arXiv subjects

Yilong Wang

Publications and source records attributed to Yilong Wang.

At least 19 recordsLinked to original sources

arXiv2026

Multi-Granularity Context-Enhanced RAG over Multimodal Knowledge Graphs

Retrieval-augmented generation (RAG) is widely used to mitigate hallucination issues in large language models (LLMs) and multimodal large language models (MLLMs). In particular, knowledge graph (KG)-based RAG leverages structured knowledge to provide (M)LLMs with high-quality external information. Building on these works, recent studies have explored multimodal knowledge graphs (MMKGs) as knowledge bases for GraphRAG. This enables Graph RAG to integrate knowledge across multiple modalities, thereby further enhancing its performance. However, existing MMKG-based RAG methods generally follow a common pipeline in which different modalities are largely processed independently before being fusion. As a result, textual context is only used to a limited extent during visual information extraction and subsequent multimodal knowledge fusion. This brings a semantic gap between images and text which limits the multimodal GraphRAG performance. To address this issue, we propose a novel framework for constructing a Context-Enhanced MMKG (CEMMKG) to better support multimodal GraphRAG. The proposed CEMMKG enriches each image with complementary textual context at both local and global scopes. Local context goes beyond the surrounding text by incorporating sentences that are semantically related to the image, while global context provides a summary of the entire passage. We further introduce a multi-granularity design for the local context, allowing it to capture semantically relevant information at different levels of detail. Extensive experiments on the selected vision-centric dataset validate that CEMMKG is effective in leveraging contextual information to improve MMKG-based RAG performance. Moreover, its effectiveness across different MMKG-based RAG methods demonstrates its broad applicability.

cs.AI↗

arXiv2026

Trojaning the Alignment: Stealthy Backdoor Attacks against Graph Foundation Models

Graph Foundation Models (GFMs) on text-attributed graphs (TAGs) align graph representations with language semantics to support transferable graph learning. Despite these advantages, the backdoor vulnerability of GFMs on TAGs remains insufficiently understood, especially under graph-language alignment, where graph and text representations are trained to constrain each other in a shared semantic space. Existing backdoor attacks mainly target either the graph side or the text side, treating the two modalities independently. This makes direct adaptation ineffective: graph-only triggers can be constrained by clean text semantics, while text-only triggers alter the language view but do not directly shift the graph representation being aligned and scored. TAGs also impose a stealth challenge because triggers are exposed as both node text and local graph structure, making incoherent trigger attributes or anomalous subgraphs easy to inspect or filter. In this paper, we propose STAG, a stealthy trojan attack framework designed for the graph-language alignment interface of GFMs on TAGs. STAG coordinates a graph-trigger generator with a text-side soft prompt so that trigger-attached graph representations and triggered text representations move toward the same target-class text region. To address TAG-specific stealthiness, STAG realizes trigger nodes as readable text through candidate retrieval and regularizes the trigger-attached subgraph so that its local structure remains close to the original subgraph. Extensive experiments on multiple TAG datasets and representative GFMs demonstrate the effectiveness and stealthiness of STAG. Our code is available at https://github.com/ventr1c/STAG.

cs.LG↗

arXiv2026

Non-semisimple open-closed 3d TFT

Given a spherical finite tensor category C, not necessarily semisimple, and a two-sided modified trace on its projective ideal, we define an open-closed three-dimensional topological field theory with values in vector spaces. The bordism category has as morphisms three-dimensional bordisms with corners, whose boundary is partitioned into the gluing boundary, parametrised by source and target surface, and the unparametrised free boundary. The free boundary is equipped with an embedded C-coloured graph satisfying an admissibility condition. Our construction starts from a new three-manifold invariant based on the multi-handlebody invariant of [arXiv:1809.07991] and the chromatic maps of [arXiv:2302.04509]. The open-closed topological field theory is then obtained via the universal construction.

