arXiv subjects

Shiqi Liu

Publications and source records attributed to Shiqi Liu.

At least 19 recordsLinked to original sources

arXiv2026

Emotional Preferences as Goal-Priority Regulation

A core question in decision-making for agents is whether the relative priorities of competing lower-level objectives can be determined by emotional preferences autonomously generated by higher-level goals, rather than being externally prespecified. Under changing external environments and evolving internal states, emotions play an important functional role in regulating the relative priorities of competing goals. Inspired by the goal-directed theory of emotion, this paper studies how such preference regulation can be computationally realized through reinforcement learning. We first propose a conception of emergent emotional preference: a high-level goal autonomously induces state-dependent preferences over competing lower-level objectives. This conception is built upon a framework consisting of a multi-objective reinforcement learning inner controller and an outer preference generator. The inner controller provides a repertoire of preference-conditioned goal-directed behaviors, while the outer preference generator learns a mapping from the current state to objective preferences through reinforcement learning on a high-level goal. We operationalize emotional preference as a state-dependent regulation of relative goal priorities that emerges through optimization. Furthermore, we characterize the policy space induced by preference regulation and derive an upper bound on the optimality gap in terms of the representation error of the inner behavioral repertoire. We show that the gap vanishes when the optimal policy can be represented by the available preference-conditioned policies. Experiments in self-constructed multi-objective exploration environments show that the learned preference function exhibits contextual priority switching, graded trade-offs, and temporal persistence, and outperforms the evaluated fixed-preference and handcrafted-preference strategies.

cs.LG↗

arXiv2026

MATEE: Efficiently Bridging the Semantic Gap in TrustZone via Arm Pointer Authentication

Trusted Execution Environments (TEEs) employ hardware-based isolation mechanisms to safeguard the confidentiality and integrity of sensitive code and data. One such prevalent implementation is Arm TrustZone, which partitions the system into the secure and normal (non-secure) worlds. However, this partitioning results in the secure world having very limited visibility into the operating information of the normal world, creating a semantic gap between these two worlds. Specifically, the secure world lacks an effective user identity authentication when receiving data requests from the normal world. Consequently, malicious Client Applications (CAs) in the normal world can deceive Trusted Applications (TAs) in the secure world by utilizing elaborate request parameters, compromising the sensitive data stored by other CAs. We systematically classify these Semantic Gap Vulnerabilities (SGVs) and propose a mate system for the TEE called MATEE to defend against SGVs. MATEE utilizes Arm Pointer Authentication (PA) to bind each request to the corresponding CA's identity and then verifies the identity when the CA accesses sensitive data, thereby preventing malicious request forgery. In particular, MATEE isolates sensitive data of different CAs without modifying existing CAs and TAs. Our evaluation demonstrates that MATEE successfully defends against SGVs with a minimal runtime overhead (2.19%).

cs.CR↗

arXiv2026

More Granular, Less Trust: Enforcing Intra-Process Isolation with Arm CCA in an Untrusted Management Environment

With the increasing adoption of confidential computing, security-sensitive applications are often deployed in confidential virtual machines (CVMs), which reduce reliance on third-party cloud providers. However, privilege attacks originating from the OS remain a significant threat in these environments. Existing finer-grained isolation schemes, such as SHELTER, provide process-level protection but are still vulnerable to intraprocess attacks and potential collusion between the OS and intra-process adversaries. Many current intra-process isolation techniques continue to depend on the OS to manage and enforce isolation domains, leading to a large Trusted Computing Base (TCB). This gap highlights the need for more granular, less trust-dependent confidential computing solutions. In this paper, we present CCAegis, a system that extends the Arm Confidential Compute Architecture (CCA) to enforce intra-process isolation of sensitive data and operations, safeguarding them from both intraprocess adversaries and the OS. We employ static analysis to track the flow of sensitive data and identify functions that handle such data. Permission-switching instructions are inserted at the function call and return points, adjusting permissions via the Granule Protection Table (GPT) to ensure that only designated functions can access the isolated data. Notably, CCAegis places trust solely in the Secure Monitor, which configures the GPTs and manages domain switching, thereby minimizing the TCB. We implemented CCAegis on both an official emulator and a real development board to assess its performance. Our experimental results show that CCAegis effectively isolates sensitive data and operations, with performance overheads ranging from 1.01x to 1.43x compared to the original version across real-world cryptographic workloads.

