arXiv subjects

Yuxin Yang

Publications and source records attributed to Yuxin Yang.

At least 19 recordsLinked to original sources

arXiv2026

Gaze-DETR: Top-Down Guidance Through Priority Maps for Infrared Weak-Small UAV Detection with DETR

Infrared small target detection (ISTD) remains challenging because tiny, low-contrast targets are easily overwhelmed by clutter, noise, or occlusion. Conventional single-frame and multi-frame detectors rely on bounding-box supervision, which specifies final target locations but offers little explicit guidance for prioritizing candidate regions or preserving weak-target evidence before localization. Task-driven visual search offers such guidance: top-down goals and visual evidence jointly form a spatial priority map that ranks candidate locations. Building on this principle, we propose Gaze-DETR, a bio-inspired detector that learns an internal priority map before localization. First, a priority head predicts a normalized priority map from image features. Second, Residual Priority-Guided Feature Modulation (RPFM) enhances high-priority responses while retaining multi-scale features. Finally, Priority-Guided Anchor Query Injection (PAQI) converts high-priority locations into decoder anchor queries. We train the priority head using three supervision schemes: box-derived Gaussian maps; real-gaze maps constructed from fixation-density maps; and transferred pseudo-gaze maps learned from gaze--box relations in paired annotations and applied to Anti-UAV410 training boxes. To support the latter two schemes, we construct TIR-UAV120-Gaze with paired detection and task-driven eye-tracking annotations. On TIR-UAV120-Gaze, Gaze-DETR achieves 85.76 mAP$_{50}$ and 88.77 F1 with box-derived supervision, and 86.18 mAP$_{50}$ and 89.00 F1 with real-gaze supervision. On Anti-UAV410, it achieves 87.06 mAP$_{50}$ and 90.90 F1 with box-derived supervision, and 87.08 mAP$_{50}$ and 90.43 F1 with transferred pseudo-gaze supervision. These results show that explicit spatial-priority learning provides pre-localization guidance complementary to bounding-box supervision across annotation settings and costs.

cs.CV↗

arXiv2026

Adaptive Fault Injection Planning for Multi-Layer Self-Healing AI Infrastructure

Modern GPU-accelerator platforms rely on multi-layer self-healing pipelines that span hardware, firmware, management software, and orchestration. When faults propagate across layer boundaries, they can bypass detection, corrupt diagnosis, or trigger conflicting remediations--yet conventional fault-injection campaigns test each layer in isolation. We present ADA-ST, an adaptive fault-injection methodology that uses a weighted fault-propagation graph to guide cross-layer scenario selection. We construct four-layer graphs for three successive platforms at a hyperscale operator: Alpha, Beta, and Gamma. Platform Alpha, a production system that accumulated 72,550 repair tickets over four years, provides the empirical foundation; 49% of those tickets involve cross-layer fault propagation. We show that existing static test campaigns cover only 20-25% of the modeled fault-propagation edges, leaving approximately three-quarters of the cross-layer attack surface unexercised. ADA-ST closes this gap through iterative, activity-guided scenario selection that maximizes marginal coverage gain per iteration, reaching full edge coverage within 10 iterations on Alpha, 12 on Beta, and 9 on Gamma. The Fault-Layer Abstraction Mapping (FLAM) transfers propagation knowledge across hardware generations with 100% fidelity from Alpha to Beta and 96% from Beta to Gamma. Physical spot-validation on the newest platform confirms all four tested propagation edges, revealing cross-layer vulnerabilities spanning telemetry blind spots, absence-based detection gaps, multi-signal correlation failures, and trust-without-verification propagation at the L2-to-L3 boundary.

cs.ET↗

arXiv2026

Quantum Sampling Architecture for Protein Structure Reconstruction on Utility-Scale Hardware

Predicting the structure of short peptides in protein binding pockets remains difficult because this regime requires physics-based conformational search, yet existing methods do not provide a practical way to carry out that search on current hardware. We present QSAD, a quantum-classical framework that reformulates peptide structure prediction as amino-acid-level Hamiltonian sampling and replaces iterative optimization with non-iterative Hamiltonian evolution. Executed entirely on IBM Heron R2 across 101 binding-pocket peptides (5-18 residues), QSAD improves prediction accuracy by 27-71% over all evaluated AI and quantum baselines while maintaining the lowest variance across tested lengths. QSAD also tolerates noise levels 3-5x beyond typical hardware error rates, where iterative methods fail, and reduces mean quantum execution time by 27x relative to VQE. The sampled ensemble further supports approximate reconstruction of protein energy landscapes. These results establish coarse-grained quantum sampling as a practical computational path for structure prediction in regimes where data-driven methods lack sufficient signal.

