Video anomaly understanding (VAU) focuses on comprehensively interpreting abnormal events in videos, requiring models to identify anomalous occurrences, discover their supporting evidence, and explain the underlying causes beyond simple anomaly detection. Existing VAU methods often rely on specialized training or limited observations, restricting generalization or evidence coverage. Although single-agent alternatives support adaptive video observation, they still integrate exploration, observation, and decision-making within a unified reasoning process, offering limited role specialization and structured evidence coordination. To address these limitations, we present AgenticVAU, a training-free multi-agent framework that casts VAU as an explore--verify process, where the system first discovers potential anomalies and then verifies them through targeted observations. To achieve this, four specialized agents are introduced to handle visual-rule construction, search planning, video observation, and final decision, respectively. These agents communicate through an anchor registry, a shared evidence memory that binds each observation. Guided by this agent framework, AgenticVAU interleaves broad temporal exploration, dense local verification, and cross-interval comparison until sufficient evidence is collected. We conduct extensive experiments on the ECVA, UCF-Crime, and MSAD subsets of VAU-Bench, the results show that AgenticVAU outperforms zero-shot inference and reinforcement learning-based baselines, demonstrating the value of multi-agent collaboration for video anomaly understanding.

cs.CV↗

arXiv2026

JoyAI-Talker: Full-Duplex Speech Interactive Large Model Built for Empathetic Voice Agents

We present JoyAI-Talker, a full-duplex speech dialogue system that delivers robust foundation model capabilities while empowering empathetic interaction and voice agent intelligence. JoyAI-Talker adopts a modular Thinker-Talker architecture and further implements a unified speech-text joint training pipeline to mitigate the common "cognitive degradation" bottleneck, thereby largely preserving the model's core textual reasoning, STEM, and logical capabilities while extending them to speech-based interaction. For expressive speech synthesis, the Talker module employs a text-controllable generation paradigm that enables natural-language instructions to flexibly control vocal attributes and localized paralinguistic events, such as laughter and sighs, supporting more expressive and fine-grained speech responses. To enhance conversational empathy, we introduce the Persona-Adaptive Empathetic Response (PAER) framework. PAER employs a hierarchical cognitive pipeline to extract non-verbal speaker cues, such as gender, age, and emotional state, from raw input audio, incorporate them into the Thinker's CoT reasoning, and generate context-adaptive responses that align semantically appropriate text with fine-grained control over utterance-level expressiveness and localized paralinguistic events, including sighs, speaking rate, and volume. We further integrate Joy-Duplex, a state-driven, plug-and-play full-duplex framework that functions as an efficient gating engine for real-time turn control. Extensive evaluations show that JoyAI-Talker achieves highly competitive performance on foundational T2T and S2T benchmarks. In full-duplex evaluation, the system reaches a high response rate of 0.88 under user interruptions while maintaining an extremely low false-trigger rate under background speech, demonstrating its readiness for fluid and natural speech dialogue.

cs.SD↗

arXiv2026

M3MAD-Bench: Multi-Dimensional Evaluation of Multi-Agent Debate Across Domains and Modalities

As an agent-level reasoning and coordination paradigm, Multi-Agent Debate (MAD) orchestrates multiple agents through structured debate to improve answer quality and support complex reasoning. However, existing research on MAD suffers from two fundamental limitations: evaluations are conducted under fragmented and inconsistent settings, making fair comparison difficult, and are largely confined to text-only scenarios, leaving its effectiveness in multimodal settings underexplored. To address these gaps, we introduce M3MAD-Bench, a unified and extensible benchmark for evaluating MAD methods across Multi-domain tasks, Multi-modal inputs, and Multi-dimensional metrics. M3MAD-Bench establishes standardized protocols over five core task domains, including Knowledge, Mathematics, Medicine, Natural Sciences, and Complex Reasoning, covering a total of 13 datasets, and systematically includes both pure text and vision-language data, enabling controlled cross-modality comparison. We evaluate MAD methods on 9 base models spanning different architectures, scales, and modality capabilities. Beyond accuracy, M3MAD-Bench incorporates efficiency-oriented metrics such as token consumption and inference time, providing a holistic view of performance--cost trade-offs. Through extensive experiments, we derive nine key insights, revealing that MAD is not uniformly effective: collaborative methods are generally more robust than adversarial ones, especially on reasoning-intensive and multimodal tasks, but often incur substantial efficiency costs. These findings provide practical guidance for selecting and designing MAD strategies in real-world applications. We believe M3MAD-Bench offers a reliable foundation for future research on standardized and reproducible MAD evaluation. The code is available at https://github.com/liaolea/M3MAD-Bench.

