arXiv subjects

Di Weng

Publications and source records attributed to Di Weng.

At least 19 recordsLinked to original sources

arXiv2026

BIRD-History: A Benchmark for History-Driven Text-to-SQL with Fine-Grained Knowledge Annotations

While recent Large Language Model (LLM)-based text-to-SQL systems achieve impressive performance on standard benchmarks, they struggle when user queries implicitly rely on domain-specific knowledge, such as business logic, data conventions, and analytical practices, that is neither captured by the schema nor explicitly stated in the natural language question. Historical SQL query logs offer a valuable source of such knowledge, yet existing benchmarks do not adequately support evaluation of history-driven approaches. To address this gap, we introduce BIRD-History, a benchmark consisting of 1,393 tasks across 11 databases, designed to evaluate text-to-SQL systems' ability to ground underspecified natural language questions using historical SQL scripts. Each task is annotated with ground-truth labels specifying which historical queries contain relevant knowledge and which SQL clauses encode it, enabling systematic evaluation of both retrieval effectiveness and knowledge utilization. Alongside the benchmark, we propose a plug-in retriever that extracts five types of external knowledge from historical SQL scripts, then retrieves and reranks relevant fragments for query generation. The retriever integrates seamlessly into existing few-shot text-to-SQL pipelines without requiring prompt modifications. Experiments demonstrate consistent improvements across four text-to-SQL systems, highlighting the value of leveraging historical query logs for handling underspecified queries. Dataset and code are open-sourced on https://github.com/zjuidg/BIRD-History.

cs.AI↗

arXiv2026

AdaLens: Interactive Storyline for Monitoring and Steering Long-Running Agentic Data Analysis

Large language models are pushing data science toward increasingly autonomous and agentic workflows, with recent systems already supporting multi-step and long-running analyses. As these workflows become more autonomous, conventional interfaces no longer provide adequate support for two critical requirements: observability for understanding an agent's evolving reasoning and evidence, and steerability for redirecting low-value directions or deepening promising ones during execution. Existing interactive approaches improve process visibility and open intervention points, but they remain largely designed for discrete, turn-by-turn exchanges rather than the parallel branches and evolving decision structures of long-running agentic analysis. We study this need as interactive oversight in long-running agentic data analysis and present AdaLens, an interactive system for monitoring and steering ongoing runs. AdaLens combines a storyline-based representation that unifies analytical plans, execution progress, intermediate findings, and data-column involvement with steering interactions grounded in these analytical elements for directional guidance and execution control. We evaluate AdaLens through two case studies and a user study, examining how it supports analysts in monitoring and steering long-running agentic data analysis.

cs.HC↗

arXiv2026

POEM: Phase-Aware $\mathrm{SO}(2)$ Feature Rotation for Time Series Forecasting Under Periodicity Drift

Deep learning has advanced time series forecasting, but periodicity drift, in which cycle timing and phase vary over time, remains a challenging problem. Existing methods predominantly model these sequences on fixed time grids, suffering from a limited ability to accommodate phase-related variation. To address this limitation, we propose \textbf{POEM}, a phase-aware forecasting framework based on latent feature rotation using the special orthogonal group in two dimensions, denoted by $\mathrm{SO}(2)$. POEM aims to reduce the phase-related variability by learning a phase-correction coordinate and applying an invertible $\mathrm{SO}(2)$-based rotation to paired latent features. To extrapolate this correction coordinate, Directional Phase Increment Attention (DPIA) retrieves historical phase increments from similar temporal contexts and integrates them into future phase corrections. Experiments demonstrate that POEM achieves competitive performance, while qualitative visualizations suggest that the learned phase-aware transformation makes latent trajectories more regular.

cs.LG↗

arXiv2026

MerchantBench: Benchmarking LLM Agents for Long-Term Coherence in E-Commerce Operations

