arXiv subjects

Yan Liu

Publications and source records attributed to Yan Liu.

At least 109 records · Page 6Linked to original sources

arXiv2026

SmartGuard: Leveraging Large Language Models for Network Attack Detection through Audit Log Analysis and Summarization

End-point monitoring solutions are widely deployed in today's enterprise environments to support advanced attack detection and investigation. These monitors continuously record system-level activities as audit logs and provide deep visibility into security events. Unfortunately, existing methods of semantic analysis based on audit logs have low granularity, only reaching the system call level, making it difficult to effectively classify highly covert behaviors. Additionally, existing works mainly match audit log streams with rule knowledge bases describing behaviors, which heavily rely on expertise and lack the ability to detect unknown attacks and provide interpretive descriptions. In this paper, we propose SmartGuard, an automated method that combines abstracted behaviors from audit event semantics with large language models. SmartGuard extracts specific behaviors (function level) from incoming system logs and constructs a knowledge graph, divides events by threads, and combines event summaries with graph embeddings to achieve information diagnosis and provide explanatory narratives through large language models. Our evaluation shows that SmartGuard achieves an average F1 score of 96\% in assessing malicious behaviors and demonstrates good scalability across multiple models and unknown attacks. It also possesses excellent fine-tuning capabilities, allowing experts to assist in timely system updates.

cs.CR↗

arXiv2026

TemporalBench: A Benchmark for Evaluating LLM-Based Agents on Contextual and Event-Informed Time Series Tasks

It is unclear whether strong forecasting performance reflects genuine temporal understanding or the ability to reason under contextual and event-driven conditions. We introduce TemporalBench, a multi-domain benchmark designed to evaluate temporal reasoning behavior under progressively richer informational settings. TemporalBench adopts a four-tier task taxonomy that examines historical structure interpretation, context-free forecasting, contextual temporal reasoning, and event-conditioned prediction across four real-world domains: retail, healthcare, energy, and physical systems. By controlling access to future targets and contextual information, the benchmark enables a diagnostic analysis of whether models can correctly interpret temporal patterns, align them with external context, and adapt predictions when conditions change. Extensive baseline experiments show that strong numerical forecasting accuracy does not reliably translate into robust contextual or event-aware temporal reasoning; instead, existing agent frameworks exhibit fragmented strengths and systematic failure modes that remain largely hidden under forecasting-only benchmarks. The TemporalBench dataset is publicly available at https://huggingface.co/datasets/Melady/TemporalBench, and we additionally provide a public leaderboard at https://huggingface.co/spaces/Melady/TemporalBench_Leaderboard.

cs.AI↗

arXiv2026

De-conflating Preference and Qualification: Constrained Dual-Perspective Reasoning for Job Recommendation with Large Language Models

Professional job recommendation involves a complex bipartite matching process that must reconcile a candidate's subjective preference with an employer's objective qualification. While Large Language Models (LLMs) are well-suited for modeling the rich semantics of resumes and job descriptions, existing paradigms often collapse these two decision dimensions into a single interaction signal, yielding confounded supervision under recruitment-funnel censoring and limiting policy controllability. To address these challenges, We propose JobRec, a generative job recommendation framework for de-conflating preference and qualification via constrained dual-perspective reasoning. JobRec introduces a Unified Semantic Alignment Schema that aligns candidate and job attributes into structured semantic layers, and a Two-Stage Cooperative Training Strategy that learns decoupled experts to separately infer preference and qualification. Building on these experts, a Lagrangian-based Policy Alignment module optimizes recommendations under explicit eligibility requirements, enabling controllable trade-offs. To mitigate data scarcity, we construct a synthetic dataset refined by experts. Experiments show that JobRec consistently outperforms strong baselines and provides improved controllability for strategy-aware professional matching.

cs.AI↗

arXiv2026

Structure-Guided Memory Consolidation for Mitigating Compounding Errors in Literature Review Generation

