arXiv subjects

Xianwei Li

Publications and source records attributed to Xianwei Li.

4 recordsLinked to original sources

arXiv2026

DexSim2Real: Foundation Model-Guided Sim-to-Real Transfer for Generalizable Dexterous Manipulation

Sim-to-real transfer remains a critical bottleneck for deploying dexterous manipulation policies learned in simulation to real-world robots. Existing approaches rely on manually designed domain randomization or task-specific adaptation, limiting their generalizability across diverse manipulation scenarios. We present DexSim2Real, an integrated framework that leverages vision-language foundation models to bridge the sim-to-real gap for dexterous manipulation. Our system combines three components: (1) Foundation Model-Guided Domain Randomization (FM-DR), which uses a vision-language model as a visual realism critic to optimize simulation parameters via closed-loop CMA-ES, complementing text-based approaches like DrEureka with direct visual feedback; (2) a Tactile-Visual Cross-Attention Policy (TVCAP) that adapts cross-attention visuo-tactile fusion to zero-shot sim-to-real RL; and (3) a Progressive Skill Curriculum (PSC) that builds on LLM-based task decomposition with a difficulty scheduler tailored to contact-rich dexterous tasks. Extensive experiments on six challenging manipulation tasks with blinded evaluation demonstrate that DexSim2Real achieves a 78.2% average real-world success rate, outperforming DrEureka and DeXtreme while reducing the sim-to-real performance gap to only 8.3%.

cs.RO↗

arXiv2026

HELM: Harness-Enhanced Long-horizon Memory for Vision-Language-Action Manipulation

Vision-Language-Action (VLA) models fail systematically on long-horizon manipulation tasks despite strong short-horizon performance. We show that this failure is not resolved by extending context length alone in the current reactive execution setting; instead, it stems from three recurring execution-loop deficiencies: the memory gap, the verification gap, and the recovery gap. We present HELM, a model-agnostic framework that addresses these deficiencies with three components: an Episodic Memory Module (EMM) that retrieves key task history via CLIP-indexed keyframes, a learned State Verifier (SV) that predicts action failure before execution from observation, action, subgoal, and memory-conditioned context, and a Harness Controller (HC) that performs rollback and replanning. The SV is the core learning contribution: it consistently outperforms rule-based feasibility checks and ensemble uncertainty baselines, and its effectiveness depends critically on access to episodic memory. On LIBERO-LONG, HELM improves task success rate by 23.1 percentage points over OpenVLA (58.4% to 81.5%), while extending the context window to H=32 yields only a 5.4-point gain and same-budget LoRA adaptation remains 12.2 points below HELM. HELM also improves long-horizon performance on CALVIN and substantially boosts recovery success under controlled perturbations. Ablations and mechanism analyses isolate the contribution of each component, and we release LIBERO-Recovery as a perturbation-injection protocol for evaluating failure recovery in long-horizon manipulation.

cs.LG↗

arXiv2026

Distributed Observers with Dynamic Event-Triggered Communication

This paper studies the problem of distributed state estimation of linear time-invariant (LTI) systems under event-triggered communication. For event-triggering mechanisms, the existence of positive minimum inter-event times (MIETs) is an essential property for ensuring practicality. It is widely recognized that dynamic event-triggering mechanisms can effectively reduce redundant communication. However, for distributed observers, it remains unclear whether dynamic event-triggering mechanisms can ensure positive MIETs. This paper proposes a dynamic event-triggered distributed observer. By introducing new comparison functions, it is proven that the dynamic event-triggered distributed observer can guarantee strictly positive MIETs and ensure the exponential convergence of the estimation error. Moreover, most existing works on event-triggered distributed observers only consider node-based event-triggering mechanisms, while both node-based and edge-based dynamic event-triggering mechanisms are constructed in this paper. Numerical examples are provided to illustrate the effectiveness of the proposed results.

eess.SY↗

arXiv2020

On the Stability of the Endemic Equilibrium of A Discrete-Time Networked Epidemic Model

Networked epidemic models have been widely adopted to describe propagation phenomena. The endemic equilibrium of these models is of great significance in the field of viral marketing, innovation dissemination, and information diffusion. However, its stability conditions have not been fully explored. In this paper we study the stability of the endemic equilibrium of a networked Susceptible-Infected-Susceptible (SIS) epidemic model with heterogeneous transition rates in a discrete-time manner. We show that the endemic equilibrium, if it exists, is asymptotically stable for any nontrivial initial condition. Under mild assumptions on initial conditions, we further prove that during the spreading process there exists no overshoot with respect to the endemic equilibrium. Finally, we conduct numerical experiments on real-world networks to demonstrate our results.

eess.SY↗