Large language model agents are increasingly evaluated as autonomous tool users, yet most benchmarks focus on bounded tasks with immediate success criteria. Real-world deployments often require Long-Term Coherence, the capacity to preserve purposeful behavior across extended horizons while adapting decisions to accumulated evidence. Evaluating this capacity requires a persistent environment in which actions constrain future choices, feedback arrives at heterogeneous delays, and incoherent behavior produces measurable cumulative effects. Seller-side e-commerce provides a suitable setting for this evaluation through recurrent and interdependent decisions over Product Sourcing, Listing and Pricing Control, Cash-Flow Management, and Mixed-Latency Feedback Adaptation. We introduce MerchantBench, a 365-day order-level simulation grounded in 98,843 real e-commerce product records and equipped with 26 tools for agent interaction. MerchantBench couples promptly observable Upstream Supplier Events with delayed Downstream Order Outcomes, requiring agents to follow individual order lifecycles and revisit earlier decisions. We evaluate eight LLMs under two agent frameworks in 48 runs, each spanning 365 simulated days. Our results reveal a substantial gap between even the latest LLMs and human participants, with the best LLM configuration attaining only 27.3\% of the mean final net assets achieved by human participants.

cs.AI↗

arXiv2026

SKILL-KD: Contrastive Skill Distillation for LLM Agents

Skill-based prompting has become a practical mechanism for improving large language model (LLM) agents, yet existing skill acquisition methods often treat skills as experience summaries, memory entries, or direct summaries of successful demonstrations. This creates a mismatch for weaker student agents: when a student fails because it lacks task knowledge or operational strategy, its failed trajectory may not contain enough evidence to infer the missing behavior, while the teacher trajectory may be too implicit to be internalized as reusable guidance. We propose SKILL-KD, a contrastive skill distillation framework that treats skills as an explicit distillation medium between agents of different capabilities. Given a student failure and the teacher trajectory on the same task, SKILL-KD distills their actionable discrepancy into a textual skill patch, evaluates the patch by re-running the student, and iteratively refines the patch when the student still fails. To prevent repeated local updates from causing skill drift, SKILL-KD further maintains trace-linked edit histories and performs Drift-Aware Skill Consolidation, deciding whether each patch should add a new rule, delete or modify an existing rule, or be skipped. Across five agent benchmarks and two student settings, SKILL-KD consistently improves frozen student agents over fixed-model adaptation baselines.

cs.AI↗

arXiv2026

SPADER: Step-wise Peer Advantage with Diversity-Aware Exploration Rewards for Multi-Answer Question Answering

Large language models are increasingly deployed as tool-augmented agents to acquire information beyond parametric knowledge. While recent work has improved long-horizon tool-use reasoning, most approaches focus on tasks with a single correct answer. In contrast, many real-world queries require discovering a comprehensive set of valid answers, a setting known as Multi-Answer QA. This setting raises two challenges: fine-grained credit assignment over long search trajectories and reward alignment for sustained exploration beyond easy high-frequency entities. We propose SPADER, a reinforcement learning framework for long-horizon tool use in Multi-Answer QA. SPADER includes Step-wise Peer Advantage (SPA), a critic-free step-level credit assignment mechanism that aligns parallel trajectories by decision step and estimates advantages from peer returns. It also includes a diversity-aware exploration reward that promotes long-tail entity discovery by upweighting rare findings and downweighting redundant ones. Experiments on QAMPARI, Mintaka, WebQSP, and QUEST show that SPADER generally improves recall and overall F1 over prompting-based agents, outcome-supervised RL methods, and recent step-level supervision approaches. Our code and model weights are available at https://github.com/KhanCold/spader.

cs.CL↗

arXiv2026

Dynamic TMoE: A Drift-Aware Dynamic Mixture of Experts Framework for Non-Stationary Time Series Forecasting

Non-stationary time series forecasting is challenged by evolving distribution shifts that static models struggle to capture. While Mixture-of-Experts (MoE) architectures offer a promising paradigm for decoupling complex drift patterns, existing approaches are limited by fixed expert pools and memoryless routing, hampering their ability to adapt to abrupt regime shifts. To address this, we propose Dynamic TMoE, a framework that unifies architectural evolution with temporal continuity during learning phase. By detecting distribution shifts via Maximum Mean Discrepancy (MMD), we dynamically instantiate heterogeneous experts and prune redundant ones to optimize capacity. Additionally, a temporal memory router leverages recurrent states and an anomaly repository to ensure stable, context-aware expert selection without requiring test-time updates. Experiments on nine benchmarks demonstrate state-of-the-art performance, reducing MSE by 10.4% and MAE by 7.8%. Code is available at https://github.com/andone-07/Dynamic-TMoE.