Compounding errors pose a significant challenge in automatic literature review generation, as inaccuracies can cascade across multi-stage retrieval and generation workflows. Existing self-correction strategies often lack mechanisms to effectively track and consolidate verified information throughout the process, making it difficult to prevent error accumulation and propagation. In this paper, we propose Structure-Guided Memory Consolidation (SGMC), a novel framework that incrementally consolidates and verifies information using structured representations at each stage of the literature review pipeline. SGMC consists of three key modules: Tree-Guided Memory for hierarchical literature retrieval and outline generation, Hub-Guided Memory for evidence extraction and iterative content refinement, and Self-Loop Memory for proactive error correction via historical feedback. Extensive experiments on public benchmarks and a newly constructed large-scale dataset demonstrate that SGMC achieves state-of-the-art performance in citation accuracy and content quality, significantly mitigating compounding errors in long-form literature review generation.

cs.CE↗

arXiv2026

Shear subdiffusion in non-relativistic holography

We study shear fluctuations in non-relativistic holographic systems coupled to torsional Newton-Cartan geometry, using asymptotically Lifshitz spacetimes in Einstein-Maxwell-dilaton gravity. We identify a universal subdiffusive shear mode characterized by the quartic dispersion relation $ω=-iD_4 k^4$, in sharp contrast to the conventional hydrodynamic diffusion. We derive this result analytically through a systematic higher-order matched asymptotic expansion connecting near-horizon and far-region solutions, and we verify it with direct numerical quasinormal mode calculations. Our numerics demonstrate that the first non-hydrodynamic mode is purely imaginary and gapped, following the dispersion relation $ω=-iω_0-i D k^2$, and that both the hydrodynamic and the first non-hydrodynamic modes pass through pole-skipping points. These results highlight Lifshitz holography as an efficient framework for anomalous transport in strongly coupled non-relativistic quantum matter.

hep-th↗

arXiv2026

State Rank Dynamics in Linear Attention LLMs

Linear Attention Large Language Models (LLMs) offer a compelling recurrent formulation that compresses context into a fixed-size state matrix, enabling constant-time inference. However, the internal dynamics of this compressed state remain largely opaque. In this work, we present a comprehensive study on the runtime state dynamics of state-of-the-art Linear Attention models. We uncover a fundamental phenomenon termed State Rank Stratification, characterized by a distinct spectral bifurcation among linear attention heads: while one group maintains an effective rank oscillating near zero, the other exhibits rapid growth that converges to an upper bound. Extensive experiments across diverse inference contexts reveal that these dynamics remain strikingly consistent, indicating that the identity of a head,whether low-rank or high-rank,is an intrinsic structural property acquired during pre-training, rather than a transient state dependent on the input data. Furthermore, our diagnostic probes reveal a surprising functional divergence: low-rank heads are indispensable for model reasoning, whereas high-rank heads exhibit significant redundancy. Leveraging this insight, we propose Joint Rank-Norm Pruning, a zero-shot strategy that achieves a 38.9\% reduction in KV-cache overhead while largely maintaining model accuracy.

cs.LG↗

arXiv2026

Achieving Time Series Reasoning Requires Rethinking Model Design, Tasks Formulation, and Evaluation

Understanding time series data is fundamental to many real-world applications. Recent work explores multimodal large language models (MLLMs) to enhance time series understanding with contextual information beyond numerical signals. This area has grown from 7 papers in 2023 to over 580 in 2025, yet existing methods struggle in real-world settings. We analyze 20 influential works from 2025 across model design, task formulation, and evaluation, and identify critical gaps: methods adapt NLP techniques with limited attention to core time series properties; tasks remain restricted to traditional prediction and classification; and evaluations emphasize benchmarks over robustness, interpretability, or decision relevance. We argue that achieving time series reasoning requires rethinking model design, task formulation, and evaluation together. We define time series reasoning, outline challenges and future directions, and call on researchers to develop unified frameworks for robust, interpretable, and decision-relevant reasoning in real-world applications. The material is available at https://github.com/Eleanorkong/Awesome-Time-Series-Reasoning.

