arXiv subjects

Siyu Liu

Publications and source records attributed to Siyu Liu.

At least 19 recordsLinked to original sources

arXiv2026

No-Box Vulnerability Analysis: Description-only Detection of Indirect Prompt Injection Vulnerabilities in MCP Servers

Conventional vulnerability analysis relies on either system access or dynamic interaction, all of which may be unavailable to third-party analysts auditing closed-source, remotely hosted, critical in situ systems, or commercially gated software. Therefore, we propose a new paradigm of no-box vulnerability analysis in which neither access nor runtime interaction is available, and only functionality metadata is available. Such metadata defines the intended behavior of the system, including its inputs, outputs, and side effects, while constraining the space of implementations consistent with that behavior. We propose hypothesizing about vulnerabilities that exist across all possible implementations of a given system metadata, without observing or interacting with the target system. An analyst can later validate these hypotheses when additional access is available. We showcase the feasibility of no-box vulnerability analysis through implementing a prototype called MCPSEC, which audits Model Context Protocol (MCP) servers for indirect prompt injection vulnerabilities using only the tool metadata exposed at server registration time. We evaluate MCPSEC on 20 widely deployed MCP servers comprising 177 tools, among which human evaluators confirm 95 vulnerable tools. MCPSEC identified 143 tools as vulnerable, and for each vulnerable tool, it produced a hypothesized vulnerability along with exploitation technique. Using metadata alone, MCPSEC predicted 94 (98.9% recall) real verified vulnerabilities, compared against an LLM baseline with 80 (84.2% recall). Overall, our results introduce no-box vulnerability analysis as a new analysis paradigm and demonstrate its practical feasibility in realistic systems.

cs.CR↗

arXiv2026

Numerical index one characterises commutative JB*-triples

We establish that a JB$^*$-triple $E$ is commutative if and only if its numerical index $n(E)$ is one. As a consequence, $n(E) = 1$ implies $n(E^*) = n(E^{**}) = 1$. This settles a question left open in the literature since 2008.

math.OA↗

arXiv2026

Bioinfoysis Technical Report

Large language model agents have shown promise in bioinformatics, but most existing systems focus primarily on producing final answers, treating planning, tool use, and code execution as transient interactions. This design is poorly suited to long-horizon bioinformatics tasks, where conclusions must remain connected to the data, computations, and intermediate evidence that support them. We introduce \textbf{Bioinfoysis}, a multi-agent harness that represents each request as a persistent, artifact-grounded analysis run. Bioinfoysis combines global planning with step-wise, evidence-driven replanning: the planner maintains an executable checklist and revises pending steps using structured handoffs returned after each worker execution. These handoffs bind intermediate results to their responsible agent, checklist step, and plan generation, preventing stale evidence from being silently reused after replanning. A controlled runtime validates generated scripts, tables, and figures before they are used in downstream analysis or reporting, while role-specific context, persistent memory, and governed bioinformatics skills support reliable execution over long analysis trajectories. We evaluate Bioinfoysis on BixBench and two question-answering tracks of LAB-Bench 2. On BixBench, Bioinfoysis achieves state-of-the-art accuracy of 82.4\%. Across four underlying language models, Bioinfoysis increases average accuracy from 27.81\% to 64.13\% on SeqQA2 and from 3.13\% to 31.25\% on DbQA2. These results demonstrate that reliable bioinformatics automation depends not only on model capability, but also on the harness that governs planning, execution, memory, and evidence flow. We hope that the emergence of Bioinfoysis will play a driving and leading role in the development of the bioinformatics community. Our demo website can be seen in https://report.bioinfoysis.com/.

cs.AI↗

arXiv2026

Quantum Divergence and Topological Edge Diagnostics via Levitov Full Counting Statistics

We propose a differential full counting statistics protocol for mesoscopic transport. Additionally, we compare terminal Fano factors and noise cumulants between gate configurations at matched k1, instead of inferring a bulk divergence sensor from a single absolute F. it is illustrated analytically for a two channel factorization via a zero temperature geometry scan. Secondary benchmarks show that a two dimensional lattice non equilibrium Greens function calculation yields sub Poissonian Fano factors, whereas Kumars low temperature quantum point contact calibration validates the numerical implementation.

