arXiv subjects

Yue Kang

Publications and source records attributed to Yue Kang.

At least 19 recordsLinked to original sources

arXiv2026

Metag: A dataset to build agentic meta-reviewing capabilities

AI tools increasingly support tasks across the scientific research cycle, from experiment design and manuscript preparation to peer review. At the same time, the continuing growth in conference submissions has increased the burden on meta-reviewers, who must synthesize reviewer feedback, author rebuttals, and manuscript revisions. To address this concern, this paper introduces Metag, a dataset to accelerate the development of meta-reviewing agents, specifically to identify changes made to scientific articles during the review-rebuttal process. Each instance contains a reviewer concern, the author's proposed resolution, and the manuscript diffs implementing the stated change. Metag is collected by obtaining manuscript versions from before the review deadline and after acceptance, computing differences between the two documents, and asking human annotators to align these differences with action items from OpenReview discussions. The resulting dataset consists of 349 high-quality action items tied to paper differences and will enable building methods to empower meta reviewers to quickly identify whether authors have addressed reviewer statements and where in the paper those changes have been made, resulting in additional transparency and traceability throughout peer review. The dataset is publicly available at https://github.com/microsoft/Metag-dataset.

cs.LG↗

arXiv2026

Conditional Evaluation of Language Models with Cheap Auxiliary Signals

Aggregate accuracy hides where models succeed and fail. Estimating conditional performance profiles from gold labels alone is expensive, while cheap auxiliary signals such as LLM-judge scores, pairwise comparisons, confidence scores, and judge-disagreement features can be collected for every benchmark item but are often biased or miscalibrated. We propose LACE (Local Augmented Control-Variate Evaluation), a semi-supervised estimator for conditional LLM evaluation. The key step is local centering: after subtracting the conditional mean of a cheap signal within the target profile region, any linear augmentation has zero conditional mean and therefore cannot change the estimand. The augmentation coefficient is used only for efficiency, and a local ridge control variate combines a gold-label residual mean from the labeled subset with a cheap-signal mean from the full item pool. We prove calibration-free identification, unbiasedness for grouped profiles, local oracle optimality within centered linear augmentations, and first-order adaptivity to the estimated coefficient. The resulting gain formula is governed by a population local $R^2$, which characterizes how the efficiency attainable from the cheap signals varies across profile values. We also derive corresponding estimators for direct paired model gaps and deployment-weighted scores. We empirically evaluate the primary performance-profile estimator on MATH-500, ScienceQA, MMLU, WinoGrande, HellaSwag, TruthfulQA, GSM8K, and ARC.

cs.LG↗

arXiv2026

SDM-Q: Cost-Aware Staged Decision-Making for Multi-Omics Classification with Deep Q-Learning

Multi-omics data provide complementary molecular characterizations of disease phenotypes and play an important role in disease diagnosis and subtype classification in precision medicine. However, acquiring complete multi-omics profiles is expensive and time-consuming, while most existing deep learning methods assume full modality availability during inference, resulting in substantial redundancy and limited practicality in clinical settings. To address this issue, we propose SDM-Q, a reinforcement learning framework for adaptive and cost-aware multi-omics classification. Specifically, multi-omics diagnosis is reformulated as a finite-horizon sequential decision problem, where the currently acquired omics modalities define the diagnostic state at each stage. An action--value function determines whether to acquire an additional modality or terminate the decision process and output the final prediction. To balance diagnostic utility and acquisition cost, the reward is defined only at the terminal stage and jointly determined by classification correctness and cumulative modality acquisition cost. A backward stage-wise optimization strategy is introduced to improve policy consistency and training stability. Experiments on four public multi-omics datasets, including ROSMAP, LGG, BRCA, and KIPAN, demonstrate that SDM-Q effectively reduces redundant modality acquisition while maintaining competitive classification performance compared with methods using complete multi-omics inputs. In the BRCA and KIPAN datasets, more than 99\% and 95\% of subjects, respectively, achieve accurate classification using only a single omics modality, while the average number of acquired modalities remains below two for ROSMAP and LGG. These results suggest that cost-aware sequential decision-making provides an effective paradigm for improving the efficiency of precision medicine workflows.

cs.LG↗

arXiv2026

Fine-tuning Small Language Models as Efficient Enterprise Search Relevance Labelers

