Searcharxiv⌕ Search

arXiv subjects

Xiaoyu Xu

Publications and source records attributed to Xiaoyu Xu.

At least 37 records · Page 2Linked to original sources
arXiv2026

When Routine Chats Turn Toxic: Unintended Long-Term State Poisoning in Personalized Agents

Personalized LLM agents maintain persistent cross-session state to support long-horizon collaboration. Yet, this persistence introduces a subtle but critical security vulnerability: routine user-agent interactions can gradually reshape an agent's long-term state, inadvertently weakening future confirmation boundaries, expanding tool-use defaults, and escalating autonomous behavior over time. We formalize this risk as \textbf{unintended long-term state poisoning}. To systematically study it, we introduce the \textbf{Unintended Long-Term State Poisoning Bench (ULSPB)}, a bilingual benchmark comprising $350$ settings spanning five assistance categories, seven interaction patterns, 24-turn routine interactions, and matched single-injection counterparts. Furthermore, we define the \emph{Harm Score} (HS), a state-centric metric that quantifies \emph{authorization drift}, \emph{tool-use escalation}, and \emph{unchecked autonomy}. Experiments on OpenClaw with four backbone LLMs demonstrate that, while single-injection is generally effective, routine conversations alone can substantially poison long-term state, primarily corrupting memory-centric artifacts. Evaluations seeded with real-world user interactions confirm that this risk is not a mere artifact of synthetic prompts. To mitigate this threat, we propose \textbf{StateGuard}, a lightweight, post-execution defense that audits state diffs at the writeback boundary and selectively rolls back dangerous edits. Across all evaluated models, StateGuard reduces HS to near zero and lowers false-negative rates, with acceptable high false-positive rates under a safety-first writeback defense and minimal overhead.

cs.CR↗
arXiv2026

From Domains to Instances: Dual-Granularity Data Synthesis for LLM Unlearning

Although machine unlearning is essential for removing private, harmful, or copyrighted content from LLMs, current benchmarks often fail to faithfully represent the true ``forgetting scope'' learned by the model. We formalize two distinct unlearning granularities, domain-level and instance-level, and propose \BiForget, an automated framework for synthesizing high-quality forget sets. Unlike prior work relying on \emph{external} generators, \BiForget exploits the target model per se to elicit data that matches its internal knowledge distribution through seed-guided and adversarial prompting. Our experiments across diverse benchmarks show that it achieves a superior balance of relevance, diversity, and efficiency. Quantitatively, in the Harry Potter domain, it improves relevance by ${\sim}20$ and diversity by ${\sim}$0.05 while \emph{halving} the total data size compared to SOTAs. Ultimately, it facilitates more robust forgetting and better utility preservation, providing a more rigorous foundation for evaluating LLM unlearning.

cs.CL↗
arXiv2026

Reasoning Fails Where Step Flow Breaks

Large reasoning models (LRMs) that generate long chains of thought now perform well on multi-step math, science, and coding tasks. However, their behavior is still unstable and hard to interpret, and existing analysis tools struggle with such long, structured reasoning traces. We introduce Step-Saliency, which pools attention--gradient scores into step-to-step maps along the question--thinking--summary trajectory. Across several models, Step-Saliency reveals two recurring information-flow failures: Shallow Lock-in, where shallow layers over-focus on the current step and barely use earlier context, and Deep Decay, where deep layers gradually lose saliency on the thinking segment and the summary increasingly attends to itself and the last few steps. Motivated by these patterns, we propose StepFlow, a saliency-inspired test-time intervention that adjusts shallow saliency patterns measured by Step-Saliency via Odds-Equal Bridge and adds a small step-level residual in deep layers via Step Momentum Injection. StepFlow improves accuracy on math, science, and coding tasks across multiple LRMs without retraining, indicating that repairing information flow can recover part of their missing reasoning performance.

cs.AI↗
arXiv2026

Cascade of Spin Liquids in a Bilayer Triangular-lattice Antiferromagnet Rb_2Co_2(SeO_3)_3