cond-mat.mes-hall↗

arXiv2026

Harnessing agent memory to build lifelong AI partners for materials scientists

Materials research advances through accumulated experience - scripts that work, protocols that are trusted, warnings attached to failed calculations or experiments, and judgement that links a new question to an old result. This experience is essential for reproducibility and knowledge transfer, yet it is usually fragmented across notebooks, repositories, job logs and individual memory, and it is rarely portable across artificial-intelligence agents. Here we argue that a lifelong AI partner for materials science can be designed around persistent memory rather than around a particular agent implementation. We introduce a self-evolving memory framework that stores scientific experience as inspectable facts and executable skills, so that observations, failure boundaries, protocols and validation checks can be retrieved, revised and migrated across models. We evaluate the idea in three computational settings that expose different layers of materials-research competence. In 49 real-world materials-tool-use questions comprising 138 executable subtasks, memory nearly doubles GPT-5.2 task success without model-parameter updates. In elemental-solid equation-of-state calculations, memory converts a wavefunction-initialization failure into a pre-execution guardrail, improving outcomes from 22/1/4 to 25/2/0 Correct/Partial/Error and avoiding 92% of repeated errors. In 13 practical material simulation workflows, remembered skills and failure facts halve the aggregate trace burden (tokens) and reduce tool calls by over a factor of two by the third round, while preserving physically meaningful outputs in band-gap, phonon, vacancy and work-function analyses. These results show that agent memory can serve as a durable scientific asset; a portable, self-improving record of materials-research experience that outlives any single model or agent stack.

cs.AI↗

arXiv2026

General Non-Clairvoyant KV-Cache Scheduling via Regime-Aware Routing

We study non-clairvoyant scheduling for batched Large Language Model (LLM) inference under a hard Key-Value (KV) cache memory budget. Each request has a known prompt length but an unknown response length, and its memory footprint comprises a fixed prompt component together with a response component that grows with each decoded token. At each decoding round, the scheduler chooses a feasible batch of active requests; evicting a request discards its accumulated cache states, wasting prior computation. The goal is to minimize total completion time against the optimal clairvoyant schedule that knows all response lengths. We present the first constant-competitive algorithm for arbitrary prompt lengths and arbitrary response lengths with no additional assumptions. Rather than relying on a single universal scheduling policy, our algorithm is built on a novel regime-aware routing framework. Specialized sub-schedulers handle different memory-growth geometries, while a meta-scheduler time-shares the memory budget across them and dynamically routes each job as its execution progressively reveals its behavior. This framework also yields constant-competitive guarantees for makespan and for total completion time under online arrivals.

cs.DS↗

arXiv2026

SeedSmith: LLM-Driven Seed Synthesis for Directed Fuzzing

Directed fuzzing steers fuzzers toward user-defined sink functions to identify vulnerabilities, but it frequently fails to trigger crashes even after long campaigns. We identify two challenges that prevent directed fuzzers from exposing crashes: incomplete static analysis of indirect calls, which leaves reachable paths invisible to distance-based guidance, and lack of semantic guidance for crash preconditions, which blind mutation cannot satisfy within practical time budgets. A natural intervention point is the initial seed corpus: seeds that encode the right control-flow path and satisfy key crash preconditions shift fuzzing from blind exploration to local refinement. Existing seed generation approaches address neither: grammar-based and format-driven methods produce structurally valid inputs with no sink awareness, while LLM-based methods either lack sink targeting or inherit static analysis limitations through one-shot prompting. We present SeedSmith, an agentic LLM pipeline that replicates a security analyst's workflow: starting from a sink, it iteratively explores the codebase, resolves indirect calls, identifies crash preconditions, and synthesizes concrete inputs that satisfy them. Because SeedSmith operates as a seed generation front-end, its seeds are fuzzer-agnostic and improve any downstream mutation-based fuzzer without modification. On Magma, fuzzers using SeedSmith seeds achieve geometric mean crash-time speedups of 11.51 times (AFL++) to 14.66 times (AFLGo) over default seeds. On ARVO, SeedSmith enables fuzzers to trigger 16 previously unreachable bugs spanning 10 projects with diverse input formats.

cs.CR↗

arXiv2026

Counting and Sampling Anti-ferromagnetic Potts Models on Random Regular Bipartite Graphs in the Non-uniqueness Regime