In enterprise search, building high-quality datasets at scale remains a central challenge due to the difficulty of acquiring labeled data. To resolve this challenge, we propose an efficient approach to fine-tune small language models (SLMs) for accurate relevance labeling, enabling high-throughput, domain-specific labeling comparable or even better in quality to that of state-of-the-art large language models (LLMs). To overcome the lack of high-quality and accessible datasets in the enterprise domain, our method leverages on synthetic data generation. Specifically, we employ an LLM to synthesize realistic enterprise queries from a seed document, apply BM25 to retrieve hard negatives, and use a teacher LLM to assign relevance scores. The resulting dataset is then distilled into an SLM, producing a compact relevance labeler. We evaluate our approach on a high-quality benchmark consisting of 923 enterprise query-document pairs annotated by trained human annotators, and show that the distilled SLM achieves agreement with human judgments on par with or better than the teacher LLM. Furthermore, our fine-tuned labeler substantially improves throughput, achieving 17 times increase while also being 19 times more cost-effective. This approach enables scalable and cost-effective relevance labeling for enterprise-scale retrieval applications, supporting rapid offline evaluation and iteration in real-world settings.

cs.IR↗

arXiv2025

LLM-Centric RAG with Multi-Granular Indexing and Confidence Constraints

This paper addresses the issues of insufficient coverage, unstable results, and limited reliability in retrieval-augmented generation under complex knowledge environments, and proposes a confidence control method that integrates multi-granularity memory indexing with uncertainty estimation. The method builds a hierarchical memory structure that divides knowledge representations into different levels of granularity, enabling dynamic indexing and retrieval from local details to global context, and thus establishing closer semantic connections between retrieval and generation. On this basis, an uncertainty estimation mechanism is introduced to explicitly constrain and filter low-confidence paths during the generation process, allowing the model to maintain information coverage while effectively suppressing noise and false content. The overall optimization objective consists of generation loss, entropy constraints, and variance regularization, forming a unified confidence control framework. In the experiments, comprehensive sensitivity tests and comparative analyses were designed, covering hyperparameters, environmental conditions, and data structures, to verify the stability and robustness of the proposed method across different scenarios. The results show that the method achieves superior performance over existing models in QA accuracy, retrieval recall, ranking quality, and factual consistency, demonstrating the effectiveness of combining multi-granularity indexing with confidence control. This study not only provides a new technical pathway for retrieval-augmented generation but also offers practical evidence for improving the reliability and controllability of large models in complex contexts.

cs.CL↗

arXiv2025

High-Fidelity Synthetic ECG Generation via Mel-Spectrogram Informed Diffusion Training

The development of machine learning for cardiac care is severely hampered by privacy restrictions on sharing real patient electrocardiogram (ECG) data. Although generative AI offers a promising solution, the real-world use of existing model-synthesized ECGs is limited by persistent gaps in trustworthiness and clinical utility. In this work, we address two major shortcomings of current generative ECG methods: insufficient morphological fidelity and the inability to generate personalized, patient-specific physiological signals. To address these gaps, we build on a conditional diffusion-based Structured State Space Model (SSSD-ECG) with two principled innovations: (1) MIDT-ECG (Mel-Spectrogram Informed Diffusion Training), a novel training paradigm with time-frequency domain supervision to enforce physiological structural realism, and (2) multi-modal demographic conditioning to enable patient-specific synthesis. We comprehensively evaluate our approach on the PTB-XL dataset, assessing the synthesized ECG signals on fidelity, clinical coherence, privacy preservation, and downstream task utility. MIDT-ECG achieves substantial gains: it improves morphological coherence, preserves strong privacy guarantees with all metrics evaluated exceeding the baseline by 4-8%, and notably reduces the interlead correlation error by an average of 74%, while demographic conditioning enhances signal-to-noise ratio and personalization. In critical low-data regimes, a classifier trained on datasets supplemented with our synthetic ECGs achieves performance comparable to a classifier trained solely on real data. Together, we demonstrate that ECG synthesizers, trained with the proposed time-frequency structural regularization scheme, can serve as personalized, high-fidelity, privacy-preserving surrogates when real data are scarce, advancing the responsible use of generative AI in healthcare.

cs.LG↗

arXiv2025

Lipschitz Bandits with Stochastic Delayed Feedback

The Lipschitz bandit problem extends stochastic bandits to a continuous action set defined over a metric space, where the expected reward function satisfies a Lipschitz condition. In this work, we introduce a new problem of Lipschitz bandit in the presence of stochastic delayed feedback, where the rewards are not observed immediately but after a random delay. We consider both bounded and unbounded stochastic delays, and design algorithms that attain sublinear regret guarantees in each setting. For bounded delays, we propose a delay-aware zooming algorithm that retains the optimal performance of the delay-free setting up to an additional term that scales with the maximal delay $\tau_{\max}$. For unbounded delays, we propose a novel phased learning strategy that accumulates reliable feedback over carefully scheduled intervals, and establish a regret lower bound showing that our method is nearly optimal up to logarithmic factors. Finally, we present experimental results to demonstrate the efficiency of our algorithms under various delay scenarios.