In frustrated Ising magnets, classical spin liquids (CSLs) with macroscopic ground-state degeneracy can survive against conventional magnetic order, as exemplified by systems on triangular, kagome and pyrochlore lattices at zero field. Here we report the discovery of a high-field route toward spin liquids in a bilayer triangular lattice antiferromagnet, Rb$_2$Co$_2$(SeO$_3$)$_3$. We demonstrate that a cascade of CSLs -- characterized by doubly degenerate one-up-one-down local spin configurations and a residual entropy of 1/2(1-M/M_s)Rln2 per mole -- emerges through field-controlled dilution of Ising dimers. Owing to the interplay of intra- and inter-layer interactions, these CSLs are further stabilized by lattice symmetry breaking at fractional magnetization plateaus. Such field-induced spin liquids can be understood as a consequence of generalized ice rules, analogous to those governing in pyrochlore antiferromagnets. In particular, the 5/6-plateau state is a candidate quantum spin liquid. Our results thereby establish a new pathway for exploring diverse spin liquid states across both classical and quantum regimes.

cond-mat.str-el↗
arXiv2026

Profinite rigidity witnessed by Dehn fillings of cusped hyperbolic 3-manifolds

Any profinite isomorphism between two cusped finite-volume hyperbolic 3-manifolds carries profinite isomorphisms between their Dehn fillings. With this observation, we prove that some cusped finite-volume hyperbolic 3-manifolds are profinitely rigid among all compact, orientable 3-manifolds, through detecting their exceptional Dehn fillings. In addition, we improved a criteria for profinite rigidity of a hyperbolic knot complement or a hyperbolic-type satellite knot complement among compact, orientable 3-manifolds, through examining its characterising slopes. We obtain the following profinitely rigid examples: the complement of the Whitehead link, Whitehead sister link, $\frac{3}{10}$ two-bridge link; specific surgeries on one component of these links; the complement of (full) twist knots $\mathcal{K}_n$, Eudave-Muñoz knots $K(3,1,n,0)$, Pretzel knots $P(-3,3,2n+1)$, $5_2$ knot; the Berge manifold, and many more.

math.GT↗
arXiv2026

MDS-VQA: Model-Informed Data Selection for Video Quality Assessment

Learning-based video quality assessment (VQA) has advanced rapidly, yet progress is increasingly constrained by a disconnect between model design and dataset curation. Model-centric approaches often iterate on fixed benchmarks, while data-centric efforts collect new human labels without systematically targeting the weaknesses of existing VQA models. Here, we describe MDS-VQA, a model-informed data selection mechanism for curating unlabeled videos that are both difficult for the base VQA model and diverse in content. Difficulty is estimated by a failure predictor trained with a ranking objective, and diversity is measured using deep semantic video features, with a greedy procedure balancing the two under a constrained labeling budget. Experiments across multiple VQA datasets and models demonstrate that MDS-VQA identifies diverse, challenging samples that are particularly informative for active fine-tuning. With only a 5% selected subset per target domain, the fine-tuned model improves mean SRCC from 0.651 to 0.722 and achieves the top gMAD rank, indicating strong adaptation and generalization.

cs.CV↗
arXiv2026

NMR evidence of spin supersolid and Pomeranchuk effect behaviors in the triangular-lattice antiferromagnet Rb$_2$Ni$_2$(SeO$_3$)$_3$

We performed $^{85}$Rb nuclear magnetic resonance (NMR) measurements on the $S$ = 1 bilayer triangular-lattice antiferromagnet Rb$_2$Ni$_2$(SeO$_3$)$_3$ in magnetic fields up to 26 T. In the field range from 3 T to 26 T, the NMR spectral lines split and their respective spectral weight ratios reveal the existence of the magnetic up-up-down (UUD) phase, although the 1/3-plateau phase is only reached at fields above 16 T. Two distinct gapless regimes are further identified: one at low fields and low temperatures, and the other at high fields and high temperatures, consistent with the spin supersolid Y and V phases. Notably, the UUD-V phase boundary exhibits a negative slope in $dT/dH$, where the supersolid phase is located at temperatures above the solid phase due to strong low-energy spin fluctuations.