cs.CR↗

arXiv2026

Temporal Risk on Satellites

Satellite vulnerabilities change over time as orbits shift, power margins tighten, and the space environment deteriorates. However, most cybersecurity risk frameworks still treat threats as static. In practice, the same exploit can be far more damaging during a critical maneuver than during routine operations. We propose a temporal risk assessment framework that makes time an explicit axis in satellite security analysis. It extends existing adversary behavior taxonomies with a five-dimensional temporal capability model and estimates exploitation difficulty across distinct temporal windows of a mission. Rather than producing a single risk score, the framework outputs a series of time-indexed likelihood-impact matrices. It discretizes missions into operationally meaningful time windows and environmental bands to show when systems are most exposed. This view helps operators avoid scheduling sensitive operations in high-risk periods and align defensive resources with a threat landscape that shifts over time.

cs.CR↗

arXiv2026

Embodied Human-Robot Interaction via Acoustics: A MARL Approach with AcoustoBots for Spatial Data Physicalization

Traditional data physicalization is often static and disconnected from real environments, limiting its ability to convey embodied spatial dynamics and engage users. To address this limitation, we present AcoustoBots, a mobile acoustophoretic data-physicalization platform in which TurtleBot3 robots carry upward-facing 8 x 8 ultrasonic phased arrays. Each array levitates a particle whose height (1-10 cm) encodes a local urban scalar value, such as population density, noise, or traffic. A MARL (Multi-Agent Reinforcement Learning) policy based on the Multi-Agent Deep Deterministic Policy Gradient (MADDPG) algorithm, with centralized training and decentralized execution, selects collision-aware navigation actions, while a high-rate Gerchberg-Saxton-Phased Array of Transducers (GS-PAT) acoustic controller maintains trap stability and updates array phases to achieve the commanded height during motion. This creates a closed perception-display-action loop. We evaluate single-robot city-to-city traversal and dual-robot cooperative coverage on a 4 m x 3 m scaled UK map using PhaseSpace-based localization for repeatable multi-robot trials. Results show stable in-motion levitation and consistent, location-dependent height rendering, with task success rates of 90% and 80% for the single and dual-robot regimes, respectively, over 10 trials per regime, and low collision counts. These findings support acoustophoretic levitation as a simple, glanceable, robot-mediated communication cue for embodied human-robot interaction in spatial analytics.

cs.RO↗

arXiv2026

Hierarchical Anti-Aesthetics: Protecting Facial Privacy against Customized Diffusion Models

The rise of customized diffusion models has fueled a boom in personalized visual content creation, but it also introduces serious risks of malicious misuse, thereby posing threats to personal privacy. Image aesthetics are strongly correlated with human perception of image quality. Motivated by this observation, we address facial privacy protection from a novel aesthetic perspective by degrading the generation quality of maliciously customized models, thus reducing facial identity leakage. Specifically, we propose a Hierarchical Anti-Aesthetics (HAA) framework that exploits aesthetic cues at multiple perceptual levels. HAA consists of two key branches: (1) Global Anti-Aesthetics, which degrades overall aesthetics and generation quality by constructing a global anti-aesthetic reward mechanism and a corresponding loss; and (2) Local Anti-Aesthetics, which disrupts facial identity by using a local anti-aesthetic reward mechanism and loss to guide adversarial perturbations toward facial regions. By integrating both branches, HAA achieves anti-aesthetic degradation from a global to a local level during customized generation. Extensive experiments show that HAA outperforms existing methods in identity removal, providing an effective tool for protecting facial privacy.

cs.CV↗

arXiv2026

DINO-Med3D: Bridging Dimension and Domain Gaps in Volumetric Segmentation via Progressive Adaptation

Although DINOv3 has demonstrated remarkable semantic discrimination in natural imagery, its direct application to volumetric medical segmentation is hindered by inherent dimension and domain disparities. To resolve these issues, we propose DINO-Med3D, a two-stage progressive framework that repurpose the pre-trained DINOv3 encoder for 3D medical tasks. In the first stage, we mitigate the dimension gap by introducing a multi-slice embedding module that incorporates pseudo-3D context, while simultaneously employing a segmentation proxy task to adapt representations learned from natural scenes to the medical domain. Subsequently, we further enhance volumetric understanding by adding lightweight 3D adapters into the frozen backbone to enforce global inter-slice continuity. Finally, to compensate for the spatial information loss inherent in the embedding process, we design a parallel detail recovery stream to explicitly preserve high-frequency boundary cues. Extensive experiments on five public datasets demonstrate that our approach successfully adapts DINOv3 to the medical domain and significantly outperforms state-of-the-art baselines.