cs.ET↗

arXiv2026

Online Data Selection Is Implicit Alignment

Supervised fine-tuning (SFT) is often treated as a capability-adaptation step, while alignment is attributed to later preference optimization or reinforcement learning. This separation is incomplete: when examples are scored and kept online during fine-tuning, the choice of which data to train on already changes the model's behavioral preferences. We study online data selection as an implicit alignment mechanism. Given the same base model, optimizer, and selected-token budget, we compare random, loss-based, quality-based, and diversity-based online selectors and measure the behavioral drift they induce without any preference optimization. The proposed evaluation tracks helpfulness, refusal rate, verbosity, truthfulness, sycophancy, calibration, and jailbreak robustness, together with diagnostics for which behavioral modes are over-represented in the selected data. We formalize online selection as a reweighted SFT objective whose weights define an implicit preference over response styles and safety postures, so that an online scorer plays the role usually assigned to a reward model. This view predicts that high-scoring data can systematically favor longer, more assertive, more compliant, or more refusal-prone behaviors depending on how the online score is defined. Empirically, selectors that are statistically indistinguishable in task accuracy diverge sharply in refusal rate, verbosity, and sycophancy, and we show that the direction of the shift is predictable from the attribute mixture of the selected data. We introduce Alignment Drift Auditing (ADA), a controlled protocol for quantifying selection-induced behavioral movement, and Alignment-Aware Selection (AAS), a diagnostic online selector that retains data efficiency while constraining drift along safety and style axes.

cs.LG↗

arXiv2026

MMAgent-R$^2$: Learning to Rerank and Reject for Agentic mRAG

Knowledge-based Visual Question Answering (KB-VQA) requires models to retrieve visual entities matching the query image from large-scale encyclopedic knowledge bases and answer related questions. Existing multimodal Retrieval Augmented Generation (mRAG) methods rely on global visual features to match candidate entities, yet when the knowledge base contains numerous visually similar entities, the retriever struggles to distinguish them, populating the candidate set with visually similar but factually mismatched distractors. Since subsequent processing steps such as noise filtering are also confined to this fixed candidate set, errors from failed retrieval inevitably propagate to the final answer. To address these challenges, we propose MMAgent-R$^2$, an agentic mRAG framework that integrates visual reranking and active rejection as its internal verification mechanism. Visual reranking directly compares query and candidate images, capturing discriminative details beyond textual descriptions to precisely identify the target entity among similar candidates; active rejection discards unreliable results and retrieves additional candidates when no confident match is found, moving beyond the fixed candidate pool. We design a composite reward function with step-level verification rewards and achieve joint optimization of external retrieval, internal verification, and answer generation via GRPO training. Experiments on InfoSeek, E-VQA, and MMhops demonstrate that \ours{} achieves state-of-the-art performance, with particularly notable advantages in challenging retrieval scenarios and complex multi-image multi-hop reasoning tasks.

cs.CV↗

arXiv2026

Leveraging Metric Depth for Relative Depth Prediction

We present our solution to the 2025 SoccerNet Monocular Depth Estimation Competition Challenge. Predicting the relative depth in football scenarios is challenging, especially with only thousands of training samples available. To address this issue, our method leverages the powerful zero-shot capabilities of models pretrained on large-scale datasets to learn metric depth for effective relative depth prediction, achieving a score of $2.68 \times 10^{-3}$ on the challenge set.