cond-mat.str-el↗
arXiv2026

Aesthetic Camera Viewpoint Suggestion with 3D Aesthetic Field

The aesthetic quality of a scene depends strongly on camera viewpoint. Existing approaches for aesthetic viewpoint suggestion are either single-view adjustments, predicting limited camera adjustments from a single image without understanding scene geometry, or 3D exploration approaches, which rely on dense captures or prebuilt 3D environments coupled with costly reinforcement learning (RL) searches. In this work, we introduce the notion of 3D aesthetic field that enables geometry-grounded aesthetic reasoning in 3D with sparse captures, allowing efficient viewpoint suggestions in contrast to costly RL searches. We opt to learn this 3D aesthetic field using a feedforward 3D Gaussian Splatting network that distills high-level aesthetic knowledge from a pretrained 2D aesthetic model into 3D space, enabling aesthetic prediction for novel viewpoints from only sparse input views. Building on this field, we propose a two-stage search pipeline that combines coarse viewpoint sampling with gradient-based refinement, efficiently identifying aesthetically appealing viewpoints without dense captures or RL exploration. Extensive experiments show that our method consistently suggests viewpoints with superior framing and composition compared to existing approaches, establishing a new direction toward 3D-aware aesthetic modeling.

cs.CV↗
arXiv2025

AutoLugano: A Deep Learning Framework for Fully Automated Lymphoma Segmentation and Lugano Staging on FDG-PET/CT

Purpose: To develop a fully automated deep learning system, AutoLugano, for end-to-end lymphoma classification by performing lesion segmentation, anatomical localization, and automated Lugano staging from baseline FDG-PET/CT scans. Methods: The AutoLugano system processes baseline FDG-PET/CT scans through three sequential modules:(1) Anatomy-Informed Lesion Segmentation, a 3D nnU-Net model, trained on multi-channel inputs, performs automated lesion detection (2) Atlas-based Anatomical Localization, which leverages the TotalSegmentator toolkit to map segmented lesions to 21 predefined lymph node regions using deterministic anatomical rules; and (3) Automated Lugano Staging, where the spatial distribution of involved regions is translated into Lugano stages and therapeutic groups (Limited vs. Advanced Stage).The system was trained on the public autoPET dataset (n=1,007) and externally validated on an independent cohort of 67 patients. Performance was assessed using accuracy, sensitivity, specificity, F1-scorefor regional involvement detection and staging agreement. Results: On the external validation set, the proposed model demonstrated robust performance, achieving an overall accuracy of 88.31%, sensitivity of 74.47%, Specificity of 94.21% and an F1-score of 80.80% for regional involvement detection,outperforming baseline models. Most notably, for the critical clinical task of therapeutic stratification (Limited vs. Advanced Stage), the system achieved a high accuracy of 85.07%, with a specificity of 90.48% and a sensitivity of 82.61%.Conclusion: AutoLugano represents the first fully automated, end-to-end pipeline that translates a single baseline FDG-PET/CT scan into a complete Lugano stage. This study demonstrates its strong potential to assist in initial staging, treatment stratification, and supporting clinical decision-making.

cs.CV↗
arXiv2025

Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM Reasoning

Math reasoning has become the poster child of progress in large language models (LLMs), with new models rapidly surpassing human-level performance on benchmarks like MATH and AIME. But as math leaderboards improve week by week, it is worth asking: do these gains reflect broader problem-solving ability or just narrow overfitting? To answer this question, we evaluate over 20 open-weight reasoning-tuned models across a broad suite of tasks, including math, scientific QA, agent planning, coding, and standard instruction-following. We surprisingly find that most models that succeed in math fail to transfer their gains to other domains. To rigorously study this phenomenon, we conduct controlled experiments on Qwen3-14B models using math-only data but different tuning methods. We find that reinforcement learning (RL)-tuned models generalize well across domains, while supervised fine-tuning (SFT)-tuned models often forget general capabilities. Latent-space representation and token-space distribution shift analyses reveal that SFT induces substantial representation and output drift, while RL preserves general-domain structure. Our results suggest a need to rethink standard post-training recipes, particularly the reliance on SFT-distilled data for advancing reasoning models.