cs.LG↗

arXiv2026

KEditVis: A Visual Analytics System for Knowledge Editing of Large Language Models

Large Language Models (LLMs) demonstrate exceptional capabilities in factual question answering, yet they sometimes provide incorrect responses. To address this issue, knowledge editing techniques have emerged as effective methods for correcting factual information in LLMs. However, typical knowledge editing workflows struggle with identifying the optimal set of model layers for editing and rely on summary indicators that provide insufficient guidance. This lack of transparency hinders effective comparison and identification of optimal editing strategies. In this paper, we present KEditVis, a novel visual analytics system designed to assist users in gaining a deeper understanding of knowledge editing through interactive visualizations, improving editing outcomes, and discovering valuable insights for the future development of knowledge editing algorithms. With KEditVis, users can select appropriate layers as the editing target, explore the reasons behind ineffective edits, and perform more targeted and effective edits. Our evaluation, including usage scenarios, expert interviews, and a user study, validates the effectiveness and usability of the system.

cs.HC↗

arXiv2026

Cerebra: Aligning Implicit Knowledge in Interactive SQL Authoring

LLM-driven tools have significantly lowered barriers to writing SQL queries. However, user instructions are often underspecified, assuming the model understands implicit knowledge, such as dataset schemas, domain conventions, and task-specific requirements, that isn't explicitly provided. This results in frequently erroneous scripts that require users to repeatedly clarify their intent. Additionally, users struggle to validate generated scripts because they cannot verify whether the model correctly applied implicit knowledge. We present Cerebra, an interactive NL-to-SQL tool that aligns implicit knowledge between users and LLMs during SQL authoring. Cerebra automatically retrieves implicit knowledge from historical SQL scripts based on user instructions, presents this knowledge in an interactive tree view for code review, and supports iterative refinement to improve generated scripts. To evaluate the effectiveness and usability of Cerebra, we conducted a user study with 16 participants, demonstrating its improved support for customized SQL authoring. The source code of Cerebra is available at https://github.com/zjuidg/CHI26-Cerebra.

cs.HC↗

arXiv2026

FEA-SLT: A Gloss-Free End-to-End Framework for Facial-Expression-Aware Sign Language Translation

Sign Language Translation (SLT) is a challenging cross-modal task requiring joint modeling of manual articulations and non-manual signals. Existing gloss-free SLT methods effectively capture gestural dynamics but often underutilize facial expressions, which play crucial grammatical and disambiguating roles. This limitation can cause semantic degradation when distinct concepts share similar manual configurations. To address this issue, we propose FEA-SLT (**F**acial-**E**xpression-**A**ware **S**ign **L**anguage **T**ranslation), a gloss-free end-to-end framework that uses facial dynamics to provide complementary cues to manual signals. FEA-SLT employs a domain-transferred facial encoder to extract expression-sensitive representations and integrates them with manual features through a linguistically motivated *Facial-Expression-Aware Fusion* (FEAF) module. FEAF captures reciprocal dependencies between manual and facial channels via bidirectional modulation, enhancing syntactic fidelity. Experiments on PHOENIX14T and CSL-Daily show that FEA-SLT achieves state-of-the-art BLEU performance among gloss-free methods, while targeted analyses support improved translation of facial-sensitive utterances. Code is available at https://github.com/TuGuobin/FEA-SLT.

cs.CV↗

arXiv2025

RULER-Bench: Probing Rule-based Reasoning Abilities of Next-level Video Generation Models for Vision Foundation Intelligence