cs.CV↗

arXiv2026

Representation Collapse in Sequential Post-Training of Large Language Models

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

cs.LG↗

arXiv2026

The Long-Term Effects of Data Selection in LLM Fine-Tuning

Data selection is increasingly used to reduce the cost of large language model (LLM) fine-tuning, with recent methods prioritizing samples by current utility, diversity, quality, or influence. This paper studies a different question: when fine-tuning occurs over multiple stages, can selection strategies that look optimal now make the model less adaptable later? We introduce a long-horizon view of LLM data selection in which a selector is evaluated not only by immediate task performance, but also by future adaptation speed, forgetting, capability imbalance, and out-of-distribution robustness. We compare representative random, loss-based, gradient-based, diversity-based, quality-based, and utility-diversity selection families under a unified multi-stage protocol. Through controlled experiments designed to instantiate this protocol, we show how short-term selectors can exhibit rank reversal: they improve the current stage while slowing subsequent learning and increasing forgetting. We formalize this behavior as \emph{myopic selection}, provide a simple local analysis of why it can occur, and propose a diagnostic Long-Horizon Aware Selection (LHAS) objective that augments immediate utility with coverage, future-proxy transfer, and anti-concentration terms. The study argues that data selection should be evaluated as a training intervention that shapes the model's learning trajectory, rather than only as a local data-efficiency mechanism.

cs.LG↗

arXiv2026

DDGAD: Trajectory Dynamics for Diffusion-Based Graph Anomaly Detection

Graph anomaly detection (GAD) aims to identify nodes or substructures whose behavior or attributes deviate significantly from the overall pattern in graph-structured data, with critical applications in financial risk control, social network analysis, and cybersecurity. However, existing GCN-based methods suffer from the fundamental problem of contamination propagation, where anomalous nodes pollute the representations of their neighbors through message passing, leading to degraded detection performance. In this paper, we propose DDGAD, a novel diffusion-based graph anomaly detection framework that leverages trajectory dynamics to distinguish normal and anomalous nodes. Our key insight is that normal nodes exhibit consistent and stable representation trajectories under the coupled effects of diffusion regularization and reliability-aware neighborhood consensus, while anomalous nodes exhibit unstable and conflicting dynamics due to the directional disagreement between the global manifold prior and locally contaminated message passing. To mitigate contamination propagation, we introduce a distributed reliability-aware consensus refinement mechanism and define three complementary anomaly signals: neighbor inconsistency, reliability weight, and dynamical conflict energy. We further provide a preliminary theoretical analysis on normal node stability under the coupled dynamics. These signals collectively characterize anomalous behaviors from the perspectives of local inconsistency, consensus reliability, and dynamical instability. Extensive experiments on five real-world datasets demonstrate the effectiveness of the proposed framework.

cs.LG↗

arXiv2026

Modulation of Spin Angular Momentum of Emission in Symmetric 1D Plasmonic Crystals by Cathodoluminescence

The spin angular momentum (SAM) of light has become a cornerstone of numerous photonic applications, including optical communication and chiral photonics. Because SAM is inherently associated with circularly polarized light (CPL), the ability to modulate CPL in a controlled and efficient manner is essential not only for advancing fundamental studies of light-matter interactions but also for enabling next-generation photonic technologies. However, such modulation is commonly realized by structurally chiral systems, which inherently limits the feasibility of dynamic tuning. Here, we demonstrate that one-dimensional plasmonic crystals (1D PlCs), despite their structural symmetry, can serve as a platform for controllable CPL generation. By employing an electron beam in scanning transmission electron microscopy (STEM), we coherently excite transition radiation and emission from 1D PlC modes. Their interference produces energy- and momentum- (emission angle-) resolved CPL, which clearly reveals its dispersion and spatial dependence at the nanoscale, providing direct guidance for its manipulation and offering insights into the design of plasmonic devices including the phase information. Furthermore, interference with surface plasmon polariton scattering at the structural boundary enables the efficiency modulation of CPL generation via the excitation position along the terrace.

physics.optics↗

arXiv2026

Cracking Gravitational Wave Multiple Ringdown Modes in Space

Ringdown signals from perturbed black holes (BHs) offer a clean window into BH spacetime, strong-field gravity, and fundamental physics. Presently the quasi-normal modes of stellar-mass BH ringdowns have been successfully extracted in the ground-based gravitational wave (GW) observations. Looking ahead, the future space-borne observatories will listen to the ringdowns from massive BH binary coalescences more loudly and resolve multiple modes to unprecedented precision, which calls for efficient approaches to mitigate the sharply increasing computational burden. We develop a practical ringdown analysis pipeline for space-borne detectors by implementing FIREFLY, a novel acceleration algorithm validated in ground-based detectors, and for the first time demonstrate its compatibility and effectiveness with the time-delay interferometry (TDI) observables. With high fidelity, we achieve a $\sim 200$-fold speedup for a simulated ringdown signal including six modes, providing a viable and scalable route for multi-mode ringdown analysis in the space context. This new approach has sound statistical interpretation and is extensible to other GW sources in band.

