arXiv subjects

Liang Liu

Publications and source records attributed to Liang Liu.

At least 37 records · Page 2Linked to original sources

arXiv2026

ToolPrivacyBench: Benchmarking Purpose-Bound Privacy in Tool-Using LLM Agents

Large language models (LLMs) have increasingly moved from standalone text generation systems to agents that invoke external tools, access environments, and execute multi-step tasks. However, conventional function-calling benchmarks mainly evaluate task completion and API correctness, while privacy evaluation benchmarks typically focus on final responses or privacy judgments. Neither perspective captures purpose-bound information flow across an executed multi-tool trajectory. Motivated by this limitation in current agent evaluation, ToolPrivacyBench audits whether task-private atoms are routed only to authorized tools and downstream sinks, thereby evaluating both task completion and privacy over-disclosure during tool use. The benchmark contains 2,150 cases, including 1,150 fully synthetic privacy-sensitive business workflows and 1,000 cases adapted from existing multi-tool and function-calling benchmarks. Each case is represented by a policy knowledge base. After an agent executes against mock business backends, the evaluator compares recorded tool arguments and backend audit logs with this policy knowledge base. The evaluation covers nine widely used agents to characterize purpose-bound privacy over-disclosure. The results show that successful tool execution does not imply appropriate privacy disclosure: an agent may complete a task while transmitting unnecessary private information through intermediate tool calls. ToolPrivacyBench therefore formalizes a need-to-know disclosure boundary, under which each tool should receive only the information necessary for its stated purpose, and uses trajectory-level auditing to identify privacy over-disclosure in multi-tool workflows.

cs.CR↗

arXiv2026

Efficient Analytic Uncertainty Quantification for Multi-Modal Regression

Efficient uncertainty quantification (UQ) is essential for trustworthy large-scale learning. Existing UQ methods for regression tasks mainly operate under the assumption that the conditional label marginal satisfies single-peak parametric models, e.g., Gaussians, where the negative log-likelihood function simplifies to the mean square error. However, such single-peak assumptions fail in regression tasks featuring multi-modal distributions. On the other hand, semi-parametric methods which achieve strong regression performance for multi-modal distributions often lack efficient quantification on their prediction variances. In this work, we extend UQ techniques based on Variational Bayesian Inference (VBI) to two widely used semi-parametric regression models that yield histogram-like reconstructions of the conditional label densities: Quantile Regression (QR) and Classification Restoration (CR). Our approach introduces a unified, distribution-agnostic framework that simultaneously achieves accurate estimation of complex conditional distributions and highly efficient UQ. Theoretically, our method is grounded in novel formulations of QR and CR within the VBI framework, yielding analytic Evidence Lower Bounds (ELBO) to streamline training and a closed-form or analytically approximated predictive density for efficient inference. Empirically, we evaluate our methods on three large-scale regression benchmarks with multi-modal label distributions. Our framework outperforms state-of-the-art multi-modal regression baselines, and even matches predictive performance of computationally expensive ensemble models. Furthermore, by leveraging epistemic uncertainty estimation, our approach enables highly data-efficient active learning strategies.

cs.LG↗

arXiv2026

MemGUI-Agent: An End-to-End Long-Horizon Mobile GUI Agent with Proactive Context Management

MLLM-based mobile GUI agents have made substantial progress on short-horizon tasks, yet remain unreliable on long-horizon tasks that require retaining intermediate facts across many steps and app transitions. We attribute this limitation to ReAct-style prompting, which passively accumulates per-step records, leading to prompt explosion and dilution of critical cross-app facts. To address this, we introduce MemGUI-Agent, an end-to-end long-horizon mobile GUI agent with proactive context management. MemGUI-Agent is built on Context-as-Action (ConAct), which casts context management as first-class actions emitted by the same policy that selects UI actions. Instead of passively appending history, ConAct maintains three structured context fields: folded action history, folded UI state, and recent step record, preserving critical UI facts while keeping context compact. To make proactive context management learnable across model scales, we construct MemGUI-3K, a 2,956-trajectory dataset with full ConAct annotations for supervised training and offline analysis. Training an 8B model on MemGUI-3K produces MemGUI-8B-SFT, an 8B MemGUI-Agent that achieves the best open-data 8B performance on MemGUI-Bench and generalizes to the out-of-distribution MobileWorld benchmark. Code, data, and trained models will be released at https://memgui-agent.github.io/.

