arXiv subjects

Yichen Liu

Publications and source records attributed to Yichen Liu.

At least 37 records · Page 2Linked to original sources

arXiv2026

ChainCaps: Composition-Safe Tool-Using Agents via Monotonic Capability Attenuation

Tool-using agents increasingly operate in open-ended deployment environments, where they compose file systems, web APIs, code interpreters, and enterprise services at runtime. This creates a safety gap in tool composition: an agent can satisfy every per-tool permission check and still produce an unsafe end-to-end effect, such as reading a confidential document, summarizing it, and sending the summary to an external endpoint. We call this failure mode permission laundering. ChainCaps addresses it with a runtime rule: every value carries a sink-specific capability budget, and tool composition propagates budgets by intersection. A value can preserve or lose authority as it moves through a tool chain, but it cannot gain new authority through composition. We implement ChainCaps as a transparent MCP proxy that requires no changes to the agent or tool servers. On 82 tasks across five frontier models from three providers, ChainCaps reduces attack success rate from 25-68% to 0-4.8% while preserving 96-100% benign completion. In replay experiments, it also outperforms scalar-IFC and per-function-isolation baselines. Manifest quality is the dominant deployment bottleneck: expert manifests reach 100% attack blocking, while naive manifests fall to 27.3%. Our claims are limited to explicit-flow composition safety under trusted manifests and proxy-visible data movement, a practical gap in deployed tool-using agents today.

cs.CR↗

arXiv2026

Tall Complexity One Spaces with k-colorable Skeleton

Tall complexity one $T$-spaces are Hamiltonian $T$-spaces $(M,ω,Φ)$ such that $\frac{1}{2}\dim M -\dim T=1$ and the symplectic quotient at each moment value is a surface. The skeleton of a complexity one $T$-space is an important invariant in the classification and encodes the information about non-generic orbits. In this paper, we study properties of the skeleton of a compact, connected tall complexity one $T$-spaces. We prove that when the skeleton is $k$-colorable, i.e., when it can be partitioned into $k$ closed and open subsets such that the orbital moment map is injective on each of them, its information can be recovered by the one-skeleton (the set of non-generic orbits whose dimension is at most one). We also prove that for any cloesd and open subset of the skeleton on which the orbital moment map is injective, one can construct a symplectic toric $(T\times S^1)$-manifold whose underlying complexity one $T$-space has the skeleton isomorphic to this subset.

math.SG↗

arXiv2026

Quantum metric-induced generalized magneto-optical effects in $\mathcal{PT}$-symmetric antiferromagnets

The magneto-optical effects (MOEs), as fundamental physical phenomena, can reveal the electronic structures of materials. The related probing methods are widely used in the study of magnetic materials. The conventional MOEs are understood to arise from the Berry curvature (the imaginary part of the quantum geometry). Within the framework of conventional MOEs, space-time inversion ($\mathcal{PT}$) symmetric antiferromagnets are magneto-optically inactive. Here, we propose quantum metric (the real part of the quantum geometry) induced generalized MOEs and build generic formulas with quantum metric for Kerr and Faraday angles in three-dimensional and two-dimensional $\mathcal{PT}$-symmetric antiferromagnets. Combining the tight-binding model and first-principles calculations, we demonstrate the quantum metric-induced generalized MOEs in the $\mathcal{PT}$-symmetric antiferromagnets. Our theory broadens the research on MOEs and also provides a microscopic understanding of experimentally observed Kerr rotations in $\mathcal{PT}$-symmetric antiferromagnets. Our theory overcomes the zero-net-moment limitation preventing (conventional) MOEs from detecting magnetic phase transitions and spin orderings in $\mathcal{PT}$-symmetric antiferromagnets -- enabling non-destructive spin-state tomography in $\mathcal{PT}$-symmetric antiferromagnets and creating new quantum metric-based pathways toward ultrafast magneto-optical applications, such as memories and sensors.

cond-mat.mtrl-sci↗

arXiv2026

Linearly Polarized Light-Induced Anomalous Hall Effect and Topological Phase Transitions in an Altermagnetic Topological Insulator