gr-qc↗

arXiv2026

Beyond Semantic Search: Towards Referential Anchoring in Composed Image Retrieval

Composed Image Retrieval (CIR) has demonstrated significant potential by enabling flexible multimodal queries that combine a reference image and modification text. However, CIR inherently prioritizes semantic matching, struggling to reliably retrieve a user-specified instance across contexts. In practice, emphasizing concrete instance fidelity over broad semantics is often more consequential. In this work, we propose Object-Anchored Composed Image Retrieval (OACIR), a novel fine-grained retrieval task that mandates strict instance-level consistency. To advance research on this task, we construct OACIRR (OACIR on Real-world images), the first large-scale, multi-domain benchmark comprising over 160K quadruples and four challenging candidate galleries enriched with hard-negative instance distractors. Each quadruple augments the compositional query with a bounding box that visually anchors the object in the reference image, providing a precise and flexible way to ensure instance preservation. To address the OACIR task, we propose AdaFocal, a framework featuring a Context-Aware Attention Modulator that adaptively intensifies attention within the specified instance region, dynamically balancing focus between the anchored instance and the broader compositional context. Extensive experiments demonstrate that AdaFocal substantially outperforms existing compositional retrieval models, particularly in maintaining instance-level fidelity, thereby establishing a robust baseline for this challenging task while opening new directions for more flexible, instance-aware retrieval systems.

cs.CV↗

arXiv2026

SWE-Milestone: Evaluating AI Agents on Continuous Software Evolution

Real-world software must continuously evolve to meet ever-changing and open-ended requirements. AI agents, increasingly deployed as long-running systems, are now entrusted to drive this evolution. Yet, existing benchmarks evaluate agents on isolated, one-off coding tasks, neglecting the temporal dependencies and technical debt inherent in real-world software evolution. To bridge this gap, we introduce DeepCommit, an agentic pipeline that reconstructs verifiable Milestone DAGs from noisy commit logs, where milestones are defined as functionally cohesive development goals. These executable sequences enable SWE-Milestone, a benchmark that evaluates agents on streams of milestone-level tasks, requiring them to sustain system integrity and limit error accumulation, dimensions of long-term software evolution largely missing from current benchmarks. Our evaluation of 12 frontier models across 4 agent frameworks reveals a critical vulnerability: overall performance scores drop significantly from >80% on isolated tasks to 38.03% in continuous settings, exposing agents' profound struggle with long-term maintenance and error propagation.

cs.SE↗

arXiv2026

NeuroLoRA: Context-Aware Neuromodulation for Parameter-Efficient Multi-Task Adaptation

Parameter-Efficient Fine-Tuning (PEFT) techniques, particularly Low-Rank Adaptation (LoRA), have become essential for adapting Large Language Models (LLMs) to downstream tasks. While the recent FlyLoRA framework successfully leverages bio-inspired sparse random projections to mitigate parameter interference, it relies on a static, magnitude-based routing mechanism that is agnostic to input context. In this paper, we propose NeuroLoRA, a novel Mixture-of-Experts (MoE) based LoRA framework inspired by biological neuromodulation -- the dynamic regulation of neuronal excitability based on context. NeuroLoRA retains the computational efficiency of frozen random projections while introducing a lightweight, learnable neuromodulation gate that contextually rescales the projection space prior to expert selection. We further propose a Contrastive Orthogonality Loss to explicitly enforce separation between expert subspaces, enhancing both task decoupling and continual learning capacity. Extensive experiments on MMLU, GSM8K, and ScienceQA demonstrate that NeuroLoRA consistently outperforms FlyLoRA and other strong baselines across single-task adaptation, multi-task model merging, and sequential continual learning scenarios, while maintaining comparable parameter efficiency.

cs.LG↗

arXiv2026

SPARC-RAG: Adaptive Sequential-Parallel Scaling with Context Management for Retrieval-Augmented Generation