cs.AI↗

arXiv2026

Stateful Cooperative Agents Safeguarding LLMs Against Evolving Multi-Turn Attacks

As LLMs become increasingly integrated into complex applications, their vulnerability to adversarial attacks has raised significant concerns. However, existing defenses remain reactive in nature. This limitation makes it difficult for them to counter sophisticated threats, as adversaries continuously adjust their strategies across multi-turn interactions. In this paper, we present a proactive defense framework for securing LLMs against evolving multi-turn adversarial attacks that combines disruption, misdirection, and adaptation across successive interaction turns. In particular, it employs a cooperative multi-agent architecture in which specialized agents execute complementary defense strategies. These strategies include controlled response pacing to increase attack costs, strategically ambiguous outputs to mislead adversaries into ineffective strategies, and forensic analysis of interaction logs to identify attack patterns and refine defenses. These agents are coordinated by an adaptive mechanism that dynamically adjusts the defense strategy in response to escalating threats. To facilitate comprehensive evaluation, we present the EMRA dataset designed to simulate evolving strategies across multi-turn attacks, including 5,200 adversarial samples across eight attack types. Experimental results on EMRA across multiple LLM backbones show that the proposed framework reduces ASR by 69% on average relative to evaluated state-of-the-art baselines. Beyond suppressing harmful outputs, it sustains deceptive engagement, achieving an average DR more than six times that of the strongest baselines and increasing attacker-token consumption by 198.83% on average relative to evaluated baselines. Code and dataset are available at https://github.com/SiyuanLi00/CoopGuard.

cs.CR↗

arXiv2026

Strong imposition of Dirichlet boundary velocities in structure-preserving discretizations of elastodynamics

The imposition of boundary velocities in finite element models of port-Hamiltonian elastodynamics typically relies on Lagrange multipliers, yielding Differential-Algebraic Equations (DAEs). Alternatively, weak imposition methods that maintain an Ordinary Differential Equation (ODE) structure often exhibit poor accuracy at Dirichlet boundaries. To address these limitations, this paper introduces an additive kinematic decomposition at the continuous level, splitting the displacement and velocity fields into a relative dynamic component that vanishes on the boundary and a prescribed lifting function extending into the interior domain. This decomposition induces a distributed port that maps the effects of the boundary actuation inside the domain. By incorporating this mapping into suitable virtual power principles, we derive lifted port-Hamiltonian system (PHS) models that, upon finite element discretization, reduce to ODE systems in which Dirichlet boundary velocities are strongly imposed. The framework is applied to derive 2-field and 4-field formulations suited to distinct PHS geometric representations. Furthermore, we show that under specific shape functions, standard FEM schemes are recovered, demonstrating that the lifting framework in the discrete models is equivalent to the classic algebraic matrix partitioning in computational mechanics practice. The energy-balance properties and computational performance of the proposed methodology are verified through numerical simulations.

cs.CE↗

arXiv2026

Bringing GRACE to Recommendation: Fine-Tuning for Sustainable and Accurate Personalization

Growing concern about environmental sustainability (e.g., reducing carbon emissions and resource use) and public health has motivated ``green'' recommender systems that steer users toward more eco-friendly and healthier choices. However, many existing green recommendation approaches require training new models from scratch, incurring substantial computational and energy costs. Reranking-based methods, meanwhile, introduce an additional sorting stage at inference, increasing latency and computational cost. In this work, we propose GRACE (Green Recommendation via Adaptive Conflict-rEsolution), a fine-tuning framework that integrates item-level sustainability signals (e.g., eco-scores or health indices) into pretrained recommendation models. Since these green values are usually discrete and non-differentiable, existing methods often rely on pairwise comparisons to promote greener items. GRACE instead introduces a differentiable approximation that enables direct optimization of the green criterion. To balance sustainability and personalization quality, GRACE further employs a gradient projection mechanism to mitigate conflicts between the green objective and the accuracy objective during fine-tuning. Experiments on real-world datasets demonstrate that GRACE improves sustainability-oriented recommendation outcomes while generally preserving recommendation accuracy through a controllable preference-anchored update mechanism.