cs.HC↗

arXiv2026

Wisdom of Committee: Diverse Distillation from Large Foundation Models and Domain Experts

Knowledge distillation from foundation models to compact domain models is challenging due to substantial gaps in capacity, architecture, and modality. For example, in our experiments, distilling from a 76M-parameter language model to a 2M-parameter recommender closes less than 40% of the performance gap between the undistilled student and the teacher. We show that introducing domain-specific experts -- which share the student's architectural characteristics -- alongside the foundation model as a diverse teacher committee significantly improves transfer. However, standard multi-teacher methods fail to exploit this diversity: naively combining heterogeneous teachers can degrade performance below single-teacher distillation. To address this, we propose DiverseDistill, an interactive distillation framework that employs a learnable Question-Answer mechanism to generate teacher-conditioned queries and align heterogeneous teacher outputs into the student's representation space. Unlike methods requiring gradient-based co-optimization or architectural modification of teachers, DiverseDistill operates with frozen teachers using only forward-pass inference through their intermediate layers: no parameter updates, no co-training, and no architectural surgery. A dynamic teacher importance mechanism further reduces training cost by filtering low-relevance teachers per sample (e.g., ~30% fewer forward passes with no quality loss for recommendation tasks), while the entire Distillation Module is discarded after training, adding zero inference overhead. Evaluations on recommendation (38x compression) and vision (3.6x compression) tasks demonstrate that DiverseDistill recovers 73-114% of the teacher-student performance gap, consistently outperforming all single- and multi-teacher baselines.

cs.LG↗

arXiv2026

Leveraging Metric Depth for Relative Depth Prediction

We present our solution to the 2025 SoccerNet Monocular Depth Estimation Competition Challenge. Predicting the relative depth in football scenarios is challenging, especially with only thousands of training samples available. To address this issue, our method leverages the powerful zero-shot capabilities of models pretrained on large-scale datasets to learn metric depth for effective relative depth prediction, achieving a score of $2.68 \times 10^{-3}$ on the challenge set.

cs.CV↗

arXiv2026

Efficient Minimal Solvers for Relative Pose Estimation in Autonomous Driving Applications

With the advancement of visual sensing systems, computer vision is playing an increasingly important role in autonomous driving and robot navigation. Relative pose estimation in multi-camera systems is essential for accurate vehicle localization and environment perception, demanding high real-time performance and robustness. Existing methods, however, often involve high computational costs and rely heavily on abundant feature matches, limiting their applicability in time-sensitive driving scenarios. To address these limitations, this paper introduces a unified framework for efficient relative pose estimation, built upon a novel translation parameterization and first-order rotation approximation. Within this framework, we propose three efficient minimal solvers specifically designed for autonomous vehicles. The first solver integrates the vertical direction prior from Inertial Measurement Units (IMUs), the second utilizes the rotation axis direction prior during steering maneuvers, and the third is designed for planar motion - a realistic assumption for ground vehicles operating on structured roads. By reducing both the minimal number of point correspondences and the algebraic complexity, our methods enable faster hypothesis generation within RANSAC-based pipelines, improving suitability for real-time systems. Extensive experiments on synthetic datasets and the KITTI autonomous driving benchmark demonstrate that the proposed solvers achieve a favorable balance between speed and accuracy compared to existing state-of-the-art algorithms.

cs.RO↗

arXiv2026

Multi-view imaging in networked sensing systems: A covariance-based approach

This paper considers multi-view imaging in a sixth-generation (6G) integrated sensing and communication network, which consists of a transmit base-station (BS), multiple receive BSs connected to a central processing unit (CPU), and multiple extended targets. Our goal is to devise an effective multi-view imaging technique that can jointly leverage the targets' echo signals at all the receive BSs to precisely construct the image of these targets. To achieve this goal, we propose a two-phase approach. In Phase I, each receive BS recovers an individual image based on the sample covariance matrix of its received signals. Specifically, we propose a novel covariance-based imaging framework to jointly estimate effective scattering intensity and grid positions, which reduces the number of estimated parameters leveraging channel statistical properties and allows grid adjustment to conform to target geometry. In Phase II, the CPU fuses the individual images of all the receivers to construct a high-quality image of all the targets. Specifically, we design edge-preserving natural neighbor interpolation (EP-NNI) to map individual heterogeneous images onto common and finer grids, and then propose a joint optimization framework to estimate fused scattering intensity and BS fields of view. Extensive numerical results show that the proposed scheme significantly enhances imaging performance, facilitating high-quality environment reconstruction for future 6G networks.