cs.CV↗

arXiv2026

DeltaBox: Scaling Stateful AI Agents with Millisecond-Level Sandbox Checkpoint/Rollback

LLM-powered AI agents require high-frequency state exploration (e.g., test-time tree search and reinforcement learning), relying on rapid checkpoint and rollback (C/R) of the complete sandbox state, including files and process state (e.g., memory, contexts, etc.). Existing mechanisms duplicate the entire state, causing hundreds of milliseconds to seconds of latency per C/R, which severely bottlenecks deep search and large-scale fan-outs. This paper observes that subsequent checkpoints in AI agents are highly similar. Therefore, instead of full duplication, a sandbox should only duplicate the changes between consecutive checkpoints (Key Insight). However, it is non-trivial to realize the idea, mainly due to the missing OS supports. This paper proposes a new OS-level abstraction, DeltaState, to enable the change-based transactional C/R for AI agents with two co-designed OS mechanisms. First, DeltaFS enables change-based filesystem C/R by organizing the file states into layers and dynamically freezing the writable layer and inserting a new one during checkpoint, reducing file updates to copy-on-write, and making rollback a simple layer switch. Second, DeltaCR enables change-based process state C/R using incremental dumps, and accelerates rollback by bypassing traditional pipelines to directly fork() from a frozen template process. We then present DeltaBox, a novel agent sandbox achieving millisecond level C/R through the two new mechanisms. Evaluations on SWE-bench and RL micro-benchmarks show DeltaBox completes checkpoint and rollback in millisecond-level latency (14ms and 5ms, respectively), empowering agents to explore substantially more nodes under fixed time budgets.

cs.OS↗

arXiv2026

Weyl asymptotic formulas in the nilpotent Lie group setting

The asymptotic properties of negative order pseudo-differential operators have been an important part of the spectral theory since H.Weyl's classical results. In this paper, we derive a spectral asymptotic formula for the negative fractional powers of hypoelliptic operators on graded Lie groups. Such operators have anisotropically homogeneous principal symbols; for these, our results generalize known results of Birman and Solomyak from 1977. Additionally, our work implies a version of Connes' integration formula for hypoelliptic operators on graded Lie groups. Our methods allow us to extend results from constant-coefficient operators to those with smoothly varying coefficients. The principal technique is to adapt the singular value perturbation arguments of Birman and Solomyak to the setting of nilpotent Lie groups. The decomposing of graded Lie groups is inspired by Folland and Stein in their development of harmonic analysis on homogeneous groups.

math.FA↗

arXiv2026

Three phases of odd robotic active matter

Nonreciprocal interactions in active matter are known to generate exotic mechanical behaviors such as odd elasticity and odd viscosity. However, these phenomena have largely been studied in isolation, raising a fundamental question: Is there a single system that embodies these distinct regimes of odd matter and can transition between phases, establishing a unified phase diagram for nonreciprocal active matter? To address this, we introduce a tunable robotic active matter platform, the Magnetomechanically Augmented Spinning roBotic (MASBot) collective, in which particle-level control of chirality, activity, and pairwise interactions enables access to distinct phases of odd matter. By continuously increasing repulsive forces relative to attractive and transverse forces, we experimentally map a transition from an odd elastic crystal to an odd viscous liquid, and then to a chiral active gas. We find that this latter phase forms a non-space-filling, nonreciprocal active gas stabilized by long-range hydrodynamic attractive forces, whose statistical signatures are consistent with those of a two-dimensional self-gravitating point vortex gas. Within these phases, adjusting spinning frequency and introducing spatially patterned activity allows us to fine-tune odd mechanical responses and tailor power spectra. Further polar and rotational symmetry breaking at the particle scale leads to novel emergent states such as phase separation and collective translation. Together, our system provides a fundamental experimental testbed for nonequilibrium physics and establishes a blueprint for treating robotic swarms as programmable states of matter, enabling functions that range from resilient structures to adaptive swarm reconfiguration.

cond-mat.soft↗

arXiv2026

STAPO: Stabilizing Reinforcement Learning for LLMs by Silencing Rare Spurious Tokens