A recently identified class of collinear magnetic order, characterized by vanishing net magnetization yet unconventional spin splitting, known as altermagnets (AMs), has attracted significant research interest. Controlling the unconventional spin splitting and the associated band topology in AMs offers opportunities for realizing novel spin and topological transport phenomena. In this work, using Floquet engineering with periodically driven linearly polarized light (LPL), we explore light-induced control of an AM topological insulator. Remarkably, we find that AMs and conventional antiferromagnets (AFMs) exhibit distinct responses under LPL irradiation. Specifically, since LPL breaks neither time-reversal ($\mathcal{T}$) symmetry nor parity-time-reversal ($\mathcal{PT}$) symmetry, it is incapable of generating spin splitting or inducing an anomalous Hall effect (AHE) in conventional AFMs. In contrast, AMs intrinsically lack both $\mathcal{T}$ and $\mathcal{PT}$ symmetries. Their spin-up and spin-down bands are related by the combined symmetry of time reversal $\mathcal{T}$ and a crystal rotation. We show that LPL readily breaks these symmetries, thereby triggering a finite AHE exclusively in AMs. Furthermore, LPL can drive the AM topological insulator into a fully spin-polarized Chern insulating phase. Our findings not only provide a robust experimental scheme to distinguish AMs from conventional AFMs, but also establish a promising pathway toward dissipationless spintronic applications.

cond-mat.mes-hall↗

arXiv2026

Learning Generalizable Robot Policy with Human Demonstration Video as a Prompt

Recent robot learning methods commonly rely on imitation learning from massive robotic dataset collected with teleoperation. When facing a new task, such methods generally require collecting a set of new teleoperation data and finetuning the policy. Furthermore, the teleoperation data collection pipeline is also tedious and expensive. Instead, human is able to efficiently learn new tasks by just watching others do. In this paper, we introduce a novel two-stage framework that utilizes human demonstrations to learn a generalizable robot policy. Such policy can directly take human demonstration video as a prompt and perform new tasks without any new teleoperation data and model finetuning at all. In the first stage, we train video generation model that captures a joint representation for both the human and robot demonstration video data using cross-prediction. In the second stage, we fuse the learned representation with a shared action space between human and robot using a novel prototypical contrastive loss. Empirical evaluations on real-world dexterous manipulation tasks show the effectiveness and generalization capabilities of our proposed method.

cs.RO↗

arXiv2026

Odd-Parity Magnons

Magnons, as charge-neutral spin excitations, can transport spin information without Joule heating and therefore offer a promising platform for low-power spintronics. However, in collinear magnets, the effective time-reversal symmetry forbids odd-parity magnon band splitting. Here we propose odd-parity magnons and establish a general mechanism for realizing them in collinear antiferromagnets. We provide a complete spin-point-group classification of odd-parity magnon splitting in two-dimensional collinear antiferromagnets by identifying the leading splitting types and their symmetry-allowed basis functions. This classification serves as a practical guide for searching for odd-parity magnons. We show that breaking effective time-reversal symmetry, for example by circularly polarized light or loop currents, can induce highly tunable $p$- and $f$-wave magnon splitting. In bilayer systems, the dynamical modulation can drive a topological magnon phase transition, accompanied by chiral edge modes and an abrupt jump in the magnon thermal Hall conductivity. Material-specific first-principles calculations further demonstrate the feasibility of this mechanism in real van der Waals antiferromagnets. Our study identifies the odd-parity magnons as a new class of spin excitations and provides a theoretical foundation for odd-parity magnons and ultrafast optically controlled topological magnonic devices.

cond-mat.mtrl-sci↗

arXiv2026

Representation Collapse in Sequential Post-Training of Large Language Models

Large language models are now adapted through chains of post-training stages rather than through a single instruction-tuning pass. This paper studies whether such sequential post-training gradually compresses internal representations into low-rank, anisotropic, and homogeneous feature spaces. We define a measurement suite for hidden states, logits, token trajectories, and LoRA updates, and we use it to analyze supervised fine-tuning, preference optimization, safety/refusal tuning, math and code specialization, and long chain-of-thought tuning under controlled stage orderings. The central hypothesis is that excessive representation concentration is not merely a geometric curiosity: it predicts reduced plasticity during later adaptation, weaker out-of-domain generalization, and poorer calibration. We further evaluate lightweight interventions, including mixed-domain replay, feature refresh, representation diversity regularization, and LoRA update decorrelation, as ways to preserve future learnability without giving up the behavioral gains of post-training.

