arXiv subjects

Yin Lin

Publications and source records attributed to Yin Lin.

At least 19 recordsLinked to original sources

arXiv2026

Context as an Environment: Programmatic Context Management for Long-Horizon Agents

LLM agents increasingly take on long-running tasks whose history grows far beyond a single model context window. Existing approaches compress earlier interactions or extract selected information into fixed memory representations, committing to what to preserve before future needs are known. We present Scroll, a context manager that treats each agent session as an executable Session Environment. The environment is backed by an append-only Event Log and a sandboxed, persistent Python kernel. The kernel maintains a typed namespace across model calls, allowing tool outputs, retrieved history, and derived state to be bound to variables rather than serialized into the prompt at each call. Model-written code searches, materializes, and transforms session state through exec; only explicitly printed projections enter the model's working view for the next call. Context management thus becomes a programming task that inherits the improving coding abilities of LLMs, while the Event Log preserves lossless historical ground truth. As the working view approaches its budget, stale spans are evicted but remain recoverable: an eviction index keeps compact landmarks tied to exact Event Log addresses, so that the agent navigates directly to evicted regions instead of searching the full log. With Qwen3.8-Max as the backbone, Scroll achieves 94.8% on LongMemEval_S; 73.1% on BEAM_10M, surpassing the best published memory system by 5.1 points; and 86.7% on LOCA_256K, exceeding the best published long-horizon agent by 37.4 points.

cs.AI↗

arXiv2026

A Scalable AI-Powered System for Explainable Machine Learning Pipelines in Brain Tumor

Artificial intelligence and radiomics are increasingly used in brain tumor research, yet their translation into clinical practice remains limited by fragmented workflows, poor transparency, and weak integration with end users' needs. We present the first version of a scalable web-based visual analytics system designed to support radiomics-driven machine learning inference in neuro-oncology. The platform integrates three core functions within a single interface: cohort management from structured clinical tables, radiomic feature extraction from medical images and segmentation masks, and guarded inference with pre-trained machine learning models. The system was developed through an iterative user-centred design process and evaluated on both a public glioblastoma dataset and a proprietary clinical cohort. A key contribution is the explicit exposure of intermediate workflow artifacts, which improves traceability, interpretability, and responsible use of AI. By combining portability, inspectability, and deployment simplicity, the proposed framework offers a practical foundation for clinically oriented AI applications in brain tumor analysis.

cs.SE↗

arXiv2026

Radiomics- and Clinical Feature-Driven Prediction of Volumetric Response in Skull-Base Meningioma after CyberKnife Radiosurgery

Skull-base meningiomas are often characterized by favorable long-term prognosis, yet their anatomical complexity and proximity to critical neurovascular structures make treatment selection challenging. Stereotactic radiosurgery with CyberKnife represents an effective therapeutic option when surgical resection is not feasible; however, not all patients benefit equally from this treatment. Early identification of patients likely to respond to radiosurgery remains an open clinical problem. In this study, we propose a radiomics- and clinical feature-driven framework for predicting volumetric response in skull-base meningiomas treated with CyberKnife. Unlike most existing approaches that focus on progression-free survival or recurrence, our method targets volumetric response as an indicator of treatment efficacy. Pre-treatment MRI images from 104 patients were processed to extract radiomic features, which were combined with clinical variables and analyzed using six models. To ensure methodological rigor, the entire modeling process was implemented within a nested cross-validation scheme. Among the evaluated models, TabPFN achieved the best overall performance, with an AUC of 0.81 and consistently favorable classification metrics. These results suggest that advanced machine learning architectures, when combined with robust validation strategies, can effectively capture patterns associated with treatment response even in small-sample, high-dimensional settings.