math.QA↗

arXiv2026

Modular fusion categories with trivial Torelli group actions

In this paper, we study modular fusion categories whose mapping class group representations are trivial on the Torelli groups, with particular emphasis on the congruence properties of the resulting representations of $\mathrm{Sp}(2g,\mathbb{Z})$. We prove that, for any $g \ge 3$, the Torelli group is contained in the kernel of the genus-$g$ mapping class group representation $ρ_g$ associated with a modular fusion category $\mathcal{C}$ if and only if $\mathcal{C}$ is pointed. This refines the corresponding result in \cite{MW25}. We also characterize the modular fusion categories for which the genus-$2$ Torelli group is contained in $\ker ρ_2$; in particular, categories with isotropic adjoint subcategories belong to this class. Finally, we give a complete classification of modular fusion categories with isotropic adjoint subcategories.

math.QA↗

arXiv2026

Non-invasive Blood Glucose Estimation from Wearable Physiological Signals

Non-invasive blood glucose estimation from wearable physiological signals remains difficult because longitudinal photoplethysmography (PPG) data are subject to distribution drift, whereas reference capillary blood glucose labels are sparse and costly to acquire. We propose a \rev{deep-learning-based} dynamic incremental learning (DIL) framework that combines a mutual entropy-optimized replay-based dynamic clustering module (MERDC) with an uncertainty-quantified proxy gradient bridging agent (PGBA) for label-efficient adaptation to unlabeled PPG streams. To support this setting, we further establish a longitudinal benchmark dataset comprising PPG, reference capillary blood glucose, and cuff blood pressure measurements from 183 participants collected over 285 days, and we make this resource available to the research community. Under 5-fold subject-independent validation, the proposed method achieves a mean absolute error (MAE) of $0.64 \pm 0.01$ millimoles per liter (mmol/L) and a root mean square error (RMSE) of $1.29 \pm 0.10$ mmol/L, with $97.69 \pm 1.63\%$ of estimates falling within Clarke zones A+B. Aggregation-level analyses further support the robustness of the observed error distribution beyond window-level evaluation. \rev{These results provide a proof-of-concept for adaptive non-invasive glucose estimation in wearable physiological sensing and establish a longitudinal benchmark for subsequent research.

eess.SP↗

arXiv2026

SynthICL: Scalable In-context Imitation Learning with Synthetic Data

In-context imitation learning (ICIL) enables robots to learn new tasks from a small number of demonstrations by conditioning a pre-trained policy on task-specific examples, without retraining at test time. Despite this promise, training generalizable and scalable in-context imitation policies remains an open challenge. We present SynthICL, a scalable framework that trains ICIL policies entirely from RGB-only synthetic data. Specifically, we build a data generation pipeline to produce high-fidelity ICIL data and train a flow-matching transformer policy on the resulting dataset. SynthICL avoids the need for depth sensing, precise camera calibration, and real-world training data in prior approaches, offering a simpler and more scalable alternative. We further incorporate subgoal prediction by training the model to predict the next subgoal images, enabling more precise and visually grounded control. Evaluated on 16 unseen real-world manipulation tasks, SynthICL achieves an average success rate of 79% with only one demonstration provided at test time and outperforms prior methods. Project page: https://synth-icl.github.io

cs.RO↗

arXiv2026

Instant-Fold: In-Context Imitation Learning for Deformable Object Manipulation

Deformable object manipulation (DOM) is challenging due to high-dimensional, partially observable states that evolve through long-horizon, topology-changing interactions with multiple valid manipulation modes. We introduce Instant-Fold, an in-context imitation learning framework for DOM. Given a single human demonstration, our policy infers and executes diverse manipulation modes directly from the demonstration, including variations in spatial execution and ordering, without requiring gradient updates. Our approach first learns deformation-aware visual representations via temporal contrastive pretraining, after which a flow-matching transformer policy conditioned on the demonstration predicts actions to execute the intended manipulation mode. Trained entirely in simulation, Instant-Fold generalizes across diverse folding modes and transfers zero-shot to real-world settings without additional data collection or finetuning. Videos are available at https://instant-fold.github.io.

cs.RO↗

arXiv2026

Macro: Enhancing Multilingual Counterfactual Explanations through Alignment-as-Preference Optimization