Retrieval-Augmented Generation (RAG) grounds large language model outputs in external evidence, but remains challenged on multi-hop question answering that requires long reasoning. Recent works scale RAG at inference time along two complementary dimensions: sequential depth for iterative refinement and parallel width for coverage expansion. However, naive scaling causes context contamination and scaling inefficiency, leading to diminishing or negative returns despite increased computation. To address these limitations, we propose SPARC-RAG, a multi-agent framework that coordinates sequential and parallel inference-time scaling under a unified context management mechanism. SPARC-RAG employs specialized agents that maintain a shared global context and provide explicit control over the scaling process. It generates targeted, complementary sub-queries for each branch to enable diverse parallel exploration, and explicitly regulates exiting decisions based on answer correctness and evidence grounding. To optimize scaling behavior, we further introduce a lightweight fine-tuning method with process-level verifiable preferences, which improves the efficiency of sequential scaling and effectiveness of parallel scaling. Across single- and multi-hop QA benchmarks, SPARC-RAG consistently outperforms previous RAG baselines, yielding an average +6.2 F1 improvement under lower inference cost.

cs.IR↗

arXiv2026

Intelligent Nano-Fingerprinting: An Efficient and Precise Approach for Liquid Biopsy

Biological matrices are rich in information related to life processes, serving as invaluable media for assessing an individual's overall physiological status and its dynamic fluctuations, as well as crucial foundations for disease diagnosis. However, the inherent complexity of these matrices, coupled with our incomplete understanding of their full composition, presents significant challenges for comprehensive analysis and accurate diagnostic interpretation. The advent of single-molecule technologies has revolutionized biomedical research, enabling the direct observation of life processes at the molecular scale. We have proposed an Intelligent Nano-Fingerprinting strategy based on single-molecule nanopore technology, designed to capture the global molecular fingerprints of complex plasma matrices. Furthermore, we developed an intelligent algorithmic model capable of achieving precise classification of plasma samples. This approach is characterized by its simplicity, efficiency, and considerable potential for large-scale adoption and transferable applications.

physics.bio-ph↗

arXiv2026

Disentangling Task Conflicts in Multi-Task LoRA via Orthogonal Gradient Projection

Multi-Task Learning (MTL) combined with Low-Rank Adaptation (LoRA) has emerged as a promising direction for parameter-efficient deployment of Large Language Models (LLMs). By sharing a single adapter across multiple tasks, one can significantly reduce storage overhead. However, this approach suffers from negative transfer, where conflicting gradient updates from distinct tasks degrade the performance of individual tasks compared to single-task fine-tuning. This problem is exacerbated in LoRA due to the low-rank constraint, which limits the optimization landscape's capacity to accommodate diverse task requirements. In this paper, we propose Ortho-LoRA, a gradient projection method specifically tailored for the bipartite structure of LoRA. Ortho-LoRA dynamically projects conflicting task gradients onto the orthogonal complement of each other within the intrinsic LoRA subspace. Extensive experiments on the GLUE benchmark demonstrate that Ortho-LoRA effectively mitigates task interference, outperforming standard joint training and recovering 95\% of the performance gap between multi-task and single-task baselines with negligible computational overhead.

cs.LG↗

arXiv2026

Towards Specialized Generalists: A Multi-Task MoE-LoRA Framework for Domain-Specific LLM Adaptation

The rapid evolution of Large Language Models (LLMs) has shifted focus from general-purpose capabilities to domain-specific expertise. However, adapting LLMs to specialized fields such as medicine presents two challenge: (1) the "Stability-Plasticity Dilemma", where the model must acquire complex clinical knowledge without suffering from catastrophic forgetting of general world knowledge; and (2) "Task Interference", where disparate sub-tasks, such as medical diagnosis, report summarization, and drug-drug interaction prediction, compete for limited low-rank parameter space. In this paper, we propose Med-MoE-LoRA, a novel framework that integrates Mixture-of-Experts (MoE) with Low-Rank Adaptation (LoRA) to enable efficient multi-task domain adaptation, especially for medical scenarios. Drawing inspiration from recent advances, our framework employs an asymmetric expert distribution where deeper layers are equipped with a higher density of LoRA experts to capture complex semantic abstractions. We further introduce a "Knowledge-Preservation Plugin", inspired by LoRA MoE, to isolate and protect general-purpose reasoning. By utilizing soft merging with adaptive routing and rank-wise decoupling, Med-MoE-LoRA achieves superior performance in medical benchmarks while reducing interference. Experimental results demonstrate that our approach consistently outperforms standard LoRA and conventional MoE architectures across multiple clinical NLP tasks while retaining the model's general cognitive capabilities.

cs.LG↗