cs.LG↗

arXiv2025

One Head, Many Models: Cross-Attention Routing for Cost-Aware LLM Selection

The proliferation of large language models (LLMs) with varying computational costs and performance profiles presents a critical challenge for scalable, cost-effective deployment in real-world applications. We introduce a unified routing framework that leverages a single-head cross-attention mechanism to jointly model query and model embeddings, enabling dynamic selection of the optimal LLM for each input query. Our approach is evaluated on RouterBench, a large-scale, publicly available benchmark encompassing diverse LLM pools and domains. By explicitly capturing fine-grained query-model interactions, our router predicts both response quality and generation cost, achieving up to 6.6% improvement in Average Improvement in Quality (AIQ) and 2.9% in maximum performance over existing routers. To robustly balance performance and cost, we propose an exponential reward function that enhances stability across user preferences. The resulting architecture is lightweight, generalizes effectively across domains, and demonstrates improved efficiency compared to prior methods, establishing a new standard for cost-aware LLM routing.

cs.LG↗

arXiv2025

Dynamic Prompt Fusion for Multi-Task and Cross-Domain Adaptation in LLMs

This study addresses the generalization limitations commonly observed in large language models under multi-task and cross-domain settings. Unlike prior methods such as SPoT, which depends on fixed prompt templates, our study introduces a unified multi-task learning framework with dynamic prompt scheduling mechanism. By introducing a prompt pool and a task-aware scheduling strategy, the method dynamically combines and aligns prompts for different tasks. This enhances the model's ability to capture semantic differences across tasks. During prompt fusion, the model uses task embeddings and a gating mechanism to finely control the prompt signals. This ensures alignment between prompt content and task-specific demands. At the same time, it builds flexible sharing pathways across tasks. In addition, the proposed optimization objective centers on joint multi-task learning. It incorporates an automatic learning strategy for scheduling weights, which effectively mitigates task interference and negative transfer. To evaluate the effectiveness of the method, a series of sensitivity experiments were conducted. These experiments examined the impact of prompt temperature parameters and task number variation. The results confirm the advantages of the proposed mechanism in maintaining model stability and enhancing transferability. Experimental findings show that the prompt scheduling method significantly improves performance on a range of language understanding and knowledge reasoning tasks. These results fully demonstrate its applicability and effectiveness in unified multi-task modeling and cross-domain adaptation.

cs.CL↗

arXiv2025

Topology-Aware Graph Reinforcement Learning for Dynamic Routing in Cloud Networks

This paper proposes a topology-aware graph reinforcement learning approach to address the routing policy optimization problem in cloud server environments. The method builds a unified framework for state representation and structural evolution by integrating a Structure-Aware State Encoding (SASE) module and a Policy-Adaptive Graph Update (PAGU) mechanism. It aims to tackle the challenges of decision instability and insufficient structural awareness under dynamic topologies. The SASE module models node states through multi-layer graph convolution and structural positional embeddings, capturing high-order dependencies in the communication topology and enhancing the expressiveness of state representations. The PAGU module adjusts the graph structure based on policy behavior shifts and reward feedback, enabling adaptive structural updates in dynamic environments. Experiments are conducted on the real-world GEANT topology dataset, where the model is systematically evaluated against several representative baselines in terms of throughput, latency control, and link balance. Additional experiments, including hyperparameter sensitivity, graph sparsity perturbation, and node feature dimensionality variation, further explore the impact of structure modeling and graph updates on model stability and decision quality. Results show that the proposed method outperforms existing graph reinforcement learning models across multiple performance metrics, achieving efficient and robust routing in dynamic and complex cloud networks.

cs.LG↗

arXiv2025

Generalized Low-Rank Matrix Contextual Bandits with Graph Information

The matrix contextual bandit (CB), as an extension of the well-known multi-armed bandit, is a powerful framework that has been widely applied in sequential decision-making scenarios involving low-rank structure. In many real-world scenarios, such as online advertising and recommender systems, additional graph information often exists beyond the low-rank structure, that is, the similar relationships among users/items can be naturally captured through the connectivity among nodes in the corresponding graphs. However, existing matrix CB methods fail to explore such graph information, and thereby making them difficult to generate effective decision-making policies. To fill in this void, we propose in this paper a novel matrix CB algorithmic framework that builds upon the classical upper confidence bound (UCB) framework. This new framework can effectively integrate both the low-rank structure and graph information in a unified manner. Specifically, it involves first solving a joint nuclear norm and matrix Laplacian regularization problem, followed by the implementation of a graph-based generalized linear version of the UCB algorithm. Rigorous theoretical analysis demonstrates that our procedure outperforms several popular alternatives in terms of cumulative regret bound, owing to the effective utilization of graph information. A series of synthetic and real-world data experiments are conducted to further illustrate the merits of our procedure.

