arXiv subjects

Yiqing Xu

Publications and source records attributed to Yiqing Xu.

At least 19 recordsLinked to original sources

arXiv2026

APIVOT: Adaptive Planning with Interleaved Vision-Language Thoughts

Long-horizon robot planning requires jointly reasoning over semantic task structure and geometric feasibility. To successfully execute a task, a robot must decompose goals, select task-relevant objects, and sequence actions, while ensuring that plans satisfy spatial constraints such as limited free space and object collisions. In this work, we propose APIVOT, a VLM-based planner that adaptively interleaves language and visual thoughts for long-horizon planning. APIVOT learns to leverage language for semantic reasoning, while using visual thoughts as imagined future states for internal verification of geometric feasibility. On long-horizon kitchen tasks, APIVOT outperforms general-purpose VLMs and prior planning frameworks, achieving the largest gains in spatially constrained settings. We find that APIVOT learns meaningful modality selection behavior, demonstrating that adaptive interleaving of vision-language thoughts improves both planning success and reasoning efficiency.

cs.CV↗

arXiv2026

Spectral tailoring of Raman soliton generation via a dispersion-managed fibre Fabry-P\'erot resonator

Dissipative Raman solitons in passive Kerr resonators have emerged as a promising route to broadband coherent frequency comb generation. Yet, their centre frequency has so far been mostly fixed near the Raman gain peak (13~THz downshifted from the pump centre frequency in silica-based fibres), constraining spectral coverage and compatibility with standard optical amplifiers. This limitation arises because the frequency shift of Raman solitons that fulfills phase-matching and group-velocity-matching conditions has to fall within the Raman gain band, leaving little room for spectral tuning when using a single conventional optical fibre. Here, we demonstrate that dispersion management of the fibre Fabry-P\'erot resonator which allows us to directly shift the soliton centre frequency. By combining two fibres with complementary dispersion profiles, we tailor the resonator's average dispersion to satisfy the phase-matching conditions for soliton formation at a target frequency downshifted by 7.8~THz from a pulsed pump, which is well outside the conventional 13~THz Raman gain band. This allows us to optically amplify the dissipative Raman soliton with a commercial L-band erbium-doped fibre amplifier, and fully characterise its temporal profile via the frequency-resolved optical gating technique.

physics.optics↗

arXiv2026

Interpretable Discriminative Text Representations via Agreement and Label Disentanglement

Interpretable text representations should expose coordinates that are not only predictive, but also meaningful enough for independent auditors to apply. Existing discriminative representations often use anonymous embedding directions, while concept-bottleneck and LLM-assisted methods attach natural-language names to features without ensuring that those definitions are reproducible or distinct from the target label. We propose an operational criterion for interpretable discriminative text representations: each coordinate should satisfy conceptual clarity, measured by chance-adjusted agreement between independent annotators applying the feature definition, and label disentanglement, meaning the feature should not merely paraphrase the prediction target. We instantiate this criterion in LLM-assisted Feature Discovery (LFD), an iterative method that proposes lexical and semantic features from contrastive outcome-opposed text pairs, screens candidates using cross-LLM Cohen's $\kappa$, and selects features by residual held-out predictive gain. A stylized analysis connects the $\kappa$ screen to a per-feature annotation-noise bound, formalizing agreement as a reliability check. Across ten text-classification tasks spanning seven corpora, LFD matches the predictive performance of a strong text bottleneck baseline while producing substantially clearer and less label-entangled features. Human audits with 232 raters show that LFD features achieve higher human--human and human--LLM agreement than baseline concepts, and raters consistently judge them as less label-leaking. These results suggest that agreement-tested, label-disentangled coordinates provide a practical auditability standard for interpretable text classification.