cs.LG↗

arXiv2026

Decoding Scientific Experimental Images: The SPUR Benchmark for Perception, Understanding, and Reasoning

We introduce SPUR, a comprehensive benchmark for scientific experimental image perception, understanding, and reasoning, comprising 4,264 question-answering (QA) pairs derived from 1,084 expert-curated images. SPUR features three key innovations: (1) Panel-Level Fine-Grained Perception: evaluating the visual perception of multimodal large language models (MLLMs) across three dimensions (numerical, morphological, and information localization) on six fine-grained panel types; (2) Cross-Panel Relation Understanding: utilizing complex images with an average of 14.3 panels per sample to evaluate MLLMs' ability to decipher intricate cross-panel relations; (3) Expert-Level Reasoning: assessment of qualitative and quantitative reasoning across five experimental paradigms to determine if models can infer conclusions from evidence as human experts do. Comprehensive evaluation of 20 MLLMs and four multimodal Chain-of-Thought (MCoT) methods reveals that current models fall significantly short of the expert-level requirements for scientific image interpretation, underscoring a critical bottleneck in AI for Science (AI4S) research.

cs.CV↗

arXiv2026

GesVLA: Gesture-Aware Vision-Language-Action Model Embedded Representations

Vision-Language-Action (VLA) models have shown strong potential for general-purpose robot manipulation by unifying perception and action. However, existing VLA systems primarily rely on textual instructions and struggle to resolve spatial ambiguity in complex scenes with multiple similar objects. To address this limitation, we introduce gesture as a parallel instruction modality and propose a Gesture-aware Vision-Language-Action model (GesVLA). Our approach encodes gesture features directly into the latent space, enabling them to participate in both high-level reasoning and low-level action generation, and adopts a dual-VLM architecture to achieve tight coupling between gesture representations and action policies. At the data level, we construct a scalable gesture data generation pipeline by rendering hand models onto real-world scene images. This reduces the sim-to-real visual gap while producing rich data with diverse motion patterns and corresponding pointing annotations. In addition, we employ a two-stage training strategy to equip the model with both gesture perception and action prediction capabilities. We evaluate our approach on multiple real-world robotic tasks, including a controlled block manipulation task for validation and more practical scenarios such as product and produce selection. Experimental results show that incorporating gesture consistently improves target grounding accuracy and human-robot interaction efficiency, especially in complex and cluttered environments. Project page: https://gwxuan.github.io/GesVLA/.

cs.RO↗

arXiv2026

AwareVLN: Reasoning with Self-awareness for Vision-Language Navigation

Vision-and-Language Navigation (VLN) requires an agent to ground language instructions to its own movement within a visual environment. While state-of-the-art methods leverage the reasoning capabilities of Vision-Language Models (VLMs) for end-to-end action prediction, they often lack an explicit and explainable understanding of the relationships between the agent, the instruction, and the scene. Conversely, explicitly building a scene map for heuristic planning is intuitively appealing but relies on additional 3D sensors and hinders large-scale vision-language pre-training. To bridge this gap, we propose AwareVLN, a novel framework that equips the navigation model with a self-aware reasoning mechanism, enabling it to understand the agent's state and task progress in a fully end-to-end and data-driven manner. Our approach features two key innovations: (1) a structural reasoning module that fosters spatial and task-oriented self-awareness, and (2) an automatic data engine with progress division for effective training. Extensive experiments on various datasets in Habitat simulator show our AwareVLN significantly outperforms previous state-of-the-art vision-language navigation methods. Project page: https://gwxuan.github.io/AwareVLN/.

cs.RO↗

arXiv2026

UniJEPA: Enhancing Robot Policy via Unified Continuous and Discrete Representation Learning

Building generalist robot policies that can handle diverse tasks in open-ended environments is a central challenge in robotics. To leverage knowledge from large-scale pretraining, prior work (VLA) has typically built generalist policies either on top of vision-language understanding models (VLMs) or generative models. However, both semantic understanding from vision-language pretraining and visual dynamics modeling from visual-generation pretraining are crucial for embodied robots. Recent unified models of generation and understanding have demonstrated strong capabilities in both comprehension and generation through large-scale pretraining. We posit that robotic policy learning can likewise benefit from the combined strengths of understanding, planning, and continuous future representation learning. Building on this insight, we introduce UniJEPA, which acquires the ability to dynamically model high-dimensional visual features through pretraining on over 1M internet-scale instructional manipulation videos. Subsequently, UniJEPA is fine-tuned on data collected from the robot embodiment, enabling the learning of mappings from predictive representations to action tokens. Extensive experiments show our approach consistently outperforms baseline methods in terms of 9\% and 12\% across simulation environments and real-world out-of-distribution tasks.