cs.IR↗

arXiv2026

A skew Murnaghan--Nakayama rule for Hopf dual pairs

We develop a uniform skew Murnaghan--Nakayama theory for graded Hopf dual pairs equipped with a nondegenerate Hopf pairing. Using the completed Cauchy element, its grouplike factorization, and the resulting partial contraction operators, we establish a general skew Cauchy identity together with an abstract skew Murnaghan--Nakayama rule. Specializing this framework recovers and extends the classical skew Murnaghan--Nakayama rule for symmetric functions, and yields new skew Murnaghan--Nakayama formulas in several settings, including the dual pairs $(\mathrm{NSym}, \mathrm{QSym}) $ and $(Λ^{(k)}, Λ_{(k)}) $ arising in $k$-Schur theory, as well as the type $C$ affine Grassmannian context. As applications, we obtain generating functions for irreducible characters of Ariki--Koike algebras, including their type $A$ and type $B$ specializations, as well as Hecke--Clifford algebras and $\mathfrak q$-rook monoid algebras. We also give ribbon-tableau expansions for skew $(q,t)$-Kostka polynomials and for the entries of the inverse transition matrix, thereby answering a question of Carbonara (1998). Finally, by specializing the auxiliary alphabet $Y$ to sums of powers of primitive roots of unity, we derive a skew plethystic Murnaghan--Nakayama formula together with a Schur expansion for skew modular Schur functions; as a further consequence, we confirm Walker's conjecture (1994) by showing that if the transition from the modular Schur functions to the Schur basis is trivial in the row indexed by $λ$, then $λ$ must be a $k$-core.

math.CO↗

arXiv2026

Lower Bounds for Linear Minimization Oracle Methods Optimizing over Strongly Convex Sets

We consider the oracle complexity of constrained convex optimization given access to a Linear Minimization Oracle (LMO) for the constraint set and a gradient oracle for the $L$-smooth, $L$-strongly convex objective. This model includes Frank-Wolfe methods and their many variants. Over the problem class of $α$-strongly convex constraint sets $S$, we demonstrate that one can construct hard ``zero-chain'' instances in the classical style of Nemirovski and Yudin. From our new approach to adversarial oracle construction, we prove that no such deterministic method can guarantee a final objective gap less than $\varepsilon$ in fewer than $Ω(\sqrt{L\, \mathrm{diam}(S)^2/\varepsilon})$ iterations. Our lower bound partly matches the accelerated Frank-Wolfe theory of Garber and Hazan (2015) of $O(\sqrt{L(\mathrm{diam}(S)^2+1/α^2)/\varepsilon})$. Second, we consider optimization over $β$-smooth sets, finding that in the modestly smooth regime of $β=Ω(1/\sqrt{\varepsilon})$, no complexity improvement for span-based LMO methods is possible against either compact convex sets or strongly convex sets.

math.OC↗

arXiv2026

Track, Rank, Crack: Epistemic Working Memory Scales Multi-Hop Reasoning in Language Agents

Language agents that interleave reasoning and tool use degrade sharply as reasoning chains lengthen, even when each individual step is easy. We trace this to context dilution: an agent's investigative state (what it has confirmed, what it suspects, and what it still needs) lives only implicitly in a growing context window, where early discoveries are buried under later retrievals. We introduce SLEUTH, which makes this state explicit and actionable through a structured epistemic working memory: the agent maintains Confirmed Facts grounded to sources, Active Hypotheses ranked by evidence, and Open Questions that directly drive its next action. Across five multi-hop benchmarks and five established baselines, SLEUTH's advantage grows with difficulty, from +5 points on HotpotQA to +11 on 4-hop chains, surpassing Reflexion without multiple episodes. Analyzing where the remaining gap lies, we identify the evidence sufficiency problem: agents often find the answer but fail to commit, exhausting their budget on needless verification. A lightweight commitment trigger fixes this, but only when the agent already maintains structured state: the identical trigger applied to an unstructured agent yields no improvement, isolating organized epistemic state as the necessary condition for effective commitment. Finally, enforcing protocol adherence on a weaker model recovers up to +19 points on the hardest problems, showing that how an agent organizes its reasoning, not raw model capability, is the active ingredient for scaling multi-hop reasoning.

cs.LG↗

arXiv2026

XR-1: Towards Versatile Vision-Language-Action Models via Learning Unified Vision-Motion Representations