Reinforcement Learning (RL) has significantly improved large language model reasoning, but existing RL fine-tuning methods rely heavily on heuristic techniques such as entropy regularization and reweighting to maintain stability. In practice, they often suffer from late-stage performance collapse, leading to degraded reasoning quality and unstable training. We identify a key factor behind this instability: a small fraction of tokens, termed spurious tokens (around 0.01%), which contribute little to the reasoning outcome but receive disproportionately amplified gradient updates due to inheriting the full sequence-level reward. We present a unified framework for evaluating token-level optimization impacts across spurious risk, gradient norms, and entropy changes. Building on the analysis of token characteristics that severely disrupt optimization, we propose the Silencing Spurious Tokens (S2T) mechanism to efficiently suppress their gradient perturbations. Incorporating this mechanism into a group-based objective, we propose Spurious-Token-Aware Policy Optimization (STAPO), which promotes stable and effective large-scale model refinement. Across six mathematical reasoning benchmarks using Qwen 1.7B, 8B, and 14B base models, STAPO consistently demonstrates superior entropy stability and achieves an average performance improvement of 11.49% ($\rho_{\mathrm{T}}$=1.0, top-p=1.0) and 3.73% ($\rho_{\mathrm{T}}$=0.7, top-p=0.9) over GRPO, 20-Entropy, and JustRL.

cs.CL↗

arXiv2026

APEX: Learning Adaptive High-Platform Traversal for Humanoid Robots

Humanoid locomotion has advanced rapidly with deep reinforcement learning (DRL), enabling robust feet-based traversal over uneven terrain. Yet platforms beyond leg length remain largely out of reach because current RL training paradigms often converge to jumping-like solutions that are high-impact, torque-limited, and unsafe for real-world deployment. To address this gap, we propose APEX, a system for perceptive, climbing-based high-platform traversal that composes terrain-conditioned behaviors: climb-up and climb-down at vertical edges, walking or crawling on the platform, and stand-up and lie-down for posture reconfiguration. Central to our approach is a generalized ratchet progress reward for learning contact-rich, goal-reaching maneuvers. It tracks the best-so-far task progress and penalizes non-improving steps, providing dense yet velocity-free supervision that enables efficient exploration under strong safety regularization. Based on this formulation, we train LiDAR-based full-body maneuver policies and reduce the sim-to-real perception gap through a dual strategy: modeling mapping artifacts during training and applying filtering and inpainting to elevation maps during deployment. Finally, we distill all six skills into a single policy that autonomously selects behaviors and transitions based on local geometry and commands. Experiments on a 29-DoF Unitree G1 humanoid demonstrate zero-shot sim-to-real traversal of 0.8 meter platforms (approximately 114% of leg length), with robust adaptation to platform height and initial pose, as well as smooth and stable multi-skill transitions.

cs.RO↗

arXiv2026

Pushing Forward Pareto Frontiers of Proactive Agents with Behavioral Agentic Optimization

Proactive large language model (LLM) agents aim to actively plan, query, and interact over multiple turns, enabling efficient task completion beyond passive instruction following and making them essential for real-world, user-centric applications. Agentic reinforcement learning (RL) has recently emerged as a promising solution for training such agents in multi-turn settings, allowing them to learn long-horizon decision-making strategies. However, existing pipelines face a critical challenge in balancing task performance with user engagement, as passive agents cannot efficiently adapt to users' intentions while overuse of human feedback increases the burden on users, which forms a Pareto Frontier between these two objectives. To push forward this frontier, we propose Behavior Agentic Optimization (BAO), an agentic RL framework that enhances and regularizes inter-turn behaviors to improve information-gathering capabilities and suppress inefficient or redundant interactions with users. We evaluate BAO on multiple tasks from the UserRL benchmark suite and demonstrate that it substantially outperforms proactive agentic RL baselines in terms of both higher task performance and lower user efforts, while achieving comparable or even superior performance to commercial LLM agents, highlighting its effectiveness for training proactive, user-centric LLM agents in complex multi-turn scenarios. Our website: https://proactive-agentic-rl.github.io/.

cs.AI↗

arXiv2026

MalURLBench: A Benchmark Evaluating Agents' Vulnerabilities When Processing Web URLs

LLM-based web agents have become increasingly popular for their utility in daily life and work. However, they exhibit critical vulnerabilities when processing malicious URLs: accepting a disguised malicious URL enables subsequent access to unsafe webpages, which can cause severe damage to service providers and users. Despite this risk, no benchmark currently targets this emerging threat. To address this gap, we propose MalURLBench, the first benchmark for evaluating LLMs' vulnerabilities to malicious URLs. MalURLBench contains 61,845 attack instances spanning 10 real-world scenarios and 7 categories of real malicious websites. Experiments with 12 popular LLMs reveal that existing models struggle to detect elaborately disguised malicious URLs. We further identify and analyze key factors that impact attack success rates and propose URLGuard, a lightweight defense module. We believe this work will provide a foundational resource for advancing the security of web agents. Our code is available at https://github.com/JiangYingEr/MalURLBench.