Recent advances in video generation have enabled the synthesis of videos with strong temporal consistency and impressive visual quality, marking a crucial step toward vision foundation models. To evaluate these video generation models, existing benchmarks primarily focus on factors related to visual perception and understanding, like visual aesthetics, instruction adherence, and temporal coherence. However, the rule-based reasoning capabilities of video generation models remain largely unexplored. Although recent studies have carried out preliminary explorations into whether video models can serve as zero-shot learners, they still lack a fine-grained decomposition of reasoning capabilities and a comprehensive evaluation protocol. To address this gap, we introduce RULER-Bench, a benchmark designed to evaluate the reasoning ability of video generation models from the perspective of cognitive rules. Built upon two fundamental paradigms: text-to-video and image-to-video, RULER-Bench covers 40 representative tasks spanning six rule categories with 622 high-quality annotated instances. For the evaluation of each generated video, we construct a checklist covering four metrics and leverage GPT-o3 to assign scores to each question, achieving 85% alignment with human judgements. Extensive experiments show that the state-of-the-art model achieves only 48.87% on the rule coherence metric, highlighting significant room for improvement in the reasoning capability of next-level video models. We expect that the insight obtained from RULER-Bench will facilitate further development of reasoning-aware video generation, advancing video generation models toward vision foundation intelligence.

cs.CV↗

arXiv2025

ViseGPT: Towards Better Alignment of LLM-generated Data Wrangling Scripts and User Prompts

Large language models (LLMs) enable the rapid generation of data wrangling scripts based on natural language instructions, but these scripts may not fully adhere to user-specified requirements, necessitating careful inspection and iterative refinement. Existing approaches primarily assist users in understanding script logic and spotting potential issues themselves, rather than providing direct validation of correctness. To enhance debugging efficiency and optimize the user experience, we develop ViseGPT, a tool that automatically extracts constraints from user prompts to generate comprehensive test cases for verifying script reliability. The test results are then transformed into a tailored Gantt chart, allowing users to intuitively assess alignment with semantic requirements and iteratively refine their scripts. Our design decisions are informed by a formative study (N=8) that explores user practices and challenges. We further evaluate the effectiveness and usability of ViseGPT through a user study (N=18). Results indicate that ViseGPT significantly improves debugging efficiency for LLM-generated data-wrangling scripts, enhances users' ability to detect and correct issues, and streamlines the workflow experience.

cs.HC↗

arXiv2025

StructVizor: Interactive Profiling of Semi-Structured Textual Data

Data profiling plays a critical role in understanding the structure of complex datasets and supporting numerous downstream tasks, such as social media analytics and financial fraud detection. While existing research predominantly focuses on structured data formats, a substantial portion of semi-structured textual data still requires ad-hoc and arduous manual profiling to extract and comprehend its internal structures. In this work, we propose StructVizor, an interactive profiling system that facilitates sensemaking and transformation of semi-structured textual data. Our tool mainly addresses two challenges: a) extracting and visualizing the diverse structural patterns within data, such as how information is organized or related, and b) enabling users to efficiently perform various wrangling operations on textual data. Through automatic data parsing and structure mining, StructVizor enables visual analytics of structural patterns, while incorporating novel interactions to enable profile-based data wrangling. A comparative user study involving 12 participants demonstrates the system's usability and its effectiveness in supporting exploratory data analysis and transformation tasks.

cs.HC↗

arXiv2025

Xavier: Toward Better Coding Assistance in Authoring Tabular Data Wrangling Scripts

Data analysts frequently employ code completion tools in writing custom scripts to tackle complex tabular data wrangling tasks. However, existing tools do not sufficiently link the data contexts such as schemas and values with the code being edited. This not only leads to poor code suggestions, but also frequent interruptions in coding processes as users need additional code to locate and understand relevant data. We introduce Xavier, a tool designed to enhance data wrangling script authoring in computational notebooks. Xavier maintains users' awareness of data contexts while providing data-aware code suggestions. It automatically highlights the most relevant data based on the user's code, integrates both code and data contexts for more accurate suggestions, and instantly previews data transformation results for easy verification. To evaluate the effectiveness and usability of Xavier, we conducted a user study with 16 data analysts, showing its potential to streamline data wrangling scripts authoring.