cs.CV↗

arXiv2026

Touchless Intraoperative Image Access System Based on Vision-Based Hand Tracking

Touchless interaction with medical images is becoming increasingly important in the surgical field, where sterility and continuity of the operational workflow are essential requirements. This work presents a vision-based system for intraoperative navigation of medical images through hand gestures acquired using a single RGB camera. Unlike many existing solutions, the system does not require additional hardware or user-specific training. Hand tracking is performed in real time using MediaPipe Hands, which provides a 2.5D estimation of hand landmarks. Simple and intuitive gestures are then mapped into translation, rotation, and zoom commands, enabling continuous and natural interaction with the image viewer. The system architecture is independent from the visualization software and, for implementation simplicity, in this study it was integrated with PyVista. Performance was evaluated through frame-level logging and quantitative analysis of latency, stability, and interaction robustness metrics. Experimental results highlight real-time behavior, with reduced latencies and stable control, in line with the requirements of fluid interaction. The system demonstrates the feasibility of a low-cost touchless solution for intraoperative access to medical images, laying the groundwork for future clinical evaluations.

cs.CV↗

arXiv2026

SEMA-SQL: Beyond Traditional Relational Querying with Large Language Models

Relational databases excel at structured data analysis, but real-world queries increasingly require capabilities beyond standard SQL, such as semantically matching entities across inconsistent names, extracting information not explicitly stored in schemas, and analyzing unstructured text. While text-to-SQL systems enable natural language querying, they remain limited to relational operations and cannot leverage the semantic reasoning capabilities of modern large language models (LLMs). Conversely, recent semantic operator systems extend relational algebra with LLM-powered operations (e.g., semantic joins, mappings, aggregations), but require users to manually construct complex query pipelines. To address this gap, we present SEMA-SQL, a system that automatically answers natural language questions by generating efficient queries that combine relational operations with LLM semantic reasoning. We formalize Hybrid Relational Algebra (HRA), a declarative abstraction unifying traditional relational operators with LLM user-defined functions (UDFs). The system automates three critical aspects: (1) query generation via in-context learning that produces HRA queries with precise natural language specifications for LLM UDFs, (2) query optimization via cost-based transformations and UDF rewriting, and (3) efficient execution algorithms that reduce LLM invocations by an average of 93% in semantic joins through intelligent batching. Extensive experiments with known benchmarks, and extensions thereof, demonstrate the significant query capability improvements possible with our design.

cs.DB↗

arXiv2026

Large Language Model-Enhanced Relational Operators: Taxonomy, Benchmark, and Analysis

With the development of large language models (LLMs), numerous studies integrate LLMs through operator-like components to enhance relational data processing tasks, e.g., filters with semantic predicates, knowledge-augmented table imputation, reasoning-driven entity matching and more challenging semantic query processing. These components invoke LLMs while preserving a relational input/output interface, which we refer to as LLM-Enhanced Relational Operators (LROs). From an operator perspective, unfortunately, these existing LROs suffer from fragmented definition, various implementation strategies and inadequate evaluation benchmarks. To this end, in this paper, we first establish a unified LRO taxonomy to align existing LROs, and categorize them into: Select, Match, Impute, Cluster and Order, along with their operands and implementation variants. Second, we design LROBench, a comprehensive benchmark featuring 290 single-LRO queries and 60 multi-LRO queries, spanning 27 databases across more than 10 domains. LROBench covers all operating logics and operand granularities in its single-LRO workload, and provides challenging multi-LRO queries stratified by query complexity. Based on these, we evaluate individual LROs under various implementations, deriving practical insights into LRO design choices and summarizing our empirical best practices. We further compare the end-to-end performance of existing multi-LRO systems against an LRO suite instantiated with these best practices, in order to investigate how to design an effective LRO set for multi-LRO systems targeting complex semantic queries. Last, to facilitate future work, we outline promising future directions and open-source all benchmark data and evaluation code, available at https://github.com/LROBench/LROBench/.