cs.RO↗

arXiv2026

A Rule-Aware Prompt Framework for Structured Numeric Reasoning in Cyber-Physical Systems

Smart grids rely on high-dimensional numeric telemetry and explicit operating rules to maintain reliable and secure operation. Recent large language models (LLMs) are increasingly considered as candidate decision-support components for power system operations, yet most deployments focus on textual logs, alerts, or operator messages and do not directly address rule-grounded reasoning over numeric grid measurements. This paper proposes a rule-aware prompt framework that systematically encodes power system domain context, numeric normalization, and decision rules into a modular prompt architecture for LLMs. The framework decomposes prompts into reusable modules, including role, domain context, numeric normalization, rule-aware reasoning, value block, and output schema, and exposes an interface for plugging in diverse grid operating rules. A key design element separates rule specification from the representation of normalized numeric deviations, enabling concise prompts aligned with power system criteria. To illustrate its behavior, we instantiate the framework on numeric anomaly detection in the IEEE 118-bus transmission network and evaluate several prompting and adaptation regimes. The results show that rule-aware, z-score-based value blocks and a hybrid LLM+DL architecture substantially improve both consistency with grid operating rules and anomaly detection performance while reducing token usage, providing a reusable bridge between grid telemetry and general-purpose LLMs.

eess.SY↗

arXiv2026

EEG-Based Emergency Braking Intensity Prediction Using Blind Source Separation

Electroencephalography (EEG) signals have been promising for long-term braking intensity prediction but are prone to various artifacts that limit their reliability. Here, we propose a novel framework that models EEG signals as mixtures of independent blind sources and identifies those strongly correlated with braking action. Our method employs independent component analysis to decompose EEG into different components and combines time-frequency analysis with Pearson correlations to select braking-related components. Furthermore, we utilize hierarchical clustering to group braking-related components into two clusters, each characterized by a distinct spatial pattern. Additionally, these components exhibit trial-invariant temporal patterns and demonstrate stable and common neural signatures of the emergency braking process. Using power features from these components and historical braking data, we predict braking intensity at a 200 ms horizon. Evaluations on the open source dataset (O.D.) and human-in-the-loop simulation (H.S.) show that our method outperforms state-of-the-art approaches, achieving RMSE reductions of 8.0% (O.D.) and 23.8% (H.S.).

cs.HC↗

arXiv2026

SOK: A Taxonomy of Attack Vectors and Defense Strategies for Agentic Supply Chain Runtime

Agentic systems based on large language models (LLMs) operate not merely as text generators but as autonomous entities that dynamically retrieve information and invoke tools. This execution model shifts the attack surface from traditional build-time artifacts to inference-time dependencies, exposing agents to manipulation through untrusted data and probabilistic capability resolution. While prior work has examined model-level vulnerabilities, security risks arising from the complex, cyclic runtime behavior of agents remain fragmented. This paper systematizes existing research into a unified runtime framework. We categorize threats into data supply chain attacks (distinguishing between transient context injection and persistent memory poisoning) and tool supply chain attacks (spanning discovery, implementation, and invocation phases). Crucially, we identify the emergence of the Viral Agent Loop, where agents effectively become vectors for self-propagating generative worms that require no code vulnerabilities to spread. We argue for a transition to a Zero-Trust Runtime Architecture, where context is treated as untrusted control flow, and tool execution is bounded by cryptographic provenance rather than semantic likelihood.

cs.CR↗

arXiv2026

HiFi-Inpaint: Towards High-Fidelity Reference-Based Inpainting for Generating Detail-Preserving Human-Product Images