cs.LG↗

arXiv2026

Policy Learning under Endogeneity Using Instrumental Variables

I propose a framework for learning individualized policy rules in observational data settings characterized by endogenous treatment selection and the availability of an instrumental variable. I introduce encouragement rules that manipulate the instrument. By incorporating the marginal treatment effect (MTE) as a policy invariant parameter, I establish the identification of the social welfare criterion for the optimal encouragement rule. Focusing on binary encouragement rules, I propose to estimate the optimal encouragement rule via the Empirical Welfare Maximization (EWM) method and derive the welfare loss convergence rate. I apply my method to advise on the optimal tuition subsidy assignment in Indonesia.

econ.EM↗

arXiv2026

FastStair: Learning to Run Up Stairs with Humanoid Robots

Running up stairs is effortless for humans but remains extremely challenging for humanoid robots due to the simultaneous requirements of high agility and strict stability. Model-free reinforcement learning (RL) can generate dynamic locomotion, yet implicit stability rewards and heavy reliance on task-specific reward shaping tend to result in unsafe behaviors, especially on stairs; conversely, model-based foothold planners encode contact feasibility and stability structure, but enforcing their hard constraints often induces conservative motion that limits speed. We present FastStair, a planner-guided, multi-stage learning framework that reconciles these complementary strengths to achieve fast and stable stair ascent. FastStair integrates a parallel model-based foothold planner into the RL training loop to bias exploration toward dynamically feasible contacts and to pretrain a safety-focused base policy. To mitigate planner-induced conservatism and the discrepancy between low- and high-speed action distributions, the base policy was fine-tuned into speed-specialized experts and then integrated via Low-Rank Adaptation (LoRA) to enable smooth operation across the full commanded-speed range. We deploy the resulting controller on the Oli humanoid robot, achieving stable stair ascent at commanded speeds up to 1.65 m/s and traversing a 33-step spiral staircase (17 cm rise per step) in 12 s, demonstrating robust high-speed performance on long staircases. Notably, the proposed approach served as the champion solution in the Canton Tower Robot Run Up Competition.

cs.RO↗

arXiv2026

Efficient Paths and Dense Rewards: Probabilistic Flow Reasoning for Large Language Models

High-quality chain-of-thought has demonstrated strong potential for unlocking the reasoning capabilities of large language models. However, current paradigms typically treat the reasoning process as an indivisible sequence, lacking an intrinsic mechanism to quantify step-wise information gain. This granularity gap manifests in two limitations: inference inefficiency from redundant exploration without explicit guidance, and optimization difficulty due to sparse outcome supervision or costly external verifiers. In this work, we propose CoT-Flow, a framework that reconceptualizes discrete reasoning steps as a continuous probabilistic flow, quantifying the contribution of each step toward the ground-truth answer. Built on this formulation, CoT-Flow enables two complementary methodologies: flow-guided decoding, which employs a greedy flow-based decoding strategy to extract information-efficient reasoning paths, and flow-based reinforcement learning, which constructs a verifier-free dense reward function. Experiments on challenging benchmarks demonstrate that CoT-Flow achieves a superior balance between inference efficiency and reasoning performance.

cs.AI↗

arXiv2026

The Repulsive Effect of Covariant Effective Quantum Gravity

In General Relativity, gravity around a black hole is universally regarded as an attractive force. However, quantum effects may significantly alter this classical picture and thus affect the dynamics of test particles. In this work, we investigate geodesic motion in a recently proposed covariant effective quantum black hole model, the ZLMY type I model in \href{https://journals.aps.org/prd/abstract/10.1103/PhysRevD.111.L081504}{[Phys.Rev.D 111 (2025) 8, L081504]}. Our analytical study reveals that, at the Planck scale, gravity can exhibit a repulsive character, most notably in trajectories involving turning points. These findings suggest that quantum corrections could fundamentally modify our conventional understanding of gravitational interactions in certain regimes.