cs.LG↗

arXiv2025

Aptamer-protein interaction prediction model based on transformer

Aptamers are single-stranded DNA/RNAs or short peptides with unique tertiary structures that selectively bind to specific targets. They have great potential in the detection and medical fields. Here, we present SelfTrans-Ensemble, a deep learning model that integrates sequence information models and structural information models to extract multi-scale features for predicting aptamer-protein interactions (APIs). The model employs two pre-trained models, ProtBert and RNA-FM, to encode protein and aptamer sequences, along with features generated from primary sequence and secondary structural information. To address the data imbalance in the aptamer dataset imbalance, we incorporated short RNA-protein interaction data in the training set. This resulted in a training accuracy of 98.9% and a test accuracy of 88.0%, demonstrating the model's effectiveness in accurately predicting APIs. Additionally, analysis using molecular simulation indicated that SelfTrans-Ensemble is sensitive to aptamer sequence mutations. We anticipate that SelfTrans-Ensemble can offer a more efficient and rapid process for aptamer screening.

q-bio.BM↗

arXiv2025

Single Index Bandits: Generalized Linear Contextual Bandits with Unknown Reward Functions

Generalized linear bandits have been extensively studied due to their broad applicability in real-world online decision-making problems. However, these methods typically assume that the expected reward function is known to the users, an assumption that is often unrealistic in practice. Misspecification of this link function can lead to the failure of all existing algorithms. In this work, we address this critical limitation by introducing a new problem of generalized linear bandits with unknown reward functions, also known as single index bandits. We first consider the case where the unknown reward function is monotonically increasing, and propose two novel and efficient algorithms, STOR and ESTOR, that achieve decent regrets under standard assumptions. Notably, our ESTOR can obtain the nearly optimal regret bound $\tilde{O}_T(\sqrt{T})$ in terms of the time horizon $T$. We then extend our methods to the high-dimensional sparse setting and show that the same regret rate can be attained with the sparsity index. Next, we introduce GSTOR, an algorithm that is agnostic to general reward functions, and establish regret bounds under a Gaussian design assumption. Finally, we validate the efficiency and effectiveness of our algorithms through experiments on both synthetic and real-world datasets.

stat.ML↗

arXiv2025

Quantum Lipschitz Bandits

The Lipschitz bandit is a key variant of stochastic bandit problems where the expected reward function satisfies a Lipschitz condition with respect to an arm metric space. With its wide-ranging practical applications, various Lipschitz bandit algorithms have been developed, achieving the cumulative regret lower bound of order $\tilde O(T^{(d_z+1)/(d_z+2)})$ over time horizon $T$. Motivated by recent advancements in quantum computing and the demonstrated success of quantum Monte Carlo in simpler bandit settings, we introduce the first quantum Lipschitz bandit algorithms to address the challenges of continuous action spaces and non-linear reward functions. Specifically, we first leverage the elimination-based framework to propose an efficient quantum Lipschitz bandit algorithm named Q-LAE. Next, we present novel modifications to the classical Zooming algorithm, which results in a simple quantum Lipschitz bandit method, Q-Zooming. Both algorithms exploit the computational power of quantum methods to achieve an improved regret bound of $\tilde O(T^{d_z/(d_z+1)})$. Comprehensive experiments further validate our improved theoretical findings, demonstrating superior empirical performance compared to existing Lipschitz bandit methods.

cs.LG↗

arXiv2024

Biased Dueling Bandits with Stochastic Delayed Feedback

The dueling bandit problem, an essential variation of the traditional multi-armed bandit problem, has become significantly prominent recently due to its broad applications in online advertising, recommendation systems, information retrieval, and more. However, in many real-world applications, the feedback for actions is often subject to unavoidable delays and is not immediately available to the agent. This partially observable issue poses a significant challenge to existing dueling bandit literature, as it significantly affects how quickly and accurately the agent can update their policy on the fly. In this paper, we introduce and examine the biased dueling bandit problem with stochastic delayed feedback, revealing that this new practical problem will delve into a more realistic and intriguing scenario involving a preference bias between the selections. We present two algorithms designed to handle situations involving delay. Our first algorithm, requiring complete delay distribution information, achieves the optimal regret bound for the dueling bandit problem when there is no delay. The second algorithm is tailored for situations where the distribution is unknown, but only the expected value of delay is available. We provide a comprehensive regret analysis for the two proposed algorithms and then evaluate their empirical performance on both synthetic and real datasets.