cs.CL↗

arXiv2026

The Harmonic Synthetic Control Method

Synthetic control methods can produce misleading counterfactual predictions when outcome series contain unit-specific stochastic trends, a common feature of nonstationary macroeconomic data. Existing remedies, such as pre-filtering or differencing, reduce spurious matching but may discard shared nonstationary variation that helps estimate donor weights. We propose Harmonic Synthetic Control (HSC), which replaces this binary choice with a soft allocation mechanism. HSC jointly estimates donor weights and a treated-unit-specific smooth residual component, then extrapolates this component into post-treatment periods using a time-series forecaster. A tuning parameter, selected by rolling-origin cross-validation, governs the division between donor matching and forecasting. As it varies, HSC continuously interpolates between synthetic control applied to differenced outcomes and synthetic control applied to raw outcomes with an intercept or trend. We provide a spectral interpretation showing how HSC downweights low-frequency residual components in donor matching and assigns them to the forecasting branch. A prediction-error decomposition separates weight-estimation distortion from residual-forecasting error. Monte Carlo exercises show that HSC adapts across regimes, performing well when stochastic trends are predominantly common or idiosyncratic, while estimators fixed to one regime can fail in the other.

econ.EM↗

arXiv2026

Learning Preferences from Conjoint Data: A Hybrid Structural Deep Learning Approach

Conjoint experiments randomize multidimensional profiles, yet political science applications typically report only nonparametric averages that do not recover counterfactual choices or individual tradeoffs. We develop a hybrid structural approach for recovering individual preferences from conjoint data. The estimator combines a flexible machine-learning mean preference function, via a deep netural network in our applications, with respondent-level empirical-Bayes updating in a logistic random utility model, allowing preferences to vary with observed characteristics while learning residual heterogeneity from repeated choices. Double/debiased machine learning delivers valid inference for population-average preference parameters with any sufficiently accurate first-stage learner. Across three applications, the method reveals heterogeneity reduced-form averages obscure: opposition to undemocratic behavior is broad but uneven in intensity, progressive tax preferences are widespread across partisan subgroups, and partisan polarization offsets the average gender effect in candidate choice. The framework opens the door to core theoretical questions in political science by recovering substantively interpretable structural parameters.

stat.ME↗

arXiv2026

StatsClaw: An AI-Collaborative Workflow for Statistical Software Development

Translating statistical methods into reliable software is a persistent bottleneck in quantitative research. Existing AI code-generation tools produce code quickly but cannot guarantee faithful implementation -- a critical requirement for statistical software. We introduce StatsClaw, a multi-agent architecture for Claude Code that enforces information barriers between code generation and validation. A planning agent produces independent specifications for implementation, simulation, and testing, dispatching them to separate agents that cannot see each other's instructions: the builder implements without knowing the ground-truth parameters, the simulator generates data without knowing the algorithm, and the tester validates using deterministic criteria. We describe the approach, demonstrate it end-to-end on a probit estimation package, and evaluate it across three applications to the authors' own R and Python packages. The results show that structured AI-assisted workflows can absorb the engineering overhead of the software lifecycle while preserving researcher control over every substantive methodological decision.

cs.SE↗

arXiv2026

Scaling Reproducibility: An AI-Assisted Workflow for Large-Scale Replication and Reanalysis

Computational reproducibility is central to scientific credibility, yet verifying published results at scale remains costly. We develop an AI-assisted workflow for automated full-paper replication -- retrieving materials, reconstructing environments, executing code, and matching outputs to point estimates reported in regression tables. We define a universe of all empirical and quantitative papers from the three top political science journals (2010--2025) and measure stated data availability using automated extraction. For a stratified sample of 384 studies, we apply the workflow to conduct full-paper replication, totaling 3,523 empirical models. We find that journal verification requirements, combined with data archiving mandates, drive reproducibility: the share of fully or largely reproducible papers rises from 20.8% before DA-RT adoption to 82.5% after, and conditional on accessible replication packages, 92.1% of papers are fully or largely reproducible (234/254). As a secondary application, we apply standardized IV diagnostics to 84 studies (597 IV specifications among 1,910 replicated models), illustrating how automated execution enables systematic reanalysis across heterogeneous empirical settings.