cs.AI↗
arXiv2025

Spinons, solitons and random singlets in the spin-chain compound copper benzoate

The $S=1/2$ antiferromagnetic Heisenberg chain is a paradigmatic quantum system hosting exotic excitations such as spinons and solitons, and forming random singlet state in the presence of quenched disorder. Realizing and distinguishing these excitations in a single material remains a significant challenge. Using nuclear magnetic resonance (NMR) on a high-quality single crystal of copper benzoate, we identify and characterize all three excitation types by tuning the magnetic field at ultra-low temperatures. At a low field of 0.2 T, a temperature-independent spin-lattice relaxation rate ($1/T_1$) over more than a decade confirms the presence of spinons. Below 0.4 K, an additional relaxation channel emerges, characterized by $1/T_1 \propto T$ and a spectral weight growing as $-\ln(T/T_0)$, signaling a random-singlet ground state induced by weak quenched disorder. At fields above 0.5 T, a field-induced spin gap $Δ\propto H^{2/3}$ observed in both $1/T_1$ and the Knight shift signifies soliton excitations. Our results establish copper benzoate as a unique experimental platform for studying one-dimensional quantum integrability and the interplay of disorder and correlations.

cond-mat.str-el↗
arXiv2025

Episodic Feedback in Triple AGN Candidate SDSS J0849+1114 Revealed by Extended ionized gas

Galaxy mergers funnel gas toward the nuclei, igniting starbursts and active galactic nuclei (AGNs). The AGN feedback can reshape the host galaxy and regulate both star formation and super-massive black-hole (SMBH) accretion. Using VLT/MUSE integral-field spectroscopy, we conduct a spatially resolved study of the triple-AGN candidate SDSS J0849+1114. Extended ionized gas structures ($>10$ kpc from nucleus A) primarily associated with tidal tails are detected. Meanwhile, two distinct ionized gas outflows are revealed. One extends over $>5$ kpc around nuclei A with a kinetic power of $\dot{E}_{\rm out,A} = 3.0\times10^{42}\rm\, erg\, s^{-1}$, which might be driven by the radio jet. The other outflow extends $\sim 5.9$ kpc around nucleus C, with a kinetic power of $\dot{E}_{\rm out,C} = 2.0\times10^{40}\rm\, erg\, s^{-1}$. High [O III]/H$α$ and [N II]/H$α$ ratios in the tidal gas require that nucleus A radiated at a high accretion rate with $L_{\rm A,bol} \sim 0.1$--$0.5\,L_{\rm Edd,A}$ at least $\sim3$--$\times10^{4}\rm\,yr$ ago, $20$--$100$ times brighter than today. Combined with multi-wavelength constraints, we find evidence for episodic AGN feedback that expelled circumnuclear gas and rapidly quenched accretion. This triple AGN candidate demonstrates how AGN feedback can self-regulate black hole growth and impact hosts during mergers.

astro-ph.GA↗
arXiv2025

OBLIVIATE: Robust and Practical Machine Unlearning for Large Language Models

Large language models (LLMs) trained over extensive corpora risk memorizing sensitive, copyrighted, or toxic content. To address this, we propose \textbf{OBLIVIATE}, a robust unlearning framework that removes targeted data while preserving model utility. The framework follows a structured process: extracting target tokens, building retain sets, and fine-tuning with a tailored loss function comprising three components -- masking, distillation, and world fact. Using low-rank adapters (LoRA) ensures efficiency without compromising unlearning quality. We conduct experiments on multiple datasets, including Harry Potter series, WMDP, and TOFU, using a comprehensive suite of metrics: \emph{forget quality} (via a new document-level memorization score), \emph{model utility}, and \emph{fluency}. Results demonstrate its effectiveness in resisting membership inference attacks, minimizing the impact on retained data, and maintaining robustness across diverse scenarios.