Self-generated counterfactual explanations (SCEs) are minimally modified inputs (minimality) generated by large language models (LLMs) that flip their own predictions (validity), offering a causally grounded approach to unraveling black-box LLM behavior. Yet extending them beyond English remains challenging: existing methods struggle to produce valid SCEs in non-dominant languages, and a persistent trade-off between validity and minimality undermines explanation quality. We introduce Macro, a preference alignment framework that applies Direct Preference Optimization (DPO) to multilingual SCE generation, using a composite scoring function to construct preference pairs that effectively translate the trade-off into measurable preference signals. Experiments across four LLMs and seven typologically diverse languages show that Macro improves validity by 12.55\% on average over the chain-of-thought baseline without degrading minimality, while avoiding the severe minimality violations of the translation-based baseline. Compared to supervised fine-tuning, Macro achieves superior performance on both metrics, confirming that explicit preference optimization is essential for balancing this trade-off. Further analyses reveal that Macro increases cross-lingual perturbation alignment and mitigates common generation errors. Our results highlight preference optimization as a promising direction for enhancing multilingual model explanations.

cs.CL↗

arXiv2026

Query-Efficient Agentic Graph Extraction Attacks on GraphRAG Systems

Graph-based retrieval-augmented generation (GraphRAG) systems construct knowledge graphs over document collections to support multi-hop reasoning. While prior work shows that GraphRAG responses may leak retrieved subgraphs, the feasibility of query-efficient reconstruction of the hidden graph structure remains unexplored under realistic query budgets. We study a budget-constrained black-box setting where an adversary adaptively queries the system to steal its latent entity-relation graph. We propose AGEA (Agentic Graph Extraction Attack), a framework that leverages a novelty-guided exploration-exploitation strategy, external graph memory modules, and a two-stage graph extraction pipeline combining lightweight discovery with LLM-based filtering. We evaluate AGEA on medical, agriculture, and literary datasets across Microsoft-GraphRAG and LightRAG systems. Under identical query budgets, AGEA significantly outperforms prior attack baselines, recovering up to 90% of entities and relationships while maintaining high precision. These results demonstrate that modern GraphRAG systems are highly vulnerable to structured, agentic extraction attacks, even under strict query limits. The code is available at https://github.com/shuashua0608/AGEA.

cs.AI↗

arXiv2026

Attack by Unlearning: Unlearning-Induced Adversarial Attacks on Graph Neural Networks

Graph neural networks (GNNs) are widely used for learning from graph-structured data in domains such as social networks, recommender systems, and financial platforms. To comply with privacy regulations like the GDPR, CCPA, and PIPEDA, approximate graph unlearning, which aims to remove the influence of specific data points from trained models without full retraining, has become an increasingly important component of trustworthy graph learning. However, approximate unlearning often incurs subtle performance degradation, which may incur negative and unintended side effects. In this work, we show that such degradations can be amplified into adversarial attacks. We introduce the notion of \textbf{unlearning corruption attacks}, where an adversary injects carefully chosen nodes into the training graph and later requests their deletion. Because deletion requests are legally mandated and cannot be denied, this attack surface is both unavoidable and stealthy: the model performs normally during training, but accuracy collapses only after unlearning is applied. Technically, we formulate this attack as a bi-level optimization problem: to overcome the challenges of black-box unlearning and label scarcity, we approximate the unlearning process via gradient-based updates and employ a surrogate model to generate pseudo-labels for the optimization. Extensive experiments across benchmarks and unlearning algorithms demonstrate that small, carefully designed unlearning requests can induce significant accuracy degradation, raising urgent concerns about the robustness of GNN unlearning under real-world regulatory demands. The source code will be released upon paper acceptance.

cs.LG↗

arXiv2026

Observer-Actor: Active Vision Imitation Learning with Sparse-View Gaussian Splatting

We propose Observer Actor (ObAct), a novel framework for active vision imitation learning in which the observer moves to optimal visual observations for the actor. We study ObAct on a dual-arm robotic system equipped with wrist-mounted cameras. At test time, ObAct dynamically assigns observer and actor roles: the observer arm constructs a 3D Gaussian Splatting (3DGS) representation from three images, virtually explores this to find an optimal camera pose, then moves to this pose; the actor arm then executes a policy using the observer's observations. This formulation enhances the clarity and visibility of both the object and the gripper in the policy's observations. As a result, we enable the training of ambidextrous policies on observations that remain closer to the occlusion-free training distribution, leading to more robust policies. We study this formulation with two existing imitation learning methods -- trajectory transfer and behavior cloning -- and experiments show that ObAct significantly outperforms static-camera setups: trajectory transfer improves by 145% without occlusion and 233% with occlusion, while behavior cloning improves by 75% and 143%, respectively. Videos are available at https://obact.github.io.