econ.EM↗

arXiv2026

VLS: Steering Pretrained Robot Policies via Vision-Language Models

Why do pretrained diffusion or flow-matching policies fail when the same task is performed near an obstacle, on a shifted support surface, or amid mild clutter? Such failures rarely reflect missing motor skills; instead, they expose a limitation of imitation learning under train-test shifts, where action generation is tightly coupled to training-specific spatial configurations and task specifications. Retraining or fine-tuning to address these failures is costly and conceptually misaligned, as the required behaviors already exist but cannot be selectively adapted at test time. We propose Vision-Language Steering (VLS), a training-free framework for inference-time adaptation of frozen generative robot policies. VLS treats adaptation as an inference-time control problem, steering the sampling process of a pretrained diffusion or flow-matching policy in response to out-of-distribution observation-language inputs without modifying policy parameters. By leveraging vision-language models to synthesize trajectory-differentiable reward functions, VLS guides denoising toward action trajectories that satisfy test-time spatial and task requirements. Across simulation and real-world evaluations, VLS consistently outperforms prior steering methods, achieving a 31% improvement on CALVIN and a 13% gain on LIBERO-PRO. Real-world deployment on a Franka robot further demonstrates robust inference-time adaptation under test-time spatial and semantic shifts. Project page: https://vision-language-steering.github.io/webpage/

cs.RO↗

arXiv2025

Multi-peak vector soliton families in defocusing Kerr resonators

We report the existence of multi-peaked vector soliton families in normally dispersive passive Kerr resonators. Through cross-phase modulation between two orthogonal polarization components, each peak becomes tightly interlocked, enabling robust localization of the entire wave packet in defocusing cavities. Analysis using snakes-and-ladder diagrams demonstrates the diversity of these vector soliton families, which include dark-bright multi-peak solitons, flat-topped solitons, and modulation instability patterns, among others. Furthermore, stability analysis based on the coupled Lugiato-Lefever equations reveals that specific combinations of parameters can sustain stable vector cavity solitons, whose peak numbers can be continuously tuned by adding appropriate perturbations. These findings significantly expand the scope of soliton dynamics and optical frequency comb generation in pumped-dissipative systems, independent of dispersion conditions.

physics.optics↗

arXiv2025

The Credibility Revolution in Political Science

How far has the credibility revolution spread through political science? We address this question by classifying 91,632 articles published between 2003 and 2023 across 156 political science journals using large language models, focusing on research design, credibility-enhancing practices, and citation patterns. We find that design-based studies, those leveraging plausibly exogenous variation to justify causal claims, have become increasingly common. In contrast, model-based approaches that rely more heavily on modeling assumptions have declined. Yet the rise of design-based work is uneven: it is concentrated in top journals and among authors at highly ranked institutions, and it is driven primarily by the growth of survey experiments. Other credibility-enhancing practices that help reduce false positives and false negatives, such as placebo tests and power calculations, remain rare. Taken together, our findings point to substantial but selective change, more consistent with a partial reform than a revolution.

cs.DL↗

arXiv2025

MRASfM: Multi-Camera Reconstruction and Aggregation through Structure-from-Motion in Driving Scenes

Structure from Motion (SfM) estimates camera poses and reconstructs point clouds, forming a foundation for various tasks. However, applying SfM to driving scenes captured by multi-camera systems presents significant difficulties, including unreliable pose estimation, excessive outliers in road surface reconstruction, and low reconstruction efficiency. To address these limitations, we propose a Multi-camera Reconstruction and Aggregation Structure-from-Motion (MRASfM) framework specifically designed for driving scenes. MRASfM enhances the reliability of camera pose estimation by leveraging the fixed spatial relationships within the multi-camera system during the registration process. To improve the quality of road surface reconstruction, our framework employs a plane model to effectively remove erroneous points from the triangulated road surface. Moreover, treating the multi-camera set as a single unit in Bundle Adjustment (BA) helps reduce optimization variables to boost efficiency. In addition, MRASfM achieves multi-scene aggregation through scene association and assembly modules in a coarse-to-fine fashion. We deployed multi-camera systems on actual vehicles to validate the generalizability of MRASfM across various scenes and its robustness in challenging conditions through real-world applications. Furthermore, large-scale validation results on public datasets show the state-of-the-art performance of MRASfM, achieving 0.124 absolute pose error on the nuScenes dataset.

cs.CV↗

arXiv2025

"Set It Up": Functional Object Arrangement with Compositional Generative Models (Journal Version)

