Searcharxiv⌕ Search

arXiv subjects

Xin Sun

Publications and source records attributed to Xin Sun.

At least 55 records · Page 3Linked to original sources
arXiv2026

GAPD: Gold-Action Policy Distillation for Agentic Reinforcement Learning in Knowledge Base Question Answering

Reinforcement learning (RL) is a natural fit for agentic knowledge base question answering (KBQA), where a model must issue executable actions, observe knowledge-base feedback, and eventually return an answer. However, current RL-based KBQA systems mainly optimize sparse rewards from the final answer, leaving intermediate action errors weakly supervised. This is especially limiting for logical-form annotated KBQA benchmarks: gold logical forms can be converted into executable action sequences, but existing pipelines use them mainly for warm-start data construction rather than for on-policy RL updates. We propose GAPD, a training-time Gold-Action Policy Distillation framework that adds dense token-level guidance to outcome-based RL. To align gold actions with on-policy student rollouts, GAPD uses MID-ANCHOR MATCHING: it treats the intermediate entities reached during student exploration and gold execution as state anchors, and matches student states to gold states through these explored entity sets. The current policy conditioned on this aligned gold action serves as a stop-gradient teacher, whose token distribution is distilled back to the ordinary student policy over generated action-token spans. GAPD consistently surpasses the current state of the art on WebQSP, GrailQA, and GraphQ.

cs.CL↗
arXiv2026

Uncovering Competing Poisoning Attacks in Retrieval-Augmented Generation

Retrieval-Augmented Generation (RAG) systems improve the factual grounding of large language models (LLMs) but remain vulnerable to retrieval poisoning, where adversaries seed the corpus with manipulated content. Prior work largely evaluates this threat under a simplified single-attacker assumption. In practice, however, high-value or high-visibility queries attract multiple adversaries with conflicting objectives. Motivated by real cases, we introduce the setting of competing attacks, in which multiple attackers simultaneously attempt to steer the same or closely related query toward different targets. We formalize this threat model and propose competitive effectiveness, a metric that quantifies an attacker's advantage under competition. Extensive experiments show that many strategies that succeed in the single-attacker regime degrade markedly under competition, revealing performance inversions and highlighting the limits of conventional metrics such as attack success rate and F1. Furthermore, we present PoisonArena, a standardized framework and benchmark for evaluating poisoning attacks and defenses under realistic, multi-adversary conditions.

cs.IR↗
arXiv2026

Rate Maximization for Multi-Waveguide PASS: A Hierarchical User Scheduling and Joint Optimization Framework

Pinching-antenna systems (PASS) have emerged as a promising flexible-antenna architecture capable of dynamically reconfiguring wireless channels by activating dielectric particles along waveguides. The sum rate maximization problem in multi-waveguide PASS is investigated in this study. Both in-waveguide propagation loss and coupling effects are explicitly modeled. To tackle the optimization problem, a hierarchical user scheduling (HUS) algorithm is proposed. The HUS algorithm minimizes the sum of squared distances between users and their associated waveguides to mitigate path loss. Additionally, spatially separated users are assigned within each time slot to reduce inter-user interference. Furthermore, a joint optimization framework integrating power allocation and pinching-antenna (PA) positioning is developed to further improve system sum rate. Specifically, PAs' positions are optimized via one-dimensional search, while the power allocation problem is solved by using the Lagrangian duality and fractional programming. Numerical results show that the HUS algorithm clearly outperforms random pairing, and the proposed power allocation algorithm shows a marked performance improvement over the maximum ratio transmission algorithm. Moreover, the results explicitly demonstrate the considerable impact of in-waveguide propagation loss and coupling effects on the performance of PASS.