cs.RO↗

arXiv2026

On the gauge invariance of the Kuperberg invariant of certain high genus framed 3-manifolds

We show that the Kuperberg invariant of the Weeks manifold with any framing is a gauge invariant of finite-dimensional Hopf algebras, which provides the first example of gauge invariants of general finite-dimensional Hopf algebras via hyperbolic 3-manifolds. We also show that the Kuperberg invariant of the 3-torus is gauge invariant, which further supports the idea of systematically producing gauge invariants of Hopf algebras via topological methods proposed in \cite{CNW25}.

math.QA↗

arXiv2026

iFlip: Iterative Feedback-driven Counterfactual Example Refinement

Counterfactual examples are minimal edits to an input that alter a model's prediction. They are widely employed in explainable AI to probe model behavior and in natural language processing (NLP) to augment training data. However, generating valid counterfactuals with large language models (LLMs) remains challenging, as existing single-pass methods often fail to induce reliable label changes, neglecting LLMs' self-correction capabilities. To explore this untapped potential, we propose iFlip, an iterative refinement approach that leverages three types of feedback, including model confidence, feature attribution, and natural language. Our results show that iFlip achieves an average 57.8% higher validity than the five state-of-the-art baselines, as measured by the label flipping rate. The user study further corroborates that iFlip outperforms baselines in completeness, overall satisfaction, and feasibility. In addition, ablation studies demonstrate that three components are paramount for iFlip to generate valid counterfactuals: leveraging an appropriate number of iterations, pointing to highly attributed words, and early stopping. Finally, counterfactuals generated by iFlip enable effective counterfactual data augmentation, substantially improving model performance and robustness.

cs.CL↗

arXiv2025

A fast powerful X-ray transient from possible tidal disruption of a white dwarf

Stars captured by black holes (BHs) can be torn apart by strong tidal forces, producing electromagnetic flares. To date, more than 100 tidal disruption events (TDEs) have been observed, each involving invariably normal gaseous stars whose debris falls onto the BH, sustaining the flares over years. White dwarfs (WDs), which are the most prevalent compact stars and a million times denser--and therefore tougher--than gaseous stars, can only be disrupted by intermediate-mass black holes (IMBHs) of 10^2--10^5 solar masses. WD-TDEs are considered to generate more powerful and short-lived flares, but their evidence has been lacking. Here we report observations of a fast and luminous X-ray transient EP250702a detected by Einstein Probe. Its one-day-long X-ray peak as luminous as 10^(47-49) erg/s showed strong recurrent flares with hard spectra extending to several tens of MeV gamma-rays, as detected by Fermi/GBM and Konus-Wind, indicating relativistic jet emission. The jet's X-ray dropped sharply from 3 x 10^49 erg/s to around 10^44 erg/s within 20 days (10 days in the source rest frame). These characteristics are inconsistent with any known transient phenomena other than a jetted-TDE evolving over an unprecedentedly short timescale, indicating the disruption of a WD by an IMBH. At late times, a new soft component progressively dominates the X-ray spectrum, exhibiting an extreme super-Eddington luminosity, which possibly originates from an accretion disc. WD-TDEs open a new window for investigating the elusive IMBHs and their surrounding stellar environments, and they are prime sources of gravitational waves in the band of space-based interferometers.

astro-ph.HE↗

arXiv2025

Accretion geometry in neutron star low-mass X-ray binaries during the hard spectral state