The anti-ferromagnetic multi-state Potts model, a generalization of the Ising model, is one of the most fundamental models in statistical physics. It was conjectured by Koteck\'{y} (Phys. Rev. B, 1985) that the model undergoes a phase transition from a disordered phase at infinite temperature to an ordered phase at sufficiently low temperature on lattices. Such phase transitions are believed to play an important role in computational complexity theory and remain closely connected to the problem of approximating the partition function of the system. For proper three-coloring models (corresponding to the zero-temperature), torpid mixing of a family of local-update Markov chains on lattices was established by Galvin, Kahn, Randall and Sorkin (SIDMA, 2015), coinciding with the presence of phase coexistence following shown by Feldheim and Spinka (J. Eur. Math. Soc., 2019). In this work, we study approximating the partition function of the anti-ferromagnetic multi-state Potts model at low temperature on random regular bipartite graphs, which are with high probability good bipartite expanders. On the negative side, we generalize the result by Geisler, Kang, Sarantis and Wdowinski (arXiv, 2026) for anti-ferromagnetic Ising models to show that when the temperature is sufficiently low relative to the degree of the underlying graph, the celebrated single-site Glauber dynamics has exponentially slow mixing time. On the positive side, we design a deterministic algorithm that yields an approximation to the partition function of the model via the framework of abstract polymer models as Jenssen, Keevash and Perkins (SICOMP, 2020), Liao, Lin, Lu and Mao (Theor. Comput. Sci., 2022), Galanis, Goldberg and Stewart (TOCT, 2021) and Geisler, Kang, Sarantis and Wdowinski (arXiv, 2026).

cs.DS↗

arXiv2026

A Le Page--Kaplansky theorem characterizing commutative JB*-triples

We prove that a Le Page-type inequality is also valid for metrically characterizing those JB$^*$-triples that are commutative. More precisely, we establish that the following statements are equivalent for any JB$^*$-triple $E$: $(a)$ $E$ is commutative. $(b)$ There exists $\gamma>0$ satisfying $$\big\|\{a,b,\{x,y,z\}\}\big\|\leq \gamma \ \! \big\|\{x,y,\{a,b,z\}\}\big\|, \hbox{ for all } a,b,x,y,z\in E.$$

math.FA↗

arXiv2026

Exploring Subnetwork Interactions in Heterogeneous Brain Network via Prior-Informed Graph Learning

Modeling the complex interactions among functional subnetworks is crucial for the diagnosis of mental disorders and the identification of functional pathways. However, learning the interactions of the underlying subnetworks remains a significant challenge for existing Transformer-based methods due to the limited number of training samples. To address these challenges, we propose KD-Brain, a Prior-Informed Graph Learning framework for explicitly encoding prior knowledge to guide the learning process. Specifically, we design a Semantic-Conditioned Interaction mechanism that injects semantic priors into the attention query, explicitly navigating the subnetwork interactions based on their functional identities. Furthermore, we introduce a Pathology-Consistent Constraint, which regularizes the model optimization by aligning the learned interaction distributions with clinical priors. Additionally, KD-Brain leads to state-of-the-art performance on a wide range of disorder diagnosis tasks and identifies interpretable biomarkers consistent with psychiatric pathophysiology. Our code is available at https://anonymous.4open.science/r/KDBrain.

cs.LG↗

arXiv2026

Mozi: Governed Autonomy for Drug Discovery LLM Agents

Tool-augmented large language model (LLM) agents promise to unify scientific reasoning with computation, yet their deployment in high-stakes domains like drug discovery is bottlenecked by two critical barriers: unconstrained tool-use governance and poor long-horizon reliability. In dependency-heavy pharmaceutical pipelines, autonomous agents often drift into irreproducible trajectories, where early-stage hallucinations multiplicatively compound into downstream failures. To overcome this, we present Mozi, a dual-layer architecture that bridges the flexibility of generative AI with the deterministic rigor of computational biology. Layer A (Control Plane) establishes a governed supervisor--worker hierarchy that enforces role-based tool isolation, limits execution to constrained action spaces, and drives reflection-based replanning. Layer B (Workflow Plane) operationalizes canonical drug discovery stages -- from Target Identification to Lead Optimization -- as stateful, composable skill graphs. This layer integrates strict data contracts and strategic human-in-the-loop (HITL) checkpoints to safeguard scientific validity at high-uncertainty decision boundaries. Operating on the design principle of ``free-form reasoning for safe tasks, structured execution for long-horizon pipelines,'' Mozi provides built-in robustness mechanisms and trace-level audibility to completely mitigate error accumulation. We evaluate Mozi on PharmaBench, a curated benchmark for biomedical agents, demonstrating superior orchestration accuracy over existing baselines. Furthermore, through end-to-end therapeutic case studies, we demonstrate Mozi's ability to navigate massive chemical spaces, enforce stringent toxicity filters, and generate highly competitive in silico candidates, effectively transforming the LLM from a fragile conversationalist into a reliable, governed co-scientist.

