Yiqing Xu

Yiqing Xu, Wei Gao, David Hsu

Inverse reinforcement learning (IRL) seeks to infer a cost function that explains the underlying goals and preferences of expert demonstrations. This paper presents receding horizon inverse reinforcement learning (RHIRL), a new IRL algorithm for high-dimensional, noisy, continuous systems with black-box dynamic models. RHIRL addresses two key challenges of IRL: scalability and robustness. To handle high-dimensional continuous systems, RHIRL matches the induced optimal trajectories with expert demonstrations locally in a receding horizon manner and 'stitches' together the local solutions to learn the cost; it thereby avoids the 'curse of dimensionality'. This contrasts sharply with earlier algorithms that match with expert demonstrations globally over the entire high-dimensional state space. To be robust against imperfect expert demonstrations and control noise, RHIRL learns a state-dependent cost function 'disentangled' from system dynamics under mild conditions. Experiments on benchmark tasks show that RHIRL outperforms several leading IRL algorithms in most instances. We also prove that the cumulative error of RHIRL grows linearly with the task duration.

Yiqing Xu, David Hsu

Tidying up a messy table may appear simple for humans, but articulating clear criteria for tidiness is challenging due to the ambiguous nature of common sense reasoning. Large Language Models (LLMs) have proven capable of capturing common sense knowledge to reason over this vague concept of tidiness. However, they alone may struggle with table tidying due to the limited grasp on the spatio-visual aspects of tidiness. In this work, we aim to ground the common-sense concept of tidiness within the context of object arrangement. Our survey reveals that humans usually factorize tidiness into semantic and visual-spatial tidiness; our grounding approach aligns with this decomposition. We connect a language-based policy generator with an image-based tidiness score function: the policy generator utilizes the LLM's commonsense knowledge to cluster objects by their implicit types and functionalities for semantic tidiness; meanwhile, the tidiness score function assesses the visual-spatial relations of the object to achieve visual-spatial tidiness. Our tidiness score is trained using synthetic data generated cheaply from customized random walks, which inherently encode the order of tidiness, thereby bypassing the need for labor-intensive human demonstrations. The simulated experiment shows that our approach successfully generates tidy arrangements, predominately in 2D, with potential for 3D stacking, for tables with various novel objects.

Yiqing Xu, Finale Doshi-Velez, David Hsu

Inverse reinforcement learning (IRL) algorithms often rely on (forward) reinforcement learning or planning, over a given time horizon, to compute an approximately optimal policy for a hypothesized reward function; they then match this policy with expert demonstrations. The time horizon plays a critical role in determining both the accuracy of reward estimates and the computational efficiency of IRL algorithms. Interestingly, an *effective time horizon* shorter than the ground-truth value often produces better results faster. This work formally analyzes this phenomenon and provides an explanation: the time horizon controls the complexity of an induced policy class and mitigates overfitting with limited data. This analysis provides a guide for the principled choice of the effective horizon for IRL. It also prompts us to re-examine the classic IRL formulation: it is more natural to learn jointly the reward and the effective horizon rather than the reward alone with a given horizon. To validate our findings, we implement a cross-validation extension and the experimental results support the theoretical analysis. The project page and code are publicly available.

Tong Wang, Yiqing Xu, Leo Yang Yang

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 $κ$, and selects features by residual held-out predictive gain. A stylized analysis connects the $κ$ 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.

Yuwei Zeng, Yiqing Xu

Learning reward functions for physical skills are challenging due to the vast spectrum of skills, the high-dimensionality of state and action space, and nuanced sensory feedback. The complexity of these tasks makes acquiring expert demonstration data both costly and time-consuming. Large Language Models (LLMs) contain valuable task-related knowledge that can aid in learning these reward functions. However, the direct application of LLMs for proposing reward functions has its limitations such as numerical instability and inability to incorporate the environment feedback. We aim to extract task knowledge from LLMs using environment feedback to create efficient reward functions for physical skills. Our approach consists of two components. We first use the LLM to propose features and parameterization of the reward function. Next, we update the parameters of this proposed reward function through an iterative self-alignment process. In particular, this process minimizes the ranking inconsistency between the LLM and our learned reward functions based on the new observations. We validated our method by testing it on three simulated physical skill learning tasks, demonstrating effective support for our design choices.

Chang Nie, Yiqing Xu, Guangming Wang et al.

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.

Yiqing Xu, Jiayuan Mao, Yilun Du et al.

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.

Connie Jiang, Yiqing Xu, David Hsu

The advantages of pre-trained large language models (LLMs) are apparent in a variety of language processing tasks. But can a language model's knowledge be further harnessed to effectively disambiguate objects and navigate decision-making challenges within the realm of robotics? Our study reveals the LLM's aptitude for solving complex decision making challenges that are often previously modeled by Partially Observable Markov Decision Processes (POMDPs). A pivotal focus of our research is the object disambiguation capability of LLMs. We detail the integration of an LLM into a tabletop environment disambiguation task, a decision making problem where the robot's task is to discern and retrieve a user's desired object from an arbitrarily large and complex cluster of objects. Despite multiple query attempts with zero-shot prompt engineering (details can be found in the Appendix), the LLM struggled to inquire about features not explicitly provided in the scene description. In response, we have developed a few-shot prompt engineering system to improve the LLM's ability to pose disambiguating queries. The result is a model capable of both using given features when they are available and inferring new relevant features when necessary, to successfully generate and navigate down a precise decision tree to the correct object--even when faced with identical options.

Tianzhu Qin, Yiqing Xu

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.

Shuo Liu, Ishneet Sukhvinder Singh, Yiqing Xu et al.

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/

Lingfeng Xuan, Chang Nie, Yiqing Xu et al.

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.

Yiqing Xu, Linfeng Li, Cunjun Yu et al.

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.

Hieu Le Trung, Yiqing Xu, Wee Sun Lee

Designing a network to learn a molecule structure given its physical/chemical properties is a hard problem, but is useful for drug discovery tasks. In this paper, we incorporate higher-order relational learning of Factor Graphs with strong approximation power of Neural Networks to create a molecule-structure learning network that has strong generalization power and can enforce higher-order relationship and valence constraints. We further propose methods to tackle problems such as the efficient design of factor nodes, conditional parameter sharing among factors, and symmetry problems in molecule structure prediction. Our experiment evaluation shows that the factor learning is effective and outperforms related methods.