Functional object arrangement (FORM) is the task of arranging objects to fulfill a function, e.g., "set up a dining table for two". One key challenge here is that the instructions for FORM are often under-specified and do not explicitly specify the desired object goal poses. This paper presents SetItUp, a neuro-symbolic framework that learns to specify the goal poses of objects from a few training examples and a structured natural-language task specification. SetItUp uses a grounding graph, which is composed of abstract spatial relations among objects (e.g., left-of), as its intermediate representation. This decomposes the FORM problem into two stages: (i) predicting this graph among objects and (ii) predicting object poses given the grounding graph. For (i), SetItUp leverages large language models (LLMs) to induce Python programs from a task specification and a few training examples. This program can be executed to generate grounding graphs in novel scenarios. For (ii), SetItUp pre-trains a collection of diffusion models to capture primitive spatial relations and online composes these models to predict object poses based on the grounding graph. We evaluated SetItUp on a dataset spanning three distinct task families: arranging tableware on a dining table, organizing items on a bookshelf, and laying out furniture in a bedroom. Experiments show that SetItUp outperforms existing models in generating functional, physically feasible, and aesthetically pleasing object arrangements. This article extends our conference paper published at Robotics: Science and Systems (RSS) 2024.

cs.RO↗

arXiv2025

"Stack It Up!": 3D Stable Structure Generation from 2D Hand-drawn Sketch

Imagine a child sketching the Eiffel Tower and asking a robot to bring it to life. Today's robot manipulation systems can't act on such sketches directly-they require precise 3D block poses as goals, which in turn demand structural analysis and expert tools like CAD. We present StackItUp, a system that enables non-experts to specify complex 3D structures using only 2D front-view hand-drawn sketches. StackItUp introduces an abstract relation graph to bridge the gap between rough sketches and accurate 3D block arrangements, capturing the symbolic geometric relations (e.g., left-of) and stability patterns (e.g., two-pillar-bridge) while discarding noisy metric details from sketches. It then grounds this graph to 3D poses using compositional diffusion models and iteratively updates it by predicting hidden internal and rear supports-critical for stability but absent from the sketch. Evaluated on sketches of iconic landmarks and modern house designs, StackItUp consistently produces stable, multilevel 3D structures and outperforms all baselines in both stability and visual resemblance.

cs.AI↗

arXiv2025

User Location Disclosure Fails to Deter Overseas Criticism but Amplifies Regional Divisions on Chinese Social Media

We examine the behavioral impact of a user location disclosure policy on Sina Weibo, China's largest microblogging platform, using a unique high-frequency dataset of uncensored engagement, including tens of thousands of comments and replies, on prominent government and media accounts. The policy, publicly justified as a measure to curb misinformation and counter foreign influence, was abruptly rolled out on April 28, 2022. Using an interrupted time series design, we find no decline in participation by overseas users. Instead, it significantly reduced domestic engagement with local issues outside users' home provinces, particularly among critical comments. Evidence indicates this decline was not driven by generalized fear or concerns about credibility, but by a surge in regionally discriminatory replies that raised the social cost of cross-provincial engagement. Our findings suggest that identity disclosure tools can have unintended consequences by activating existing social divisions in ways that reinforce state control without direct censorship.

econ.GN↗

arXiv2025

Soliton self-excitation under pulsed driving in a Kerr resonator

We present a novel regime of cavity soliton excitation in a Kerr resonator driven by a train of desynchronised pulses. In this regime, the soliton solution is shown to be the sole available state for the intracavity field, allowing for the automatic excitation of single solitons without the application of any external perturbations or parameter ramping. The self-excitation of cavity soliton frequency combs is validated through numerical continuation of the Lugiato-Lefever equation, direct numerical integration, and experimental observation. We show that this regime of CS self-excitation requires only the cavity detuning and pump desynchronisation parameters to be set within the correct range, thus considerably simplifying the usually complex task of deterministic cavity soliton excitation. Additionally, we show that this procedure can also be extended to allow the deterministic generation of different families of multi-soliton bound-states. We believe this research offers a promising approach to considerably simplify cavity soliton generation in both macro- and micro- scale Kerr resonators, while also offering greatly increased thermal, power, and nonlinear efficiencies intrinsic to pulsed-driven systems.

physics.optics↗

arXiv2025

Comparing Experimental and Nonexperimental Methods: What Lessons Have We Learned Four Decades After LaLonde (1986)?