eess.SP↗

arXiv2026

A Scalable 256-Antenna Distributed MIMO Testbed with Real-Time Fully Digital Beamforming

Distributed massive MIMO (D-MIMO) is a promising technology for future generation wireless systems as it takes advantage of both an increased array aperture and a decentralized processing architecture and topology. In order to truly understand the possibilities and limitations of these approaches in real scenarios, practical realization of testbeds is an essential step in the technology advancement. This work presents the Lund University Large Intelligent Surface testbed -- LuLIS, that can operate up to 256 coherent radio frequency (RF) chains using 16 AMD Zynq UltraScale RFSoC ZCU216 evaluation boards acting as distributed processing nodes. Real-time processing is facilitated by acceleration and distribution of MIMO processing algorithms on the FPGA fabric of the boards. The system is easily scalable, as increasing the number of antennas is done in multiples of 16 by adding more RFSoCs, which also implies addition of another processing node. The design allows up-scaling without hardware redesign, introduction of large latencies or data transfer overhead. The testbed is flexible in terms of deployment, with options of fully distributing the nodes (as in D-MIMO) or co-locating them (as in more traditional Massive MIMO). A detailed description of the implementation of the testbed is presented and initial results are shown for an uplink (UL) transmission from four single-antenna user equipments (UEs) to 64, 128 and 256 base-station antennas.

eess.SP↗

arXiv2026

Active Evidence-Seeking and Diagnostic Reasoning in Large Language Models for Clinical Decision Support

Large language models perform well on static medical examinations, yet clinical diagnosis often requires iterative evidence gathering under uncertainty. Building on prior interactive evaluation efforts, we introduce an OSCE-inspired standardized patient simulator and a controlled, reproducible benchmark for active diagnostic inquiry. Across 468 cases and 15 models in our protocol, we observe that multi-turn evidence seeking reduces diagnostic accuracy by 12.75% and lowers supporting-evidence quality by 24.36% relative to full-context evaluation; error analyses associate these drops with premature diagnostic closure and inefficient questioning. Together, these results suggest that static full-context benchmarks may overestimate performance in interactive evidence-seeking settings, motivating complementary interactive assessment for safer clinical decision support.

cs.AI↗

arXiv2026

Multiple Superconducting Phases in Rhombohedral Heptalayer Graphene

Crystalline rhombohedral multilayer graphene (RMG) has emerged as an ideal platform for studying unconventional superconductivity. Here, we report the observation of superconductivity in moiréless rhombohedral heptalayer graphene (RHG) at zero magnetic field. The superconducting phases emerge at low displacement electric fields (|D| < 0.2 V/nm) and are symmetrically distributed about D = 0, with one robust state exhibiting zero resistance and two weaker superconducting features. Comparisons with rhombohedral pentalayer graphene (RPG) reveal distinct perpendicular magnetic-field responses, and quantum oscillation measurements indicate that superconductivity in RHG arises from a half-metallic normal state. These results highlight the strong dependence of superconductivity on layer number and electronic structure in RMG systems and provide new insights into its microscopic origin.

cond-mat.mes-hall↗

arXiv2026

Benchmarking State-of-the-Art Theory and Empirical Models of Pionless Neutrino-Argon Scattering in GENIE

Upcoming experiments need improved simulations of neutrino scattering. This work uses the popular GENIE event generator to test a variety of neutrino interaction models against recent MicroBooNE measurements of pionless charged-current interactions. The GENIE code can easily interchange model components, including nucleon form factor parameterizations, quasielastic cross-section calculations, treatments of the nuclear ground state and hadronic final-state interactions. Leveraging this software capability in comparisons with MicroBooNE data, the performance of some of GENIE's most theoretically sophisticated model components is evaluated and contrasted with more empirically-driven alternatives.