gr-qc↗

arXiv2026

Uncertainty-Adjusted Sorting for Asset Pricing with Machine Learning

Machine learning is central to empirical asset pricing, but portfolio construction still relies on point predictions and largely ignores asset-specific estimation uncertainty. We propose a simple change: sort assets using uncertainty-adjusted prediction bounds instead of point predictions alone. Across a broad set of ML models and a U.S. equity panel, this approach improves portfolio performance relative to point-prediction sorting. These gains persist even when bounds are built from partial or misspecified uncertainty information. They arise mainly from reduced volatility and are strongest for flexible machine learning models. Identification and robustness exercises show that these improvements are driven by asset-level rather than time or aggregate predictive uncertainty.

q-fin.PM↗

arXiv2025

Deterministic implementation in single-item auctions

Deterministic auctions are attractive in practice due to their transparency, simplicity, and ease of implementation, motivating a sharper understanding of when they can attain the same outcomes as randomized mechanisms. We study deterministic implementation in single-item auctions under two notions of outcomes: (revenue, welfare) pairs and interim allocations. For (revenue, welfare) pairs, we show a separation in discrete settings: there exists a pair implementable by a deterministic Bayesian incentive-compatible (BIC) auction but not by any deterministic dominant-strategy incentive-compatible (DSIC) auction. For continuous atomless priors, we identify conditions under which deterministic DSIC auctions are equivalent to randomized BIC auctions in terms of achievable outcomes. For interim allocations, under a strict monotonicity condition, we establish a deterministic analogue of Border's theorem for two bidders, providing a necessary and sufficient condition for deterministic DSIC implementability. Using this characterization, we exhibit an interim allocation implementable by a randomized BIC auction but not by any deterministic DSIC auction.

cs.GT↗

arXiv2025

Holmes: Towards Effective and Harmless Model Ownership Verification to Personalized Large Vision Models via Decoupling Common Features

Large vision models (LVMs) achieve remarkable performance in various downstream tasks, primarily by personalizing pre-trained models through fine-tuning with private and valuable local data, which makes the personalized model a valuable intellectual property. Similar to the era of traditional DNNs, model stealing attacks also pose significant risks to LVMs. However, this paper reveals that most existing defense methods (developed for traditional DNNs), typically designed for models trained from scratch, either introduce additional security risks, are prone to misjudgment, or are even ineffective for fine-tuned models. To alleviate these problems, this paper proposes a harmless model ownership verification method for personalized LVMs by decoupling similar common features. In general, our method consists of three main stages. In the first stage, we create shadow models that retain common features of the victim model while disrupting dataset-specific features. We represent the dataset-specific features of the victim model by computing the output differences between the shadow and victim models, without altering the victim model or its training process. After that, a meta-classifier is trained to identify stolen models by determining whether suspicious models contain the dataset-specific features of the victim. In the third stage, we conduct model ownership verification by hypothesis test to mitigate randomness and enhance robustness. Extensive experiments on benchmark datasets verify the effectiveness of the proposed method in detecting different types of model stealing simultaneously. Our codes are available at https://github.com/zlh-thu/Holmes.

cs.CV↗

arXiv2025

On-Demand Control of Input-State-Dependent Single-Photon Scattering in Multi-Mode Waveguides

