Selected work

Representative Papers

Solutions of Word Equations Over Partially Commutative Structures

Mar 09, 2016International Colloquium on Automata, Languages and Programming

This paper investigates the satisfiability and finiteness problems for systems of word equations with recognizable constraints over the free partially commutative monoid $M(A,I)$ and its quotient group $G(A,I)$. Methodologically, it characterizes solution sets as EDT0L languages and provides an explicit construction of these languages within NSPACE$(n log n)$. Building on this, a unified algorithm is devised that simultaneously decides both satisfiability and finiteness—each in NSPACE$(n log n)$. Notably, the long-standing finiteness problem, previously known to be PSPACE-complete, is resolved at the significantly lower complexity NSPACE$(n log n)$. Moreover, the solution sets are described in a tight, computable, and structurally explicit form. The approach integrates techniques from combinatorial group theory, EDT0L language theory, space-bounded computation, and partial commutation algebraic modeling.

23 citations2 influentialRead paper

Bridging Language and Action: A Survey of Language-Conditioned Robot Manipulation

Dec 17, 2023

This work addresses the semantic gap between natural language instructions and robotic physical actions to enhance the naturalness and reliability of human-robot collaboration. We propose the first four-dimensional taxonomy for language-conditioned robotic manipulation—comprising reward shaping, policy learning, neurosymbolic AI, and foundation model–driven approaches—and systematically analyze their fundamental limitations in generalization and safety. Integrating large language models (LLMs), vision-language models (VLMs), neurosymbolic reasoning, and multimodal semantic parsing, we develop a unified analytical framework spanning semantic extraction, environmental assessment, and auxiliary task design. Our analysis rigorously characterizes the performance boundaries of each paradigm for the first time, establishing theoretical foundations and concrete technical pathways toward safe, generalizable, and interpretable language-driven robotic systems.

10 citationsRead paper

End-to-end guarantees for indirect data-driven control of bilinear systems with finite stochastic data

Sep 26, 2024arXiv.org

This work addresses indirect data-driven control of bilinear systems under finite stochastic data, specifically ensuring end-to-end closed-loop stability in the presence of unbounded-support noise. The method introduces the first prior- and data-dependent finite-sample identification error ellipsoidal bound for bilinear systems, which is directly integrated into a robust controller synthesis framework. It synergistically combines statistical learning theory, ellipsoidal-set-based robust control, and Koopman operator approximation, and rigorously establishes exponential stability of the closed-loop system. Numerical experiments quantitatively characterize the trade-off between identification accuracy and control performance. Furthermore, the framework is extended to general nonlinear systems via Koopman-based data-driven control, substantially enhancing both theoretical guarantees and practical applicability under limited data.

5 citationsRead paper

The LSCD Benchmark: a Testbed for Diachronic Word Meaning Tasks

Mar 29, 2024arXiv.org

Lexical Semantic Change Detection (LSCD) has long suffered from severe heterogeneity in datasets, preprocessing pipelines, and evaluation metrics, impeding fair model comparison and reproducibility. Method: We introduce the first modular, plug-and-play standardized LSCD benchmark platform that unifies evaluation protocols across three hierarchical tasks—Word-in-Context (WiC), Word Sense Induction (WSI), and LSCD. Our approach innovatively models lexical usage evolution as a graph structure, integrating cross-temporal semantic clustering, sense induction, and context-aware word sense disambiguation. All components are open-sourced with full implementation transparency. Contribution/Results: The framework significantly improves evaluation consistency and reproducibility, enables independent assessment of subtasks and joint optimization, and has emerged as the de facto community standard for LSCD research.

3 citationsRead paper

A Convoy of Magnetic Millirobots Transports Endoscopic Instruments for Minimally-Invasive Surgery.

Jul 01, 2024Advancement of science

In minimally invasive surgery, microrobots suffer from insufficient traction on slippery, soft-tissue surfaces, hindering reliable transport of elongated instruments (e.g., endoscopes, catheters). To address this, we present TrainBot—a magnetically actuated millirobotic convoy system—where multiple millirobots cooperatively form a “train-like” configuration to enable stable, heavy-load instrument transport within narrow anatomical lumens (e.g., bile ducts, intestines). Key contributions include: (i) the first demonstration of millirobotic swarm-based cargo transport, achieving a twofold increase in output force; (ii) bioinspired, biocompatible microstructured feet that enhance individual propulsion force by threefold; and (iii) the world’s first millirobot-assisted electrodilatation procedure for biliary stricture relief. Integrated with wireless permanent-magnet actuation and multi-robot closed-loop control, TrainBot successfully validated biliary obstruction clearance, drainage tunnel creation, and targeted drug delivery in human-scale organ phantoms—significantly advancing precision instrument delivery in minimally invasive interventions.