cs.CR↗

arXiv2025

Uniformity of Maximal Hypoellipticity on Graded Lie Groups: From Pointwise to Global

On graded Lie groups, we develop a mechanism that transfers the uniformity of maximal hypoellipcity from the frozen coefficients principal part of a differential operator to the full operator. Our approach brings the century-old "freeze-unfreeze" strategy into the hypoelliptic setting, and offers a transparent and flexible framework for lifting symbol-level hypoelliptic properties to global elliptic estimates, without relying on pseudodifferential calculus. In addition, we prove that symmetric operators of hypoelliptic type on a graded Lie group are self-adjoint.

math.AP↗

arXiv2025

A Passive Software-Defined Radio-based mmWave Sensing System for Blind Integrated Communication and Sensing

Integrated Sensing and Communication (ISAC) is considered as a key component of future 6G technologies, especially in the millimeter-wave (mmWave) bands. Recently, the performances of ISAC were experimentally evaluated and demonstrated in various scenarios by developing ISAC systems. These systems generally consist of coherent transmitting (Tx) and receiving (Rx) modules. However, actively transmitting radio waves for experiments is not easy due to regulatory restrictions of radio. Meanwhile, the Tx/Rx should be synchronized and Rx need the information of Tx. In this paper, a fully passive mmWave sensing system is developed with software-defined radio for blind ISAC. It only consists of a passive Rx module which does not depend on the Tx. Since the proposed system is not synchronized with Tx and has no knowledge of the transmitted signals, a differential structure with two oppositely-oriented receivers is introduced to realize the sensing function. This structure can mitigate the influences of unknown source signals and other distortions. With the proposed sensing system, the ambient mmWave communication signals are leveraged for sensing without interrupting the existing systems. It can be deployed for field applications such as signal detection and dynamic human activity recognition since it does not emit signals. The efficacy of the developed system is first verified with a metallic plate with known motion pattern. The measured Doppler spectrogram shows good agreement with the simulation results, demonstrating the correctness of the sensing results. Further, the system is evaluated in complex scenarios, including handwaving, single- and multi-person motion detection. The sensing results successfully reflect the corresponding motions, demonstrating that the proposed sensing system can be utilized for blind ISAC in various applications.

eess.SY↗

arXiv2025

One Filters All: A Generalist Filter for State Estimation

Estimating hidden states in dynamical systems, also known as optimal filtering, is a long-standing problem in various fields of science and engineering. In this paper, we introduce a general filtering framework, \textbf{LLM-Filter}, which leverages large language models (LLMs) for state estimation by embedding noisy observations with text prototypes. In various experiments for classical dynamical systems, we find that first, state estimation can significantly benefit from the reasoning knowledge embedded in pre-trained LLMs. By achieving proper modality alignment with the frozen LLM, LLM-Filter outperforms the state-of-the-art learning-based approaches. Second, we carefully design the prompt structure, System-as-Prompt (SaP), incorporating task instructions that enable the LLM to understand the estimation tasks. Guided by these prompts, LLM-Filter exhibits exceptional generalization, capable of performing filtering tasks accurately in changed or even unseen environments. We further observe a scaling-law behavior in LLM-Filter, where accuracy improves with larger model sizes and longer training times. These findings make LLM-Filter a promising foundation model of filtering.

cs.LG↗

arXiv2025

Query-Centric Diffusion Policy for Generalizable Robotic Assembly

The robotic assembly task poses a key challenge in building generalist robots due to the intrinsic complexity of part interactions and the sensitivity to noise perturbations in contact-rich settings. The assembly agent is typically designed in a hierarchical manner: high-level multi-part reasoning and low-level precise control. However, implementing such a hierarchical policy is challenging in practice due to the mismatch between high-level skill queries and low-level execution. To address this, we propose the Query-centric Diffusion Policy (QDP), a hierarchical framework that bridges high-level planning and low-level control by utilizing queries comprising objects, contact points, and skill information. QDP introduces a query-centric mechanism that identifies task-relevant components and uses them to guide low-level policies, leveraging point cloud observations to improve the policy's robustness. We conduct comprehensive experiments on the FurnitureBench in both simulation and real-world settings, demonstrating improved performance in skill precision and long-horizon success rate. In the challenging insertion and screwing tasks, QDP improves the skill-wise success rate by over 50% compared to baselines without structured queries.

cs.RO↗