cs.HC↗

arXiv2024

RCInvestigator: Towards Better Investigation of Anomaly Root Causes in Cloud Computing Systems

Finding the root causes of anomalies in cloud computing systems quickly is crucial to ensure availability and efficiency since accurate root causes can guide engineers to take appropriate actions to address the anomalies and maintain customer satisfaction. However, it is difficult to investigate and identify the root causes based on large-scale and high-dimension monitoring data collected from complex cloud computing environments. Due to the inherently dynamic characteristics of cloud computing systems, the existing approaches in practice largely rely on manual analyses for flexibility and reliability, but massive unpredictable factors and high data complexity make the process time-consuming. Despite recent advances in automated detection and investigation approaches, the speed and quality of root cause analyses remain limited by the lack of expert involvement in these approaches. The limitations found in the current solutions motivate us to propose a visual analytics approach that facilitates the interactive investigation of the anomaly root causes in cloud computing systems. We identified three challenges, namely, a) modeling databases for the root cause investigation, b) inferring root causes from large-scale time series, and c) building comprehensible investigation results. In collaboration with domain experts, we addressed these challenges with RCInvestigator, a novel visual analytics system that establishes a tight collaboration between human and machine and assists experts in investigating the root causes of cloud computing system anomalies. We evaluated the effectiveness of RCInvestigator through two use cases based on real-world data and received positive feedback from experts.

cs.HC↗

arXiv2024

Relation-driven Query of Multiple Time Series

Querying time series based on their relations is a crucial part of multiple time series analysis. By retrieving and understanding time series relations, analysts can easily detect anomalies and validate hypotheses in complex time series datasets. However, current relation extraction approaches, including knowledge- and data-driven ones, tend to be laborious and do not support heterogeneous relations. By conducting a formative study with 11 experts, we concluded 6 time series relations, including correlation, causality, similarity, lag, arithmetic, and meta, and summarized three pain points in querying time series involving these relations. We proposed RelaQ, an interactive system that supports the time series query via relation specifications. RelaQ allows users to intuitively specify heterogeneous relations when querying multiple time series, understand the query results based on a scalable, multi-level visualization, and explore possible relations beyond the existing queries. RelaQ is evaluated with two use cases and a user study with 12 participants, showing promising effectiveness and usability.

cs.HC↗

arXiv2023

NeighViz: Towards Better Understanding of Neighborhood Effects on Social Groups with Spatial Data

Understanding how local environments influence individual behaviors, such as voting patterns or suicidal tendencies, is crucial in social science to reveal and reduce spatial disparities and promote social well-being. With the increasing availability of large-scale individual-level census data, new analytical opportunities arise for social scientists to explore human behaviors (e.g., political engagement) among social groups at a fine-grained level. However, traditional statistical methods mostly focus on global, aggregated spatial correlations, which are limited to understanding and comparing the impact of local environments (e.g., neighborhoods) on human behaviors among social groups. In this study, we introduce a new analytical framework for analyzing multi-variate neighborhood effects between social groups. We then propose NeighVi, an interactive visual analytics system that helps social scientists explore, understand, and verify the influence of neighborhood effects on human behaviors. Finally, we use a case study to illustrate the effectiveness and usability of our system.

cs.HC↗

arXiv2023

GeoCamera: Telling Stories in Geographic Visualizations with Camera Movements

In geographic data videos, camera movements are frequently used and combined to present information from multiple perspectives. However, creating and editing camera movements requires significant time and professional skills. This work aims to lower the barrier of crafting diverse camera movements for geographic data videos. First, we analyze a corpus of 66 geographic data videos and derive a design space of camera movements with a dimension for geospatial targets and one for narrative purposes. Based on the design space, we propose a set of adaptive camera shots and further develop an interactive tool called GeoCamera. This interactive tool allows users to flexibly design camera movements for geographic visualizations. We verify the expressiveness of our tool through case studies and evaluate its usability with a user study. The participants find that the tool facilitates the design of camera movements.

cs.HC↗