cs.IT↗
arXiv2026

Integrated Positioning and Communications for PASS: A Robust Approach

The pinching-antenna systems (PASS), which dynamically activate and relocate the pinching-antennas (PAs) along the dielectric waveguide, offer unprecedented potential for integrated positioning and communication. The multi-waveguide-based uplink positioning approaches for indoor environments are first proposed in this paper, and the downlink communication performance is analyzed. Two possible scenarios, multi-waveguide single-PA (MWSP) and multi-waveguide multi-PA (MWMP), are considered under the assumptions of line-of-sight channels and a single, stationary user. For the MWSP scenario, the received signal strength indication (RSSI)-based ranging method and the MWSP-based least square (LS) positioning algorithm are developed. To gain deeper insights, a comprehensive error analysis of the LS positioning algorithm is conducted. Subsequently, for the MWMP scenario, the closed-form expression of the superposed signal is derived. According to the signal power, the MWMP-based grid search algorithm is proposed and the estimation error of proposed algorithm is analyzed. Then, based on the user's positioning result, the PAs are relocated to provide downlink communication service, and the achievable data rate of MWSP and MWMP scenarios are analyzed. Numerical results validate the correctness of our analysis, which show that: i) For the MWSP scenario, a smaller geometric dilution of precision (GDoP) leads to a lower average positioning error. Furthermore, even when the GDoP is large, the regions where the distances to PAs are nearly equal achieve the best accuracy. ii) For the MWMP scenario, non-parallel waveguide deployment improves positioning accuracy, although errors increase with the number of PAs. iii) The noise has a serious double-impact on data rate. There is a trade-off between positioning accuracy and communication performance.

eess.SP↗
arXiv2026

Multi-/Uni-Cast Non-Orthogonal Multiple Access-Based INAC

With the rapid development of satellite communication and navigation, there is an urgent need to integrate both technologies to achieve reliable communication and precise navigation services within the same satellite system. By combining multi-/uni-cast (MUC) and non-orthogonal multiple access (NOMA) technologies, we propose a novel MUC-NOMA-based integrated navigation and communication (INAC) signal structure, in which the navigation and communication signals share a common pseudo noise (PN) sequence, thereby integrating satellite communication and navigation at the signal level. According to different power allocation strategies, two scenarios are defined: multi-cast-oriented (MO-) INAC and uni-cast-oriented (UO-) INAC, where a greater portion of power is assigned to either the multi-cast or the uni-cast signal, respectively. To mitigate co-channel interference, we employ successive interference cancellation (SIC) at the receiver and design a signal processing algorithm for the proposed INAC signal. Then, closed-form expressions are subsequently derived for the bit error rates (BER) of both the navigation and communication signals, along with the positioning accuracy of the navigation signal. To gain further insights, the impacts of power allocation factors and communication rates are evaluated. Our analysis results show that: i) In the MO-INAC scenario, the positioning and BER performance of navigation signal are excellent when more power is assigned to the multi-cast signal; ii) In the UO-INAC scenario, interference in the shared resources is reduced when more power is assigned to the uni-cast signal; iii) The ranging accuracy decreases as the communication data rate increases. Numerical results confirm the superior BER and positioning accuracy of the MO-INAC scenario for MEO satellites.

eess.SP↗
arXiv2026

DV-SFT: Direct Vision Supervision for Fine-Grained Visual Understanding

Multimodal large language models are typically trained end-to-end to predict ground-truth answers, yet supervision signals are applied exclusively to text tokens. Visual tokens, the core carriers of visual information, are optimized only implicitly as part of the context, leading to coarse-grained visual understanding. Prior works attempt to supervise visual inputs but inevitably rely on auxiliary components such as additional decoders or forward passes, because visual tokens lack readily interpretable labels. This limits their practical applicability. In this work, we propose \textbf{D}irect \textbf{V}ision \textbf{S}upervised \textbf{F}ine-\textbf{T}uning (DV-SFT), which constructs explicit, token-level supervision for visual tokens and trains them through the same next-token prediction objective used for text. Specifically, we exploit the direct vision--text correspondence in OCR-related scenarios and automatically label each visual token with the word in its corresponding image patch. DV-SFT treats the MLLM as a black box, requiring no architectural modifications or additional forward passes. Extensive experiments demonstrate the superiority of direct vision supervision. DV-SFT consistently outperforms standard SFT across three in-domain and four out-of-domain benchmarks. Further analyses show that vision supervision effectively enhances fine-grained visual understanding and achieves higher multimodal alignment efficiency.

cs.CV↗
arXiv2026

Satellite Navigation: A Transmitting Intelligent Surface (TIS)-aided Indoor System