cs.AI↗

arXiv2026

Improving Reconstruction of Representation Autoencoder

Recent work leverages Vision Foundation Models as image encoders to boost the generative performance of latent diffusion models (LDMs), as their semantic feature distributions are easy to learn. However, such semantic features often lack low-level information (\eg, color and texture), leading to degraded reconstruction fidelity, which has emerged as a primary bottleneck in further scaling LDMs. To address this limitation, we propose LV-RAE, a representation autoencoder that augments semantic features with missing low-level information, enabling high-fidelity reconstruction while remaining highly aligned with the semantic distribution. We further observe that the resulting high-dimensional, information-rich latent make decoders sensitive to latent perturbations, causing severe artifacts when decoding generated latent and consequently degrading generation quality. Our analysis suggests that this sensitivity primarily stems from excessive decoder responses along directions off the data manifold. Building on these insights, we propose fine-tuning the decoder to increase its robustness and smoothing the generated latent via controlled noise injection, thereby enhancing generation quality. Experiments demonstrate that LV-RAE significantly improves reconstruction fidelity while preserving the semantic abstraction and achieving strong generative quality. Our code is available at https://github.com/modyu-liu/LVRAE.

cs.CV↗

arXiv2026

ReWeaver: Towards Simulation-Ready and Topology-Accurate Garment Reconstruction

High-quality 3D garment reconstruction plays a crucial role in mitigating the sim-to-real gap in applications such as digital avatars, virtual try-on and robotic manipulation. However, existing garment reconstruction methods typically rely on unstructured representations, such as 3D Gaussian Splats, struggling to provide accurate reconstructions of garment topology and sewing structures. As a result, the reconstructed outputs are often unsuitable for high-fidelity physical simulation. We propose ReWeaver, a novel framework for topology-accurate 3D garment and sewing pattern reconstruction from sparse multi-view RGB images. Given as few as four input views, ReWeaver predicts seams and panels as well as their connectivities in both the 2D UV space and the 3D space. The predicted seams and panels align precisely with the multi-view images, yielding structured 2D--3D garment representations suitable for 3D perception, high-fidelity physical simulation, and robotic manipulation. To enable effective training, we construct a large-scale dataset GCD-TS, comprising multi-view RGB images, 3D garment geometries, textured human body meshes and annotated sewing patterns. The dataset contains over 100,000 synthetic samples covering a wide range of complex geometries and topologies. Extensive experiments show that ReWeaver consistently outperforms existing methods in terms of topology accuracy, geometry alignment and seam-panel consistency.

cs.CV↗

arXiv2026

Does Motion Intensity Impair Cognition in HCI? The Critical Role of Physical Motion-Visual Target Directional Congruency

Human-computer interaction (HCI) increasingly occurs in motion-rich environments. The ability to accurately and rapidly respond to directional visual cues is critical in these contexts. How whole-body motion and individual differences affect human perception and reaction to these directional cues is therefore a key, yet an underexplored question for HCI. This study used a 6-DOF motion platform to measure task performance on a visual direction judgment task. We analyzed performance by decomposing the complex motion into two distinct components: a task-irrelevant lateral interference component and a task-aligned directional congruency component. Results indicate that increased motion intensity lengthened reaction times. This effect was primarily driven by the lateral interference component, and this detrimental impact was disproportionately amplified for individuals with high motion sickness susceptibility. Conversely, directional congruency, where motion direction matched the visual cue, improved performance for all participants. These findings suggest that motion's impact on cognition is not monolithic, and that system design for mobile HCI can be informed by strategies that actively shape motion, such as minimizing lateral interference while maximizing directional congruency.

cs.HC↗

arXiv2025

PerTouch: VLM-Driven Agent for Personalized and Semantic Image Retouching

Image retouching aims to enhance visual quality while aligning with users' personalized aesthetic preferences. To address the challenge of balancing controllability and subjectivity, we propose a unified diffusion-based image retouching framework called PerTouch. Our method supports semantic-level image retouching while maintaining global aesthetics. Using parameter maps containing attribute values in specific semantic regions as input, PerTouch constructs an explicit parameter-to-image mapping for fine-grained image retouching. To improve semantic boundary perception, we introduce semantic replacement and parameter perturbation mechanisms during training. To connect natural language instructions with visual control, we develop a VLM-driven agent to handle both strong and weak user instructions. Equipped with mechanisms of feedback-driven rethinking and scene-aware memory, PerTouch better aligns with user intent and captures long-term preferences. Extensive experiments demonstrate each component's effectiveness and the superior performance of PerTouch in personalized image retouching. Code Pages: https://github.com/Auroral703/PerTouch.