Recent progress in large-scale robotic datasets and vision-language models (VLMs) has advanced research on vision-language-action (VLA) models. However, existing VLA models still face two fundamental challenges: (i) producing precise low-level actions from high-dimensional observations, (ii) bridging domain gaps across heterogeneous data sources, including diverse robot embodiments and human demonstrations. Existing methods often encode latent variables from either visual dynamics or robotic actions to guide policy learning, but they fail to fully exploit the complementary multi-modal knowledge present in large-scale, heterogeneous datasets. In this work, we present X Robotic Model 1 (XR-1), a novel framework for versatile and scalable VLA learning across diverse robots, tasks, and environments. XR-1 introduces the \emph{Unified Vision-Motion Codes (UVMC)}, a discrete latent representation learned via a dual-branch VQ-VAE that jointly encodes visual dynamics and robotic motion. UVMC addresses these challenges by (i) serving as an intermediate representation between the observations and actions, and (ii) aligning multimodal dynamic information from heterogeneous data sources to capture complementary knowledge. To effectively exploit UVMC, we propose a three-stage training paradigm: (i) self-supervised UVMC learning, (ii) UVMC-guided pretraining on large-scale cross-embodiment robotic datasets, and (iii) task-specific post-training. We validate XR-1 through extensive real-world experiments with more than 14,000 rollouts on six different robot embodiments, spanning over 120 diverse manipulation tasks. XR-1 consistently outperforms state-of-the-art baselines such as $π_{0.5}$, $π_0$, RDT, UniVLA, and GR00T-N1.5 while demonstrating strong generalization to novel objects, background variations, distractors, and illumination changes. Our project is at https://xr-1-vla.github.io/.

cs.RO↗

arXiv2026

Constraints on Axion-Like Particles with the Silicon Detector at a Nuclear Reactor

Axion and axion-like particles (ALPs), predicted in various extensions of the Standard Model, can be abundantly produced in nuclear reactors via the Primakoff process. In this work, we explore the detection of ALPs in silicon detectors through plasmon excitations. Owing to their relativistic nature, reactor-produced ALPs can efficiently excite plasmon resonances, while the accompanying energetic photon typically escapes from the thin detector without depositing an appreciable amount of energy. Utilizing the data from the Connie and Atucha-II experiments, we set the 90\% confidence level upper limits on the ALP-photon coupling $g_{aγγ}$ over the axion mass range $0.1-100$ keV. We further show that, for an exposure of 30 kg$\cdot$yr, the projected sensitivity of vIOLETA exceeds the current NEON limit by a factor of three in the same mass range. This improvement would expand the explored region of the QCD axion and ALP parameter space.

hep-ph↗

arXiv2026

Detecting light dark matter with prompt-delayed events in neutrino experiments

We demonstrate the prompt-delayed signals induced by knockout neutrons from the quasi-elastic scattering in neutrino experiments provides a new avenue for detecting light dark matter. As an illustration, we consider the detection of atmospheric dark matter in the liquid scintillator detectors. The results show that the constraint on the DM-nucleon interaction from KamLAND is approximately one order of magnitude more stringent than those obtained from the elastic nuclear recoil signals in dark matter direct detection experiments. Furthermore, a larger volume neutrino experiment, such as JUNO, is expected to significantly enhance the light dark matter detection sensitivity through the quasi-elastic scattering.

hep-ph↗

arXiv2026

Direct Detection of Leptophobic Dark Matter with Electronic Collective Excitations

Some new-generation dark matter detection experiments are primarily designed to search for the dark matter-electron interactions, but they can also be utilized to probe models in which dark matter couples exclusively to nucleon via the quantum effects. The hadronic loop-induced interactions can directly excite plasmons in semiconductors, thereby providing an additional channel for detecting the leptophobic dark matter. In this work, we investigate plasmon excitations in silicon detectors induced by boosted dark matter and cosmic-ray up-scattering dark matter via the hadronic loop process. By analyzing the available experimental data, we derive new exclusion limits on the leptophobic dark matter-nucleon scattering cross section in the sub-MeV mass range.

hep-ph↗

arXiv2026

Beyond Semantic Understanding: Preserving Collaborative Frequency Components in LLM-based Recommendation

Recommender systems in concert with Large Language Models (LLMs) present promising avenues for generating semantically-informed recommendations. However, LLM-based recommenders exhibit a tendency to overemphasize semantic correlations within users' interaction history. When taking pretrained collaborative ID embeddings as input, LLM-based recommenders progressively weaken the inherent collaborative signals as the embeddings propagate through LLM backbones layer by layer, as opposed to traditional Transformer-based sequential models in which collaborative signals are typically preserved or even enhanced for state-of-the-art performance. To address this limitation, we introduce FreLLM4Rec, an approach designed to balance semantic and collaborative information from a spectral perspective. Item embeddings that incorporate both semantic and collaborative information are first purified using a Global Graph Low-Pass Filter (G-LPF) to preliminarily remove irrelevant high-frequency noise. Temporal Frequency Modulation (TFM) then actively preserves collaborative signal layer by layer. Note that the collaborative preservation capability of TFM is theoretically guaranteed by establishing a connection between the optimal but hard-to-implement local graph fourier filters and the suboptimal yet computationally efficient frequency-domain filters. Extensive experiments on four benchmark datasets demonstrate that FreLLM4Rec successfully mitigates collaborative signal attenuation and achieves competitive performance, with improvements of up to 8.00\% in NDCG@10 over the best baseline. Our findings provide insights into how LLMs process collaborative information and offer a principled approach for improving LLM-based recommendation systems.