A transmitting intelligent surfaces (TISs) aided satellite indoor navigation system is investigated. By leveraging the unique features of TIS, we address the limitations of conventional global navigation satellite systems (GNSS) in providing reliable positioning services within indoor environments. To facilitate the extension of GNSS indoor signals, we establish an extended line-of-sight link using TIS which has the capability to change signal direction. A three-stage TIS-aided satellite indoor positioning algorithm (TSIPA), which utilizes the positions of TIS arrays and the angle of arrival, is proposed to locate indoor users. To evaluate the distribution of TIS arrays, we propose TIS position dilution of precision (TPDoP) to evaluate centroid deviation and utilize the root mean square error (RMSE) to represent compactness.

cs.IT↗
arXiv2026

Tell Model Where to Look: Mitigating Hallucinations in MLLMs by Vision-Guided Attention

Visual attention serves as the primary mechanism through which MLLMs interpret visual information; however, its limited localization capability often leads to hallucinations. We observe that although MLLMs can accurately extract visual semantics from visual tokens, they fail to fully leverage this advantage during subsequent inference. To address this limitation, we propose Vision-Guided Attention (VGA), a training-free method that first constructs precise visual grounding by exploiting the semantic content of visual tokens, and then uses this grounding to guide the model's focus toward relevant visual regions. In image captioning, VGA further refines this guidance dynamically during generation by suppressing regions that have already been described. In VGA, each token undergoes only a single forward pass, introducing a negligible latency overhead. In addition, VGA is fully compatible with efficient attention implementations such as FlashAttention. Extensive experiments across diverse MLLMs and multiple hallucination benchmarks demonstrate that VGA achieves state-of-the-art dehallucination performance. Further analysis confirms that explicit visual guidance plays a crucial role in enhancing the visual understanding capabilities of MLLMs.

cs.CV↗
arXiv2026

Resource-Constrained UAV-Based Weed Detection for Site-Specific Management on Edge Devices

Weeds compete with crops for light, water, and nutrients, reducing yield and crop quality. Efficient weed detection is essential for site-specific weed management (SSWM). Although deep learning models have been deployed on UAV-based edge systems, a systematic understanding of how different model architectures perform under real-world resource constraints is still lacking. To address this gap, this study proposes a deployment-oriented framework for real-time UAV-based weed detection on resource-constrained edge platforms. The framework integrates UAV data acquisition, model development, and on-device inference, with a focus on balancing detection accuracy and computational efficiency. A diverse set of state-of-the-art object detection models is evaluated, including convolution-based YOLO models (v8-v12) and transformer-based RT-DETR models (v1-v2). Experiments on three edge devices (Jetson Orin Nano, Jetson AGX Xavier, and Jetson AGX Orin) demonstrate clear trade-offs between accuracy and inference latency across models and hardware configurations. Results show that high-capacity models achieve up to 86.9% mAP50 but suffer from high latency, limiting real-time deployment. In contrast, lightweight models achieve 66%-71% mAP50 with significantly lower latency, enabling real-time performance. Among all models, RT-DETRv2-R50-M achieves competitive accuracy (79% mAP50) with improved efficiency, while YOLOv10n provides the fastest inference speed. YOLOv11s and RT-DETRv2-R50-M offer the best balance between accuracy and speed, making them strong candidates for real-time UAV deployment.

cs.CV↗
arXiv2026

StoryMI: Steerable Multi-Agent Therapeutic Dialogue Generation

Large language models (LLMs) can generate fluent dialogue, but prior works lack situational grounding, dynamic strategy control, and evaluation aligned with clinical standards in motivational interviewing (MI). We introduce StoryMI, a multi-LLM agent framework for controllable MI dialogue generation, where questionnaire-based client profiles are expanded into situational stories that provide narrative context for the dialogue. Therapist and client agents generate MI-coded utterances guided by MI codes selected by the interaction agent, while an interaction agent dynamically coordinates exchanges to control MI strategies during a multi-turn conversation. We propose a two-level evaluation protocol: lexical metrics and MI-specific measures of macro-level counseling strategies, alongside LLM-as-judge and human expert assessments. We construct a dataset of 6K simulated MI dialogues grounded in 1K questionnaire-story pairs, covering 12 MI codes and 13 symptom domains, and benchmark six open- and closed-source LLMs. Our results show that situational grounding and macro-level control can improve MI adherence and clinical plausibility, demonstrating the effectiveness of a structured multi-agent workflow for psychotherapy dialogue generation. We provide code and data for reproducibility.