cs.CL↗
arXiv2025

Profinite almost rigidity in 3-manifolds

We prove that any compact, orientable 3-manifold with empty or toral boundary is profinitely almost rigid among all compact, orientable 3-manifolds. In other words, the profinite completion of its fundamental group determines its homeomorphism type to finitely many possibilities. Moreover, the profinite completion of the fundamental group of a mixed 3-manifold, together with the peripheral structure, uniquely determines the homeomorphism type of its Seifert part, i.e. the maximal graph manifold components in the JSJ-decomposition. On the other hand, without assigning the peripheral structure, the profinite completion of a mixed 3-manifold group may not uniquely determine the fundamental group of its Seifert part. The proof is based on JSJ-decomposition.

math.GT↗
arXiv2025

Artificial intelligence in drug discovery: A comprehensive review with a case study on hyperuricemia, gout arthritis, and hyperuricemic nephropathy

This paper systematically reviews recent advances in artificial intelligence (AI), with a particular focus on machine learning (ML), across the entire drug discovery pipeline. Due to the inherent complexity, escalating costs, prolonged timelines, and high failure rates of traditional drug discovery methods, there is a critical need to comprehensively understand how AI/ML can be effectively integrated throughout the full process. Currently available literature reviews often narrowly focus on specific phases or methodologies, neglecting the dependence between key stages such as target identification, hit screening, and lead optimization. To bridge this gap, our review provides a detailed and holistic analysis of AI/ML applications across these core phases, highlighting significant methodological advances and their impacts at each stage. We further illustrate the practical impact of these techniques through an in-depth case study focused on hyperuricemia, gout arthritis, and hyperuricemic nephropathy, highlighting real-world successes in molecular target identification and therapeutic candidate discovery. Additionally, we discuss significant challenges facing AI/ML in drug discovery and outline promising future research directions. Ultimately, this review serves as an essential orientation for researchers aiming to leverage AI/ML to overcome existing bottlenecks and accelerate drug discovery.

cs.AI↗
arXiv2025

Two Plaquette-Singlet Phases and Emergent SO(5) Deconfined Quantum Criticality in SrCu2(BO3)2

The deconfined quantum critical point (DQCP) has become a central open concept in the physics of quantum matter, and its proposed presence in the Shastry-Sutherland model was followed by the experimental observation of at least a minimal DQC scenario induced by an applied magnetic field in SrCu$_2$(BO$_3$)$_2$. However, the nature of the plaquette-singlet phase in SrCu$_2$(BO$_3$)$_2$ remains unresolved, and with it the identification of the DQCP symmetry from among several theoretical scenarios. Here we perform detailed high-pressure $^{11}$B NMR studies to reveal the presence of both the full-plaquette (FP) and empty-plaquette (EP) phases in SrCu$_2$(BO$_3$)$_2$, phase-separated at a first-order, pressure-driven transition with a volume-fraction effect. The field-driven transition from the EP to the antiferromagnetic (AFM) phase complements our previous observations of the FP--AFM transition, with both showing deconfined quantum criticality, while the scaling of the spin-lattice relaxation rate near the EP--AFM transition, $1/T_1 \propto T^{0.6}$, suggests a DQCP governed by a different universality class. We discuss possible extensions to the Shastry-Sutherland model that account for these pressure and field effects. The expanded phase space we discover mandates an SO(5) DQCP symmetry, and hence our results take an important step towards a complete understanding of deconfined quantum criticality in SrCu$_2$(BO$_3$)$_2$.

cond-mat.str-el↗