2 citationsRead paper

Recent publications

Latest Papers

Distillation of Foundation Models for Time-dependent PDEs

Aug 12, 2026

While large foundation models demonstrate strong performance in solving time-dependent partial differential equations, their high computational cost limits their practicality as replacements for efficient numerical solvers. This work proposes the Teacher Rollout Extension (TREX) framework, which leverages knowledge distillation to transfer capabilities from a pretrained teacher model to a lightweight student model. By using long-horizon synthetic trajectories generated by the teacher to augment limited downstream data, TREX enables sampling of rollout trajectories without requiring prior knowledge of the initial condition distribution. This exposes the student model to both long-term dynamics and local recovery behaviors, while allowing integration of task-specific inductive biases—such as equivariance. Combined with noise injection and an equivariant network architecture, the resulting student model achieves several orders of magnitude fewer parameters, over tenfold faster inference, and accuracy comparable to or exceeding that of the teacher.

0 citationsRead paper

Clustered Randomized Smoothing for Stochastic Prediction Functions

Aug 12, 2026

This work addresses the challenge of mode collapse in randomized multimodal prediction, where conventional randomized smoothing fails to capture the true data distribution, thereby compromising robustness in safety-critical applications. The authors propose a clustered α-smoothing framework that first partitions noisy samples into clusters and then applies α-smoothing locally within each cluster, ultimately aggregating the results into a mixture distribution to preserve multimodal structure. This approach is the first to integrate clustering with local α-smoothing, effectively mitigating mode collapse through mixture-based modeling. The paper also provides a theoretical lower bound on the probability that predictions fall within multimodal regions. Empirical evaluations demonstrate significant improvements: a 27% reduction in Wasserstein distance for autonomous driving trajectory prediction and an 81% decrease in collision rates compared to existing methods in quadrotor control tasks.

0 citationsRead paper

Structuring the Space of Perspectives

Aug 12, 2026

This study addresses the conceptual ambiguity and unclear interrelationships among stance, sentiment, framing, and argumentation—key perspective-related constructs in natural language processing—that stem from the absence of a unified theoretical framework. Through a systematic literature review and conceptual analysis, the work proposes a set of distinguishing attributes and, for the first time, formulates a linear hierarchical model that clarifies the intrinsic logical relationships among these constructs. The resulting model offers a coherent theoretical foundation and a conceptual navigation tool for perspective research, enabling scholars to select appropriate operationalization pathways aligned with their specific task objectives. This advancement enhances the systematicity and effectiveness of research on linguistic perspectives.

0 citationsRead paper

FITTER: Vocabulary-Agnostic Cross-Domain Inference on Temporal Knowledge Graphs

Aug 11, 2026

Existing methods struggle to generalize to out-of-domain temporal knowledge graphs containing entirely new entities, relations, and timestamps. This work proposes the first vocabulary-agnostic, fully inductive structural model that enables cross-graph link prediction without retraining and exhibits temporal translation invariance. By leveraging interaction-pattern-based relation representations, relative temporal encoding, and a temporally aware message-passing mechanism, the model effectively captures dynamic relational structures across diverse temporal contexts. Evaluated on six benchmarks spanning varied domains, granularities, and temporal extents, the approach significantly outperforms current inductive baselines, demonstrating strong generalization capability and effectiveness in cross-domain temporal reasoning.

0 citationsRead paper

GESTO: Human-Centric Spatio-Temporal Memory for Reasoning in Dynamic Scenes

Aug 11, 2026

Existing 4D scene graphs struggle to model the structured temporal dynamics of human activities, and current activity representations either decouple from persistent 3D scenes or rely on predefined event boundaries and object associations. This work proposes a spatiotemporal memory system that integrates a persistent 4D scene graph with a dual-layer human–object interaction framework and a goal-driven hierarchical event structure to automatically extract, associate, and cluster atomic interactions from RGB-D streams into structured events. Through hierarchical event modeling and a context-aware object association refinement mechanism, the system enables retrospective and inferable activity memory. It achieves performance of 0.71–0.75 on standard benchmarks and scores 0.73 and 0.75 on newly introduced Space2Event and Event2Space query tasks, respectively, approaching the upper bound attainable with ground-truth events and associations.

0 citationsRead paper