cs.CL↗
arXiv2026

Exact solution of three-point functions in critical loop models

We propose an exact formula for three-point functions on the sphere in critical loop models with primary fields $V_{(r,s)}$ characterized by $2r$ legs and a parameter \(s\) that describes diagonal fields for $r=0$ and the momentum of legs for $r>0$. We demonstrate its validity in three ways: the conformal bootstrap method for 4-point functions, a transfer-matrix study of the lattice model, and a probabilistic method based on conformal loop ensemble and Liouville quantum gravity. This work provides a crucial missing piece for solving critical loop models and reveals a deep unity between three fundamental approaches to 2D statistical physics: transfer matrix, conformal field theory, and probability theory.

cond-mat.stat-mech↗
arXiv2026

Label Effects: Shared Heuristic Reliance in Trust Assessment by Humans and LLM-as-a-Judge

Large language models (LLMs) are increasingly used as automated evaluators (LLM-as-a-Judge). This work challenges its reliability by showing that trust judgments by LLMs are biased by disclosed source labels. Using a counterfactual design, we find that both humans and LLM judges assign higher trust to information labeled as human-authored than to the same content labeled as AI-generated. Eye-tracking data reveal that humans rely heavily on source labels as heuristic cues for judgments. We analyze LLM internal states during judgment. Across label conditions, models allocate denser attention to the label region than the content region, and this label dominance is stronger under Human labels than AI labels, consistent with the human gaze patterns. Besides, decision uncertainty measured by logits is higher under AI labels than Human labels. These results indicate that the source label is a salient heuristic cue for both humans and LLMs. It raises validity concerns for label-sensitive LLM-as-a-Judge evaluation, and we cautiously raise that aligning models with human preferences may propagate human heuristic reliance into models, motivating debiased evaluation and alignment.

cs.AI↗
arXiv2026

Stochastic Ray Tracing for the Reconstruction of 3D Gaussian Splatting

Ray-tracing-based 3D Gaussian splatting (3DGS) methods overcome the limitations of rasterization -- rigid pinhole camera assumptions, inaccurate shadows, and lack of native reflection or refraction -- but remain slower due to the cost of sorting all intersecting Gaussians along every ray. Moreover, existing ray-tracing methods still rely on rasterization-style approximations such as shadow mapping for relightable scenes, undermining the generality that ray tracing promises. We present a differentiable, sorting-free stochastic formulation for ray-traced 3DGS -- the first framework that uses stochastic ray tracing to both reconstruct and render standard and relightable 3DGS scenes. At its core is an unbiased Monte Carlo estimator for pixel-color gradients that evaluates only a small sampled subset of Gaussians per ray, bypassing the need for sorting. For standard 3DGS, our method matches the reconstruction quality and speed of rasterization-based 3DGS while substantially outperforming sorting-based ray tracing. For relightable 3DGS, the same stochastic estimator drives per-Gaussian shading with fully ray-traced shadow rays, delivering notably higher reconstruction fidelity than prior work.

cs.CV↗
arXiv2026

Evolving fractal dimensions in iterative bicolored percolation

Criticality is traditionally regarded as an unstable, fine-tuned fixed point of the renormalization group. We introduce an iterative bicolored percolation process in two dimensions and show that it can both preserve criticality and transform fractal dimensions. Starting from critical configurations, such as the O$(n)$ loop and fuzzy Potts models, successive coarse-graining generates a hierarchy of distinct yet critical generations. Using the conformal loop ensemble, we derive exact, generation-dependent fractal dimensions, which are quantitatively confirmed by large-scale Monte Carlo simulations. The evolutionary trajectory depends not only on the universality class of the initial state but also on whether it possesses a two-state critical structure, leading to different critical exponents starting from site and bond percolation. These results establish a general geometric mechanism for evolving fractal dimensions, in which scale invariance persists across generations.

cond-mat.stat-mech↗
arXiv2026

How to Utilize Complementary Vision-Text Information for 2D Structure Understanding

LLMs typically linearize 2D tables into 1D sequences to fit their autoregressive architecture, which weakens row-column adjacency and other layout cues. In contrast, purely visual encoders can capture spatial cues, yet often struggle to preserve exact cell text. Our analysis reveals that these two modalities provide highly distinct information to LLMs and exhibit strong complementarity. However, direct concatenation and other fusion methods yield limited gains and frequently introduce cross-modal interference. To address this issue, we propose DiVA-Former, a lightweight architecture designed to effectively integrate vision and text information. DiVA-Former leverages visual tokens as dynamic queries to distill long textual sequences into digest vectors, thereby effectively exploiting complementary vision--text information. Evaluated across 13 table benchmarks, DiVA-Former improves upon the pure-text baseline by 23.9\% and achieves consistent gains over existing baselines using visual inputs, textual inputs, or a combination of both.