hep-ph↗

arXiv2026

What Will Happen Next: Large Models-Driven Deduction for Emergency Instances

Traditional simulation methods reproduce occurred emergency instances through presetting to assist people in risk assessment and emergency decision-making. However, due to the lack of randomness and diversity, existing simulation systems struggle to fully explore the potential risk as emergency instances are scarce. In contrast, Large Models (LMs) can dynamically adjust generation strategies to introduce controllable randomness, while also possessing extensive prior knowledge and cross-domain knowledge transfer capabilities. Inspired by it, we propose the LMs-driven World Line Divergence System (WLDS), which enables diversified visualization and deduction of emergency instances in different domains. WLDS leverages LMs to deduce emergency instances in various development directions, and introduces the factual calibration and logical calibration mechanism to ensure factual accuracy and logical rigor during the deduction process. The interactive module can independently select deduction directions to avoid potential hallucinations that are difficult for the system to identify. Furthermore, by introducing the visualization module, WLDS forms simulation and deduction that combine text and images, which enhances interpretability. Extensive experiments conducted on the proposed Emergency Instances Deduction (EID) benchmark dataset demonstrate that WLDS achieves high-precision and high-fidelity simulation and deduction of emergency instances in multiple specific domains. Relevant experiments further demonstrate that WLDS can generate more emergency instances deduction data for users and provide support for better decision-making in similar emergency instances in the future.

cs.AI↗

arXiv2026

Multi-User XR Offloading via Massive MIMO: A System-Level Analysis using a Real-Life Dataset

SLAM is one of the biggest bottlenecks of XR devices, which have strict requirements for latency, power consumption, and user satisfaction. A solution that has been proposed and studied to meet the requirements is to offload SLAM to a remote server, which leverages computational hardware but may suffer due to incurred delays and transmission power. In this work, we propose offloading SLAM using Massive MIMO, which is attractive due to lower latencies, transmission power, and a more reliable link for multiple users. A framework for system-level analysis of latency and localisation error in multi-user offloaded XR with Massive MIMO has been proposed, and a case study with varying system-level parameters has been performed with it. The case study showed that there are important trade-offs between latency, localisation error, and device transmission power. We find that Massive MIMO is a promising technology for XR offloading, but that further evaluations including complete device power consumption are needed to get the full picture.

eess.SP↗

arXiv2026

Beyond Item IDs: Scaling Short-Form-Video Recommendation via Semantic-Native Long Sequence Modeling

Capturing user interests across extensive watch histories is critical for short-form video recommendation, yet scaling sequence length is limited by two bottlenecks: the semantic sparsity of atomic Video IDs and the quadratic computational complexity of Transformers. Traditional orthogonal Video IDs fail to capture content relationships and demand large embedding tables, while the quadratic complexity of self-attention restricts the maximum sequence length under strict industrial latency and resource constraints. In this work, we present a production-deployed framework for modeling ultra-long user behavior sequences at a billion-user scale. We first address the representation bottleneck by adopting content-native Semantic IDs. By utilizing depth-truncated, coarse-grained Semantic IDs, we shrink the embedding table size from corpus cardinality. This compact representation naturally generalizes to cold-start content through shared semantic prefixes. Second, to overcome the sequence scaling barrier, we introduce a Global-Aware Compression Transformer that leverages non-parametric temporal folding and unified global query integration to effectively condense the sequence, alleviating both the memory and computational bottlenecks of standard self-attention. Offline profiling on our computing infrastructure demonstrates an order-of-magnitude reduction in peak memory footprint and a drastic decrease in computational overhead. This efficiency gain enables supporting longer sequence lengths at an affordable cost in production, yielding substantial online gains in satisfied user engagement and satisfied content consumption in large-scale online A/B tests.

cs.IR↗

arXiv2026

OR-VSKC: Resolving Visual-Semantic Knowledge Conflicts in Operating Rooms with Synthetic Data-Guided Alignment