cs.DB↗

arXiv2025

High-Precision Scale Setting with the Omega-Baryon Mass and Gradient Flow

The gradient-flow scale $w_0$ in lattice QCD is determined using the mass of the $\Omega^-$ baryon to set the physical scale. Nine ensembles using the highly improved staggered quark (HISQ) action with lattice spacings of 0.15 fm down to 0.04 fm are used, seven of which have nearly physical light-quark masses. Electromagnetic corrections to the $\Omega^-$ mass are defined in order to compute a pure-QCD $\Omega$ mass. The final result is $w_0 = 0.17187(68)$ fm, corresponding to a relative uncertainty of 0.40% and a central value in good agreement with previous calculations in the literature.

hep-lat↗

arXiv2025

Matrix-free Neural Preconditioner for the Dirac Operator in Lattice Gauge Theory

Linear systems arise in generating samples and in calculating observables in lattice quantum chromodynamics~(QCD). Solving the Hermitian positive definite systems, which are sparse but ill-conditioned, involves using iterative methods, such as Conjugate Gradient (CG), which are time-consuming and computationally expensive. Preconditioners can effectively accelerate this process, with the state-of-the-art being multigrid preconditioners. However, constructing useful preconditioners can be challenging, adding additional computational overhead, especially in large linear systems. We propose a framework, leveraging operator learning techniques, to construct linear maps as effective preconditioners. The method in this work does \emph{not} rely on explicit matrices from either the original linear systems or the produced preconditioners, allowing efficient model training and application in the CG solver. In the context of the Schwinger model U(1) gauge theory in 1+1 spacetime dimensions with two degenerate-mass fermions), this preconditioning scheme effectively decreases the condition number of the linear systems and approximately halves the number of iterations required for convergence in relevant parameter ranges. We further demonstrate the framework learns a general mapping dependent on the lattice structure which leads to zero-shot learning ability for the Dirac operators constructed from gauge field configurations of different sizes.

hep-lat↗

arXiv2025

AmbiSQL: Interactive Ambiguity Detection and Resolution for Text-to-SQL

Text-to-SQL systems translate natural language questions into SQL queries, providing substantial value for non-expert users. While large language models (LLMs) show promising results for this task, they remain error-prone. Query ambiguity has been recognized as a major obstacle in LLM-based Text-to-SQL systems, leading to misinterpretation of user intent and inaccurate SQL generation. To this end, we present AmbiSQL, an interactive system that automatically detects query ambiguities and guides users through intuitive multiple-choice questions to clarify their intent. It introduces a fine-grained ambiguity taxonomy for identifying ambiguities arising from both database elements and LLM reasoning, and subsequently incorporates user feedback to rewrite ambiguous questions. In this demonstration, AmbiSQL is integrated with XiYan-SQL, our commercial Text-to-SQL backend. We provide 40 ambiguous queries collected from two real-world benchmarks that SIGMOD'26 attendees can use to explore how disambiguation improves SQL generation quality. Participants can also apply the system to their own databases and natural language questions. The codebase and demo video are available at: https://github.com/JustinzjDing/AmbiSQL and https://www.youtube.com/watch?v=rbB-0ZKwYkk.

cs.DB↗

arXiv2025

Glioblastoma Overall Survival Prediction With Vision Transformers

Glioblastoma is one of the most aggressive and common brain tumors, with a median survival of 10-15 months. Predicting Overall Survival (OS) is critical for personalizing treatment strategies and aligning clinical decisions with patient outcomes. In this study, we propose a novel Artificial Intelligence (AI) approach for OS prediction using Magnetic Resonance Imaging (MRI) images, exploiting Vision Transformers (ViTs) to extract hidden features directly from MRI images, eliminating the need of tumor segmentation. Unlike traditional approaches, our method simplifies the workflow and reduces computational resource requirements. The proposed model was evaluated on the BRATS dataset, reaching an accuracy of 62.5% on the test set, comparable to the top-performing methods. Additionally, it demonstrated balanced performance across precision, recall, and F1 score, overcoming the best model in these metrics. The dataset size limits the generalization of the ViT which typically requires larger datasets compared to convolutional neural networks. This limitation in generalization is observed across all the cited studies. This work highlights the applicability of ViTs for downsampled medical imaging tasks and establishes a foundation for OS prediction models that are computationally efficient and do not rely on segmentation.