cs.CV↗
arXiv2026

Modeling Inverse Ellipsometry Problem via Flow Matching with a Large-Scale Dataset

Inverse ellipsometry, i.e., reconstructing optical constants and film thickness from the measured phase difference $Δ$ and amplitude ratio $Ψ$, is a fundamentally ill-posed problem. Traditional solutions rely on slow, expert-driven iterative fitting, while the development of machine learning approaches has been severely limited by the lack of large-scale, physically consistent datasets. To address this gap, we introduce \textbf{EllipBench}, a comprehensive benchmark comprising over 8 million high-precision samples spanning 98 thin-film materials and 5 substrates. Building upon this benchmark, we conduct a systematic evaluation of a broad spectrum of methods, including traditional machine learning models, deep neural networks, and Physics-Informed Neural Networks, and show that existing paradigms consistently struggle to fully resolve the inverse ellipsometry task. To better capture its inherent ambiguity, we further propose a novel \textbf{Decoupled Conditional Flow Matching (DCFM)} framework. Rather than formulating the problem as deterministic point-to-point regression, DCFM explicitly decouples geometric film thickness and incorporates it as a robust physical condition to guide a continuous vector field for modeling the inverse probability distribution of wavelength-dependent optical constants. Combined with a gradient detachment strategy and physics-based constraints, our joint architecture effectively mitigates intrinsic physical ambiguities and delivers a robust and accurate solution for inverse ellipsometry.

cs.LG↗
arXiv2026

Quality Assurance of LLM-generated Code: Addressing Non-Functional Quality Characteristics

In recent years, large language models have been widely integrated into software engineering workflows, supporting tasks like code generation. While prior evaluations focus on functional correctness, there is still a limited understanding of the non-functional quality characteristics of generated code. Guided by the ISO/IEC 25010 quality model, this study adopts a multi-methods approach comprising three complementary elements: a literature review of 109 papers, two industry workshops with practitioners from multiple organizations, and an empirical analysis of patching real-world software issues using three LLMs. Motivated by insights from both the literature and practitioners, the empirical study examined the quality of generated patches regarding security, maintainability, and performance efficiency, which were identified as critical code-level quality attributes. Our results indicate that existing research primarily emphasizes security, performance efficiency, and maintainability, while other quality attributes are understudied. In contrast, practitioners prioritize maintainability and readability, warning that generated code may accelerate the accumulation of technical debt. The empirical evaluation demonstrates the instability of optimizing NFQCs through prompts in practical software engineering settings. Overall, our findings expose a misalignment between academic focus, industry priorities, and observed model behavior, highlighting the need to integrate quality assurance mechanisms into LLM code generation pipelines to ensure that future generated code not only passes tests but truly passes with quality.

cs.SE↗
arXiv2026

Revealing Combinatorial Reasoning of GNNs via Graph Concept Bottleneck Layer

Despite their success in various domains, the growing dependence on GNNs raises a critical concern about the nature of the combinatorial reasoning underlying their predictions, which is often hidden within their black-box architectures. Addressing this challenge requires understanding how GNNs translate topological patterns into logical rules. However, current works only uncover the hard logical rules over graph concepts, which cannot quantify the contribution of each concept to prediction. Moreover, they are post-hoc interpretable methods that generate explanations after model training and may not accurately reflect the true combinatorial reasoning of GNNs, since they approximate it with a surrogate. In this work, we develop a graph concept bottleneck layer that can be integrated into any GNN architectures to guide them to predict the selected discriminative global graph concepts. The predicted concept scores are further projected to class labels by a sparse linear layer. It enforces the combinatorial reasoning of GNNs' predictions to fit the soft logical rule over graph concepts and thus can quantify the contribution of each concept. To further improve the quality of the concept bottleneck, we treat concepts as "graph words" and graphs as "graph sentences", and leverage language models to learn graph concept embeddings. Extensive experiments on multiple datasets show that our method GCBMs achieve state-of-the-art performance both in classification and interpretability.

cs.LG↗