Automated identification of surgical safety risks is critical for improving patient outcomes; however, Multimodal Large Language Models (MLLMs) frequently suffer from Visual-Semantic Knowledge Conflicts (VS-KC), a phenomenon where models possess safety knowledge but fail to activate it during visual inspection. Investigating this alignment gap in operating rooms (ORs) is impeded by a critical bottleneck: the scarcity and privacy constraints of real-world OR data depicting safety violations. To address this, we introduce OR-VSKC, a benchmark for studying VS-KC and surgical risk perception in strictly regulated OR environments. Constructed via our Protocol-to-Pixel Generative Framework, OR-VSKC comprises 28,190 high-fidelity synthetic images grounded in authoritative safety standards, complemented by a 713-image expert-authored challenge subset validated by multiple experts. The full benchmark is built from authentic OR contexts drawn from the 4D-OR and CAMMA-MVOR datasets, where the 4D-OR-based portion serves as the primary benchmark core and the CAMMA-MVOR-based portion is reserved for external validation and cross-dataset generalization analysis. Evaluations of state-of-the-art MLLMs reveal substantial reliability gaps even in advanced generalist models. Furthermore, experiments show that fine-tuning on OR-VSKC effectively mitigates VS-KC and enables robust generalization to unseen camera viewpoints. We open-source the code and dataset to support reproducible research in safety-critical medical environments. The source code is available at https://github.com/zgg2577/VS-KC.

cs.CV↗

arXiv2026

Tunable high-Chern-number Chern insulators in rhombohedral tetralayer graphene/hBN moiré superlattices

Moiré superlattices based on rhombohedral multilayer graphene have emerged as a highly tunable platform for engineering correlated topological phases. Here, we systematically investigate the transport properties of the hole-doped side in rhombohedral tetralayer graphene/ hexagonal boron nitride (hBN) moiré superlattices across a range of twist angles and alignment orientations. Notably, we observed multiple high-Chern-number Chern insulators, including the previously reported integer Chern insulator with Chern number C = -4 at moiré filling factor v = -1 and newly discovered symmetry-broken Chern insulating states with C = +3, $\pm$2, $\pm$1 at fractional moiré fillings of v = -2.5 or -2.6. These Chern insulating states emerge in both hBN alignment, but exhibit a sensitive moiré wavelength dependence. Our findings demonstrate the exceptional tunability of these high-Chern-number states via moiré wavelength, displacement electric field and external magnetic field, underscoring the distinct topological landscape realized in hole-doped RTG/hBN moiré superlattices.

cond-mat.mes-hall↗

arXiv2026

Symplectic connection third-order Hall effect in a room-temperature ferromagnet

Third-order nonlinear Hall effects (THE) have recently attracted considerable experimental interest as powerful probes for quantum geometric properties in emergent quantum materials, encompassing quadrupole moments of quantum metric and Berry curvature. Here, we report a fundamentally new THE in room-temperature van der Waals ferromagnet Fe3GaTe2 from second-order Berry connection polarizability, which manifests a higher-order characterization of band geometry called symplectic connection. Our observations show that the third-order transverse response in Fe3GaTe2 is odd to magnetization, vanishes above the Curie temperature and remains independent of driving current directions. Scaling law analysis combined with first-principles calculations establishes this response as the symplectic-connection-induced THE. This discovery opens the door to probing high-order quantum geometric properties beyond Berry curvature and quantum metric through nonlinear transport, unveiling the potential of exploring nonlinear Hall phenomena in broad classes of magnets without breaking inversion symmetry. Moreover, the room-temperature manipulation of THE holds promises for device applications based on harnessing the quantum-geometric connection structure.

cond-mat.mes-hall↗

arXiv2026

Networked Tracking of Multiple Moving Targets in 6G Network

This paper considers a networked tracking architecture in 6G integrated sensing and communication (ISAC) systems, where multiple base stations (BSs) cooperatively transmit radio signals and process received echo signals to track multiple moving targets. Compared to the single-BS counterpart, networked tracking allows the moving targets to be associated with different BSs over time such that the wireless resources can be dynamically allocated among BSs based on target locations. However, networked tracking imposes new challenges for algorithm design and resource allocation. In this paper, we first design the networked Kalman Filter (NKF) that is suitable for multi-BS based tracking, then characterize the posterior Cramer-Rao bound (PCRB) under this NKF, and last design the beamforming vectors of all the BSs to minimize the tracking PCRB. Numerical results show that our dynamic beamforming design can properly associate the targets to the suitable BSs at various sensing blocks and reduce the tracking mean-squared error (MSE).

eess.SP↗