cs.LG↗

arXiv2024

Low-rank Matrix Bandits with Heavy-tailed Rewards

In stochastic low-rank matrix bandit, the expected reward of an arm is equal to the inner product between its feature matrix and some unknown $d_1$ by $d_2$ low-rank parameter matrix $Θ^*$ with rank $r \ll d_1\wedge d_2$. While all prior studies assume the payoffs are mixed with sub-Gaussian noises, in this work we loosen this strict assumption and consider the new problem of \underline{low}-rank matrix bandit with \underline{h}eavy-\underline{t}ailed \underline{r}ewards (LowHTR), where the rewards only have finite $(1+δ)$ moment for some $δ\in (0,1]$. By utilizing the truncation on observed payoffs and the dynamic exploration, we propose a novel algorithm called LOTUS attaining the regret bound of order $\tilde O(d^\frac{3}{2}r^\frac{1}{2}T^\frac{1}{1+δ}/\tilde{D}_{rr})$ without knowing $T$, which matches the state-of-the-art regret bound under sub-Gaussian noises~\citep{lu2021low,kang2022efficient} with $δ= 1$. Moreover, we establish a lower bound of the order $Ω(d^\fracδ{1+δ} r^\fracδ{1+δ} T^\frac{1}{1+δ}) = Ω(T^\frac{1}{1+δ})$ for LowHTR, which indicates our LOTUS is nearly optimal in the order of $T$. In addition, we improve LOTUS so that it does not require knowledge of the rank $r$ with $\tilde O(dr^\frac{3}{2}T^\frac{1+δ}{1+2δ})$ regret bound, and it is efficient under the high-dimensional scenario. We also conduct simulations to demonstrate the practical superiority of our algorithm.

stat.ML↗

arXiv2024

Online Continuous Hyperparameter Optimization for Generalized Linear Contextual Bandits

In stochastic contextual bandits, an agent sequentially makes actions from a time-dependent action set based on past experience to minimize the cumulative regret. Like many other machine learning algorithms, the performance of bandits heavily depends on the values of hyperparameters, and theoretically derived parameter values may lead to unsatisfactory results in practice. Moreover, it is infeasible to use offline tuning methods like cross-validation to choose hyperparameters under the bandit environment, as the decisions should be made in real-time. To address this challenge, we propose the first online continuous hyperparameter tuning framework for contextual bandits to learn the optimal parameter configuration in practice within a search space on the fly. Specifically, we use a double-layer bandit framework named CDT (Continuous Dynamic Tuning) and formulate the hyperparameter optimization as a non-stationary continuum-armed bandit, where each arm represents a combination of hyperparameters, and the corresponding reward is the algorithmic result. For the top layer, we propose the Zooming TS algorithm that utilizes Thompson Sampling (TS) for exploration and a restart technique to get around the \textit{switching} environment. The proposed CDT framework can be easily utilized to tune contextual bandit algorithms without any pre-specified candidate set for multiple hyperparameters. We further show that it could achieve a sublinear regret in theory and performs consistently better than all existing methods on both synthetic and real datasets.

cs.LG↗

arXiv2024

Try with Simpler -- An Evaluation of Improved Principal Component Analysis in Log-based Anomaly Detection

The rapid growth of deep learning (DL) has spurred interest in enhancing log-based anomaly detection. This approach aims to extract meaning from log events (log message templates) and develop advanced DL models for anomaly detection. However, these DL methods face challenges like heavy reliance on training data, labels, and computational resources due to model complexity. In contrast, traditional machine learning and data mining techniques are less data-dependent and more efficient but less effective than DL. To make log-based anomaly detection more practical, the goal is to enhance traditional techniques to match DL's effectiveness. Previous research in a different domain (linking questions on Stack Overflow) suggests that optimized traditional techniques can rival state-of-the-art DL methods. Drawing inspiration from this concept, we conducted an empirical study. We optimized the unsupervised PCA (Principal Component Analysis), a traditional technique, by incorporating lightweight semantic-based log representation. This addresses the issue of unseen log events in training data, enhancing log representation. Our study compared seven log-based anomaly detection methods, including four DL-based, two traditional, and the optimized PCA technique, using public and industrial datasets. Results indicate that the optimized unsupervised PCA technique achieves similar effectiveness to advanced supervised/semi-supervised DL methods while being more stable with limited training data and resource-efficient. This demonstrates the adaptability and strength of traditional techniques through small yet impactful adaptations.

cs.LG↗