cs.CV↗

arXiv2024

Efficient Row-Level Lineage Leveraging Predicate Pushdown

Row-level lineage explains what input rows produce an output row through a data processing pipeline, having many applications like data debugging, auditing, data integration, etc. Prior work on lineage falls in two lines: eager lineage tracking and lazy lineage inference. Eager tracking integrates lineage tracing tightly into the operator implementation, enabling efficient customized tracking. However, this approach is intrusive, system-specific, and lacks adaptability. In contrast, lazy inference generates additional queries to compute lineage; it can be easily applied to any database, but the lineage query is usually slow. Furthermore, both approaches have limited coverage of the type of data processing pipeline supported due to operator-specific tracking or inference rules. In this work, we propose PredTrace, a lineage inference approach that achieves easy adaptation, low runtime overhead, efficient lineage querying, and high pipeline coverage. It achieves this by leveraging predicate pushdown: pushing a row-selection predicate that describes the target output down to source tables and querying the lineage by running the pushed-down predicate. PredTrace may require saving intermediate results when running the pipeline in order to compute the precise lineage. When this is not viable, it can still infer lineage but may return a superset. Compared to prior work, PredTrace achieves higher coverage on TPC-H queries as well as 70 sampled real-world data processing pipelines in which UDFs are widely used. It can infer lineage in seconds, outperforming prior lazy approaches by up to 10x.

cs.DB↗

arXiv2024

Exploring gauge-fixing conditions with gradient-based optimization

Lattice gauge fixing is required to compute gauge-variant quantities, for example those used in RI-MOM renormalization schemes or as objects of comparison for model calculations. Recently, gauge-variant quantities have also been found to be more amenable to signal-to-noise optimization using contour deformations. These applications motivate systematic parameterization and exploration of gauge-fixing schemes. This work introduces a differentiable parameterization of gauge fixing which is broad enough to cover Landau gauge, Coulomb gauge, and maximal tree gauges. The adjoint state method allows gradient-based optimization to select gauge-fixing schemes that minimize an arbitrary target loss function.

hep-lat↗

arXiv2024

Cross-modulated Attention Transformer for RGBT Tracking

Existing Transformer-based RGBT trackers achieve remarkable performance benefits by leveraging self-attention to extract uni-modal features and cross-attention to enhance multi-modal feature interaction and template-search correlation computation. Nevertheless, the independent search-template correlation calculations ignore the consistency between branches, which can result in ambiguous and inappropriate correlation weights. It not only limits the intra-modal feature representation, but also harms the robustness of cross-attention for multi-modal feature interaction and search-template correlation computation. To address these issues, we propose a novel approach called Cross-modulated Attention Transformer (CAFormer), which performs intra-modality self-correlation, inter-modality feature interaction, and search-template correlation computation in a unified attention model, for RGBT tracking. In particular, we first independently generate correlation maps for each modality and feed them into the designed Correlation Modulated Enhancement module, modulating inaccurate correlation weights by seeking the consensus between modalities. Such kind of design unifies self-attention and cross-attention schemes, which not only alleviates inaccurate attention weight computation in self-attention but also eliminates redundant computation introduced by extra cross-attention scheme. In addition, we propose a collaborative token elimination strategy to further improve tracking inference efficiency and accuracy. Extensive experiments on five public RGBT tracking benchmarks show the outstanding performance of the proposed CAFormer against state-of-the-art methods.

cs.CV↗

arXiv2024

Update on the gradient flow scale on the 2+1+1 HISQ ensembles

We report on the ongoing effort of improving the determination of the gradient flow scale on the (2+1+1)-flavor HISQ ensembles generated by the MILC collaboration. We compute the scales $\sqrt{t_0}/a$ and $w_0/a$ with the Wilson and Symanzik flow using three discretizations for the action density: clover, Wilson and tree-level Symanzik improved. For the absolute scale setting, we intend to employ the $\Omega$-baryon mass, but are also using the pion decay constant while the $\Omega$-mass calculations are in progress.