cs.CL↗

arXiv2026

Testing lepton-flavor-violating decay of doubly charged Higgs bosons in type-II seesaw via photon fusion at the high-energy LHC

Tiny neutrino masses can be explained by the type-II seesaw mechanism, where a triplet scalar under $SU(2)_{L}$ is predicted. Collider searches for this exotic scalar have been extensively conducted, especially for its doubly charged component $Δ^{\pm\pm}$. Utilizing the forward detectors at the Large Hadron Collider (LHC), we study the probing sensitivity for the elastic photon fusion production of the scalars $pp\to p(γγ\toΔ^{++}Δ^{--})p$ followed by the lepton-flavor-violating (LFV) decay channels $Δ^{\pm\pm}\to e^{\pm}μ^{\pm}$. With a high center-of-mass energy of 100 TeV and several luminosity scenarios, we can extensively broaden the exclusion bounds in the parametric space of Br$(Δ^{\pm\pm}\to e^{\pm}μ^{\pm})$ versus the triplet scalar mass $m_Δ$. Specifically, at the 100 TeV LHC with an integrated luminosity of 3 ab$^{-1}$, the mass exclusion limit at 95\% C.L. can reach around 1150 GeV with the assumption of inverted neutrino mass hierarchy.

hep-ph↗

arXiv2026

Long-time behaviour of two-dimensional Navier-Stokes equations in the presence of Couette flow on the half plane

In this paper, we study the long-time behavior of solutions to the two-dimensional Navier-Stokes equations in the presence of Couette flow on the half plane with Navier-slip boundary conditions. We prove that the total vorticity will approach \begin{align*} -1+\frac{M_2(ω_{0})}{ν^{3/2}(1+t)^{5/2}} \barΩ\left( \frac{x}{\sqrt{ν(1+t)^3}}, \frac{y}{\sqrt{ν(1+t)}} \right), \end{align*} where $-1$ is the vorticity of the Couette flow and $\barΩ$ is the kernel of a Fokker-Planck type operator $\mathcal{L}=\partial_Y^2+\frac32 X\partial_X+\frac12 Y\partial_Y+\frac52-Y\partial_X$. In the proof, we introduce a new idea of studying the spectrum of such type operators with boundary.

math.AP↗

arXiv2026

FedSDR: Federated Self-Distillation with Rectification

Federated fine-tuning of Large Language Models faces severe statistical heterogeneity. However, existing model-level defenses often overlook the root cause: intrinsic data distribution mismatches. In this work, we first establish Federated Self-Distillation (FedSD) as a fundamental and potent strategy. By projecting client representations into a smoothed ``model-understanding space,'' FedSD alone serves as a universal booster, demonstrating superior performance over conventional algorithms. Despite its success, we identify a subtle trade-off termed the Rewrite Paradox -- unconstrained self-distillation can inadvertently increase hallucinations and redundancy. To refine this paradigm, we further propose FedSDR (Federated Self-Distillation with Rectification), the ultimate reinforced framework. It augments FedSD with a dual-stream mechanism: a local LoRA-S (Smoothing) branch to implicitly absorb heterogeneity via distilled data, and a parallel global LoRA-R (Rectification) branch anchored to raw data to enforce factual correctness. By selectively aggregating only LoRA-R, FedSDR yields a globally aligned and faithful model. Extensive experiments verify its superior performance.

cs.LG↗

arXiv2026

On the (In-)Security of the Shuffling Defense in the Transformer Secure Inference

For Transformer models, cryptographically secure inference ensures that the client learns only the final output, while the server learns nothing about the client's input. However, securely computing nonlinear layers remains a major efficiency bottleneck due to the substantial communication rounds and data transmission required. To address this issue, prior works reveal intermediate activations to the client, allowing nonlinear operations to be computed in plaintext. Although this approach significantly improves efficiency, exposing activations enables adversaries to extract model weights. To mitigate this risk, existing works employ a shuffling defense that reveals only randomly permuted activations to the client. In this work, we show that the shuffling defense is not as robust as previously claimed. We propose an attack that aligns differently shuffled activations to a common permutation and subsequently exploits them to extract model weights. Experiments on Pythia-70m and GPT-2 demonstrate that the proposed attack can align shuffled activations with mean squared errors ranging from $10^{-9}$ to $10^{-6}$. With a query cost of approximately \$1, the adversary can recover model weights with L1-norm differences ranging from $10^{-4}$ to $10^{-2}$ compared to the oracle weights.

cs.CR↗