Precise control of a single photon transport in broadband, multi-mode waveguides is a fundamental challenge for scalable quantum networks. We propose a theoretical scheme for on-demand control of single-photon scattering using a driven $Λ$-type emitter coupled to a rectangular waveguide. By employing the Lippmann-Schwinger formalism, we derive the exact analytical scattering matrix and reveal two key interference mechanisms: electromagnetically induced transparency for complete transmission and Fano resonance for complete reflection. We demonstrate that the single-photon scattering is dynamically engineered by the driving field, enabling a switch between complete transmission and dual-frequency complete reflection. Crucially, in the multi-mode regime, we show that the scattering is governed by quantum interference between modes, making it critically dependent on the input photonic state. By preparing the photon in a specific coherent superposition state, the multi-mode interference is harnessed to achieve Fano resonance-mediated complete reflection. Conversely, a single-mode input suppresses complete reflection. This input-state-dependent scattering establishes a general framework for multi-mode quantum photonics, paving the way for broadband dual-frequency filters, multi-mode quantum routers, and on-chip spectrometers.

quant-ph↗

arXiv2025

Conversational Time Series Foundation Models: Towards Explainable and Effective Forecasting

The proliferation of time series foundation models has created a landscape where no single method achieves consistent superiority, framing the central challenge not as finding the best model, but as orchestrating an optimal ensemble with interpretability. While Large Language Models (LLMs) offer powerful reasoning capabilities, their direct application to time series forecasting has proven ineffective. We address this gap by repositioning the LLM as an intelligent judge that evaluates, explains, and strategically coordinates an ensemble of foundation models. To overcome the LLM's inherent lack of domain-specific knowledge on time series, we introduce an R1-style finetuning process, guided by SHAP-based faithfulness scores, which teaches the model to interpret ensemble weights as meaningful causal statements about temporal dynamics. The trained agent then engages in iterative, multi-turn conversations to perform forward-looking assessments, provide causally-grounded explanations for its weighting decisions, and adaptively refine the optimization strategy. Validated on the GIFT-Eval benchmark on 23 datasets across 97 settings, our approach significantly outperforms leading time series foundation models on both CRPS and MASE metrics, establishing new state-of-the-art results.

cs.AI↗

arXiv2025

Spectroscopic evidences for the spontaneous symmetry breaking at the $SO(5)$ deconfined critical point of $J$-$Q_3$ model

Recent numerical and theoretical studies on the two-dimensional $J$-$Q_3$ model suggests that the deconfined quantum critical point is actually a $SO(5)$-symmetry-enhanced first-order phase transition that is spontaneously broken to $O(4)$. However, this conclusion has mainly relied on finite-size scaling of the entanglement entropy, lacking direct evidence from physical observables.} Here, we investigate the dynamical spectra of spin and bond operators at the deconfined critical point of the $J$-$Q_3$ model using large-scale quantum Monte Carlo simulations, and contrasting them with the well-established $\mathrm{O(3)}$ Wilson-Fisher criticality in the $J_1$-$J_2$ Heisenberg model. Although both models exhibit two gapless magnon modes in the Néel phase, their critical behaviors diverge strikingly. At the $J_1$-$J_2$ critical point, the Higgs mode becomes gapless, yielding three gapless modes that reflect the full restoration of the $\mathrm{O(3)}$ symmetry. {In the $J$-$Q_3$ model, we instead observe four gapless transverse modes at the either side of the transition. This spectral feature, together with the entanglement entropy results, provides direct evidence for the weakly first-order scenario that the deconfined quantum critical point exhibits an emergent $\mathrm{SO(5)}$ symmetry that spontaneously breaks to $\mathrm{O(4)}$.

cond-mat.str-el↗

arXiv2025

The late-time attractor structure of dynamical black branes

The ringdown phase of a perturbed black hole is conventionally described by a linear superposition of quasinormal modes. However, as the AdS black brane approaches its final global equilibrium, this linear quasinormal mode description becomes inadequate, and nonlinear dynamics play a significant role in the late-stage evolution. We show that the interplay between nonlinear evolution and horizon dissipation in general relativity drives dynamical AdS black branes towards the final state along a unique path, independent of their initial perturbations. Through numerical simulations, we identify this late-time attractor and uncover the associated universal nonlinear behavior, characterized by a simple dimensionless relative amplitude in the dual hydrodynamic variables.

hep-th↗