Human-product images, which showcase the integration of humans and products, play a vital role in advertising, e-commerce, and digital marketing. The essential challenge of generating such images lies in ensuring the high-fidelity preservation of product details. Among existing paradigms, reference-based inpainting offers a targeted solution by leveraging product reference images to guide the inpainting process. However, limitations remain in three key aspects: the lack of diverse large-scale training data, the struggle of current models to focus on product detail preservation, and the inability of coarse supervision for achieving precise guidance. To address these issues, we propose HiFi-Inpaint, a novel high-fidelity reference-based inpainting framework tailored for generating human-product images. HiFi-Inpaint introduces Shared Enhancement Attention (SEA) to refine fine-grained product features and Detail-Aware Loss (DAL) to enforce precise pixel-level supervision using high-frequency maps. Additionally, we construct a new dataset, HP-Image-40K, with samples curated from self-synthesis data and processed with automatic filtering. Experimental results show that HiFi-Inpaint achieves state-of-the-art performance, delivering detail-preserving human-product images.

cs.CV↗

arXiv2026

OmniShow: Unifying Multimodal Conditions for Human-Object Interaction Video Generation

In this work, we study Human-Object Interaction Video Generation (HOIVG), which aims to synthesize high-quality human-object interaction videos conditioned on text, reference images, audio, and pose. This task holds significant practical value for automating content creation in real-world applications, such as e-commerce demonstrations, short video production, and interactive entertainment. However, existing approaches fail to accommodate all these requisite conditions. We present OmniShow, an end-to-end framework tailored for this practical yet challenging task, capable of harmonizing multimodal conditions and delivering industry-grade performance. To overcome the trade-off between controllability and quality, we introduce Unified Channel-wise Conditioning for efficient image and pose injection, and Gated Local-Context Attention to ensure precise audio-visual synchronization. To effectively address data scarcity, we develop a Decoupled-Then-Joint Training strategy that leverages a multi-stage training process with model merging to efficiently harness heterogeneous sub-task datasets. Furthermore, to fill the evaluation gap in this field, we establish HOIVG-Bench, a dedicated and comprehensive benchmark for HOIVG. Extensive experiments demonstrate that OmniShow achieves overall state-of-the-art performance across various multimodal conditioning settings, setting a solid standard for the emerging HOIVG task.

cs.CV↗

arXiv2026

Reservoir observer enhanced with residual calibration and attention mechanism

Reservoir observers provide a data-driven approach to the inference of unmeasured variables from observed ones for nonlinear dynamical systems. While previous studies have demonstrated wide applicability, their performance may vary considerably with different input variables, even compromising reliability in the worst cases. To enhance the performance of inference, we integrate residual calibration and attention mechanism into the reservoir observer design. The residual calibration module leverages information from the estimation residuals to refine the observer output, and the attention mechanism exploits the temporal dependencies of the data to enrich the representation of reservoir internal dynamics. Experiments on typical chaotic systems demonstrate that our method substantially improves inference accuracy, especially for the worst cases resulting from the traditional reservoir observers. We also invoke the notion of transfer entropy to explain the reason for the input-dependent observation discrepancy and the effectiveness of the proposed method.

cs.LG↗

arXiv2026

An AI-Driven Framework for Energy-Efficient Environmental Monitoring in Smart Cities Using Edge Intelligence

Environmental monitoring is a crucial component of the smart city infrastructure. It enables informed decision making which enhances sustainability, public health and urban planning. However, the large-scale deployments of the smart sensors have raised concerns on excessive energy consumption and redundant data collection as well as limited sensor lifespan. To resolve these issues, we present an AI-driven framework for energy-efficient environmental monitoring in smart cities utilizing edge intelligence. Our proposed framework leverages TinyML-enabled edge devices and context-aware adaptive decision-making in order to dynamically activate the sensors based on the spatiotemporal conditions, environmental statistics and energy constraints. The sensors will be dynamically activated based on a utility function that takes in factors such as real-time environmental conditions, sensor location, and remaining battery lifespan. Our framework will reduce unnecessary sensing and communication while maintaining high coverage for monitoring. We introduce a hierarchical Edge Intelligence architecture to support deployments in city-wide scales. We conducted evaluation using a city-scale simulation driven by real multi-sensor environmental traces, which demonstrates that the proposed mechanism significantly reduces energy consumption and extends sensor lifespan when compared to static, periodic, and UCB-based adaptive sensing strategies. The results highlight the potential of edge intelligence and adaptive AI techniques for building sustainable and efficient smart city monitoring systems.

cs.DC↗