In 1986, Robert LaLonde published an article comparing nonexperimental estimates to experimental benchmarks (LaLonde 1986). He concluded that the nonexperimental methods at the time could not systematically replicate experimental benchmarks, casting doubt on their credibility. Following LaLonde's critical assessment, there have been significant methodological advances and practical changes, including (i) an emphasis on the unconfoundedness assumption separated from functional form considerations, (ii) a focus on the importance of overlap in covariate distributions, (iii) the introduction of propensity score-based methods leading to doubly robust estimators, (iv) methods for estimating and exploiting treatment effect heterogeneity, and (v) a greater emphasis on validation exercises to bolster research credibility. To demonstrate the practical lessons from these advances, we reexamine the LaLonde data. We show that modern methods, when applied in contexts with sufficient covariate overlap, yield robust estimates for the adjusted differences between the treatment and control groups. However, this does not imply that these estimates are causally interpretable. To assess their credibility, validation exercises (such as placebo tests) are essential, whereas goodness-of-fit tests alone are inadequate. Our findings highlight the importance of closely examining the assignment process, carefully inspecting overlap, and conducting validation exercises when analyzing causal effects with nonexperimental data.

econ.EM↗

arXiv2025

"Set It Up!": Functional Object Arrangement with Compositional Generative Models

This paper studies the challenge of developing robots capable of understanding under-specified instructions for creating functional object arrangements, such as "set up a dining table for two"; previous arrangement approaches have focused on much more explicit instructions, such as "put object A on the table." We introduce a framework, SetItUp, for learning to interpret under-specified instructions. SetItUp takes a small number of training examples and a human-crafted program sketch to uncover arrangement rules for specific scene types. By leveraging an intermediate graph-like representation of abstract spatial relationships among objects, SetItUp decomposes the arrangement problem into two subproblems: i) learning the arrangement patterns from limited data and ii) grounding these abstract relationships into object poses. SetItUp leverages large language models (LLMs) to propose the abstract spatial relationships among objects in novel scenes as the constraints to be satisfied; then, it composes a library of diffusion models associated with these abstract relationships to find object poses that satisfy the constraints. We validate our framework on a dataset comprising study desks, dining tables, and coffee tables, with the results showing superior performance in generating physically plausible, functional, and aesthetically pleasing object arrangements compared to existing models.

cs.RO↗

arXiv2025

MovSAM: A Single-image Moving Object Segmentation Framework Based on Deep Thinking

Moving object segmentation plays a vital role in understanding dynamic visual environments. While existing methods rely on multi-frame image sequences to identify moving objects, single-image MOS is critical for applications like motion intention prediction and handling camera frame drops. However, segmenting moving objects from a single image remains challenging for existing methods due to the absence of temporal cues. To address this gap, we propose MovSAM, the first framework for single-image moving object segmentation. MovSAM leverages a Multimodal Large Language Model (MLLM) enhanced with Chain-of-Thought (CoT) prompting to search the moving object and generate text prompts based on deep thinking for segmentation. These prompts are cross-fused with visual features from the Segment Anything Model (SAM) and a Vision-Language Model (VLM), enabling logic-driven moving object segmentation. The segmentation results then undergo a deep thinking refinement loop, allowing MovSAM to iteratively improve its understanding of the scene context and inter-object relationships with logical reasoning. This innovative approach enables MovSAM to segment moving objects in single images by considering scene understanding. We implement MovSAM in the real world to validate its practical application and effectiveness for autonomous driving scenarios where the multi-frame methods fail. Furthermore, despite the inherent advantage of multi-frame methods in utilizing temporal information, MovSAM achieves state-of-the-art performance across public MOS benchmarks, reaching 92.5\% on J\&F. Our implementation will be available at https://github.com/IRMVLab/MovSAM.

cs.CV↗