hep-lat↗

arXiv2023

SequencePAR: Understanding Pedestrian Attributes via A Sequence Generation Paradigm

Current pedestrian attribute recognition (PAR) algorithms use multi-label or multi-task learning frameworks with specific classification heads. These models often struggle with imbalanced data and noisy samples. Inspired by the success of generative models, we propose Sequence Pedestrian Attribute Recognition (SequencePAR), a novel sequence generation paradigm for PAR. SequencePAR extracts pedestrian features using a language-image pre-trained model and embeds the attribute set into query tokens guided by text prompts. A Transformer decoder generates human attributes by integrating visual features and attribute query tokens. The masked multi-head attention layer in the decoder prevents the model from predicting the next attribute during training. The extensive experiments on multiple PAR datasets validate the effectiveness of SequencePAR. Specifically, we achieve 84.92\%, 90.44\%, 90.73\%, and 90.46\% in accuracy, precision, recall, and F1-score on the PETA dataset. The source code and pre-trained models are available at https://github.com/Event-AHU/OpenPAR.

cs.CV↗

arXiv2023

SMARTFEAT: Efficient Feature Construction through Feature-Level Foundation Model Interactions

Before applying data analytics or machine learning to a data set, a vital step is usually the construction of an informative set of features from the data. In this paper, we present SMARTFEAT, an efficient automated feature engineering tool to assist data users, even non-experts, in constructing useful features. Leveraging the power of Foundation Models (FMs), our approach enables the creation of new features from the data, based on contextual information and open-world knowledge. Our method incorporates an intelligent operator selector that discerns a subset of operators, effectively avoiding exhaustive combinations of original features, as is typically observed in traditional automated feature engineering tools. Moreover, we address the limitations of performing data tasks through row-level interactions with FMs, which could lead to significant delays and costs due to excessive API calls. We introduce a function generator that facilitates the acquisition of efficient data transformations, such as dataframe built-in methods or lambda functions, ensuring the applicability of SMARTFEAT to generate new features for large datasets. Code repo with prompt details and datasets: (https://github.com/niceIrene/SMARTFEAT).

cs.DB↗

arXiv2023

Signal-to-noise improvement through neural network contour deformations for 3D $SU(2)$ lattice gauge theory

Complex contour deformations of the path integral have been demonstrated to significantly improve the signal-to-noise ratio of observables in previous studies of two-dimensional gauge theories with open boundary conditions. In this work, new developments based on gauge fixing and a neural network definition of the deformation are introduced, which enable an effective application to theories in higher dimensions and with generic boundary conditions. Improvements of the signal-to-noise ratio by up to three orders of magnitude for Wilson loop measurements are shown in $SU(2)$ lattice gauge theory in three spacetime dimensions.

hep-lat↗

arXiv2023

Exploring Part-Informed Visual-Language Learning for Person Re-Identification

Recently, visual-language learning (VLL) has shown great potential in enhancing visual-based person re-identification (ReID). Existing VLL-based ReID methods typically focus on image-text feature alignment at the whole-body level, while neglecting supervision on fine-grained part features, thus lacking constraints for local feature semantic consistency. To this end, we propose Part-Informed Visual-language Learning ($\pi$-VL) to enhance fine-grained visual features with part-informed language supervisions for ReID tasks. Specifically, $\pi$-VL introduces a human parsing-guided prompt tuning strategy and a hierarchical visual-language alignment paradigm to ensure within-part feature semantic consistency. The former combines both identity labels and human parsing maps to constitute pixel-level text prompts, and the latter fuses multi-scale visual features with a light-weight auxiliary head to perform fine-grained image-text alignment. As a plug-and-play and inference-free solution, our $\pi$-VL achieves performance comparable to or better than state-of-the-art methods on four commonly used ReID benchmarks. Notably, it reports 91.0% Rank-1 and 76.9% mAP on the challenging MSMT17 database, without bells and whistles.

cs.CV↗