We investigate the accretion geometry in neutron star low-mass X-ray binaries (LMXBs) in the hard spectral state. It is commonly accepted that, for low mass transfer rates, an advection-dominated accretion flow (ADAF) is present in the inner region. But the observed relativistically broadened emission lines in the reflection spectra clearly indicate the existence of discs near the innermost stable circular orbit $(R_{\rm{ISCO}})$. We investigate the interaction between the coronal flow and the disc in neutron star LMXBs, and find that gas condensation from the dominant, coronal accretion flow to an inner disc is enhanced as compared to that in black hole LMXBs as a consequence of irradiation of the corona by the neutron star surface. Computations show that for low mass transfer rates ($\sim 0.005-0.02$ Eddington rate) a persistent weak disc can coexist with a coronal flow in the innermost region, where a pure ADAF would have been expected. The inner disc extends outwards from $R_{\rm{ISCO}}$ to $\sim 10 R_{\rm{ISCO}}$ for Eddington ratios ($L/L_{\rm{Edd}}$) as low as $\sim 0.002$, covers a larger region for higher Eddington ratios, and eventually connects to the outer disc at $L/L_{\rm{Edd}} \sim 0.02$, thereby transiting to a soft state. We demonstrate that the observationally inferred region of the broad iron lines in the hard-state sources generally lies within the extension of the inner discs predicted by the condensation model. Disappearance of the broad iron lines is predicted at very low luminosities, either caused by very low accretion rates or disc truncation by strong magnetic fields.

astro-ph.HE↗

arXiv2025

Unlearning Inversion Attacks for Graph Neural Networks

Graph unlearning methods aim to efficiently remove the impact of sensitive data from trained GNNs without full retraining, assuming that deleted information cannot be recovered. In this work, we challenge this assumption by introducing the graph unlearning inversion attack: given only black-box access to an unlearned GNN and partial graph knowledge, can an adversary reconstruct the removed edges? We identify two key challenges: varying probability-similarity thresholds for unlearned versus retained edges, and the difficulty of locating unlearned edge endpoints, and address them with TrendAttack. First, we derive and exploit the confidence pitfall, a theoretical and empirical pattern showing that nodes adjacent to unlearned edges exhibit a large drop in model confidence. Second, we design an adaptive prediction mechanism that applies different similarity thresholds to unlearned and other membership edges. Our framework flexibly integrates existing membership inference techniques and extends them with trend features. Experiments on four real-world datasets demonstrate that TrendAttack significantly outperforms state-of-the-art GNN membership inference baselines, exposing a critical privacy vulnerability in current graph unlearning methods.

cs.LG↗

arXiv2025

Generalized Witt and Morita equivalences

In this work, we introduce a family of new equivalence relations among fusion categories that are less refined than the usual Morita equivalence. We obtain abelian groups by quotienting these new equivalence relations from the commutative monoids of the equivalence classes of all fusion categories. Moreover, we upgrade them to equivalence relations among nondegenerate braided fusion categories that are more refined than the usual Witt equivalence. As a consequence, we obtain new abelian groups that are more refined than the usual Witt group. These new groups allow us to access the internal structures within Witt classes. We expect that they are useful in the classification program of (braided) fusion (higher) categories and in the study of gapless edges of 2+1D topological orders.

math.QA↗

arXiv2025

Every Step Evolves: Scaling Reinforcement Learning for Trillion-Scale Thinking Model

We present Ring-1T, the first open-source, state-of-the-art thinking model with a trillion-scale parameter. It features 1 trillion total parameters and activates approximately 50 billion per token. Training such models at a trillion-parameter scale introduces unprecedented challenges, including train-inference misalignment, inefficiencies in rollout processing, and bottlenecks in the RL system. To address these, we pioneer three interconnected innovations: (1) IcePop stabilizes RL training via token-level discrepancy masking and clipping, resolving instability from training-inference mismatches; (2) C3PO++ improves resource utilization for long rollouts under a token budget by dynamically partitioning them, thereby obtaining high time efficiency; and (3) ASystem, a high-performance RL framework designed to overcome the systemic bottlenecks that impede trillion-parameter model training. Ring-1T delivers breakthrough results across critical benchmarks: 93.4 on AIME-2025, 86.72 on HMMT-2025, 2088 on CodeForces, and 55.94 on ARC-AGI-1. Notably, it attains a silver medal-level result on the IMO-2025, underscoring its exceptional reasoning capabilities. By releasing the complete 1T parameter MoE model to the community, we provide the research community with direct access to cutting-edge reasoning capabilities. This contribution marks a significant milestone in democratizing large-scale reasoning intelligence and establishes a new baseline for open-source model performance.

cs.CL↗