cs.CV↗

arXiv2025

Nonequilibrium dynamics of membraneless active droplets

Membraneless droplets or liquid condensates formed via liquid-liquid phase separation (LLPS) play a pivotal role in cell biology and hold potential for biomedical engineering. While membraneless droplets are often studied in the context of interactions between passive components, it is increasingly recognized that active matter inclusions, such as molecular motors and catalytic enzymes in cells, play important roles in the formation, transport and interaction of membraneless droplets. Here we developed a bacteria-polymer active phase separation system to study the nonequilibrium effect of active matter inclusions on the LLPS dynamics. We found that the presence of bacterial active matter accelerated the initial condensation of phase-separated liquid droplets but subsequently arrested the droplet coarsening process, resulting in a stable suspension of membraneless active droplets packed with motile bacterial cells. The arrested phase separation of the bacterial active droplet system presumably arises from anti-phase entrainment of interface fluctuations between neighboring droplets, which reduces the frequency of inter-droplet contact and suppresses droplet coarsening. In addition, the active stresses generated by cells within the droplets give rise to an array of nonequilibrium phenomena, such as dominant long-wavelength fluctuations and enhanced droplet transport with short-term persistent motion due to spontaneous symmetry breaking. Our study reveals a unique mechanism for arrested phase separation and long-term stability in membraneless droplet systems. The bacteria-polymer active phase separation system opens a new avenue for studying the dynamics of membraneless active droplets relevant to non-equilibrium LLPS in cells and in biomedical engineering applications.

cond-mat.soft↗

arXiv2025

BuildBench: Benchmarking LLM Agents on Compiling Real-World Open-Source Software

Automatically compiling open-source software (OSS) projects is a vital, labor-intensive, and complex task, which makes it a good challenge for LLM Agents. Existing methods rely on manually curated rules and workflows, which cannot adapt to OSS that requires customized configuration or environment setup. Recent attempts using Large Language Models (LLMs) used selective evaluation on a subset of highly rated OSS, a practice that underestimates the realistic challenges of OSS compilation. In practice, compilation instructions are often absent, dependencies are undocumented, and successful builds may even require patching source files or modifying build scripts. We propose a more challenging and realistic benchmark, BUILD-BENCH, comprising OSS that are more diverse in quality, scale, and characteristics. Furthermore, we propose a strong baseline LLM-based agent, OSS-BUILD-AGENT, an effective system with enhanced build instruction retrieval module that achieves state-of-the-art performance on BUILD-BENCH and is adaptable to heterogeneous OSS characteristics. We also provide detailed analysis regarding different compilation method design choices and their influence to the whole task, offering insights to guide future advances. We believe performance on BUILD-BENCH can faithfully reflect an agent's ability to tackle compilation as a complex software engineering tasks, and, as such, our benchmark will spur innovation with a significant impact on downstream applications in the fields of software development and software security.

cs.SE↗

arXiv2025

Trees as Gaussians: Large-Scale Individual Tree Mapping

Trees are key components of the terrestrial biosphere, playing vital roles in ecosystem function, climate regulation, and the bioeconomy. However, large-scale monitoring of individual trees remains limited by inadequate modelling. Available global products have focused on binary tree cover or canopy height, which do not explicitely identify trees at individual level. In this study, we present a deep learning approach for detecting large individual trees in 3-m resolution PlanetScope imagery at a global scale. We simulate tree crowns with Gaussian kernels of scalable size, allowing the extraction of crown centers and the generation of binary tree cover maps. Training is based on billions of points automatically extracted from airborne lidar data, enabling the model to successfully identify trees both inside and outside forests. We compare against existing tree cover maps and airborne lidar with state-of-the-art performance (fractional cover R$^2 = 0.81$ against aerial lidar), report balanced detection metrics across biomes, and demonstrate how detection can be further improved through fine-tuning with manual labels. Our method offers a scalable framework for global, high-resolution tree monitoring, and is adaptable to future satellite missions offering improved imagery.

cs.CV↗