Source author record

Qiwei Li

Qiwei Li appears in the imported research catalog. Authorship, coauthor and topic links are available while profile ownership is still unclaimed.

ResearcherUnclaimed source record

Artificial Intelligence Applications Computer Vision Databases Methodology Multiagent Systems Robotics

Catalog footprint

What is connected

4works

7topics

4close collaborators

Actions

Connect this record

Open graph Browse works

Inspect adjacent papers, topics, institutions and collaborators without losing the researcher page.

Building this map preview

BZPEER is loading the nearby papers, people, topics and institutions for this page.

preprint2026arXiv

TraceFix: Repairing Agent Coordination Protocols with TLA+ Counterexamples

We present TraceFix, a verification-first pipeline for Large Language Model (LLM) multi-agent coordination. An agent synthesizes a protocol topology as a structured intermediate representation (IR) from a task description, generates PlusCal coordination logic, and iteratively repairs the protocol using counterexamples from the TLA+ model checker (TLC) until verification succeeds. Verified process bodies are compiled into per-agent system prompts and executed under a runtime monitor that rejects out-of-topology coordination operations. On 48 tasks spanning 16 scenario families, all tasks reach full TLC verification; 62.5% pass on the first attempt and none requires more than four repair iterations. State spaces span six orders of magnitude yet verification completes in under 60 s for every task. A 3,456-run runtime comparison shows that topology-monitored execution achieves the highest task completion (89.4% average, 81.5% full) and that runtimes using the verified protocol degrade at roughly half the rate of prompt-only and chat-only baselines when model capability is reduced. A paired ablation under a fixed runtime shows that TLC-verified protocols cut deadlock/livelock (DL/LL) from 31.1% to 14.1%, with the largest separation under fault injection.

preprint2026arXiv

Unified 4D World Action Modeling from Video Priors with Asynchronous Denoising

We propose X-WAM, a Unified 4D World Model that unifies real-time robotic action execution and high-fidelity 4D world synthesis (video + 3D reconstruction) in a single framework, addressing the critical limitations of prior unified world models (e.g., UWM) that only model 2D pixel-space and fail to balance action efficiency and world modeling quality. To leverage the strong visual priors of pretrained video diffusion models, X-WAM imagines the future world by predicting multi-view RGB-D videos, and obtains spatial information efficiently through a lightweight structural adaptation: replicating the final few blocks of the pretrained Diffusion Transformer into a dedicated depth prediction branch for the reconstruction of future spatial information. Moreover, we propose Asynchronous Noise Sampling (ANS) to jointly optimize generation quality and action decoding efficiency. ANS applies a specialized asynchronous denoising schedule during inference, which rapidly decodes actions with fewer steps to enable efficient real-time execution, while dedicating the full sequence of steps to generate high-fidelity video. Rather than entirely decoupling the timesteps during training, ANS samples from their joint distribution to align with the inference distribution. Pretrained on over 5,800 hours of robotic data, X-WAM achieves 79.2% and 90.7% average success rate on RoboCasa and RoboTwin 2.0 benchmarks, while producing high-fidelity 4D reconstruction and generation surpassing existing methods in both visual and geometric metrics.

preprint2015arXiv

Oracally Efficient Estimation of Functional-Coefficient Autoregressive Models

Nonlinear autoregressive models are very useful for modeling many natural processes, however, the size of the class of these models is large. Functional-coefficient autoregressive models (FCAR) are useful structures for reducing the size of the class of these models. Although this structure reduces the class of nonlinear models, it is broad enough to include some common time series models as specific cases. A recent development in estimating nonlinear time series data is the spline backfitted kernel (SBK) method. This method combines the computational speed of splines with the asymptotic properties of kernel smoothing. To estimate a component function in the model, all other component functions are pre-estimated with splines and then the difference is taken of the observed time series and the pre-estimates. This difference is then used as pseudo-responses for which kernel smoothing is used to estimate the function of interest. By constructing the estimates in this way, the method does not suffer from the curse of dimensionality. In this paper, we adapt the SBK method to FCAR models.

preprint2011arXiv

Enabling Multi-level Trust in Privacy Preserving Data Mining

Privacy Preserving Data Mining (PPDM) addresses the problem of developing accurate models about aggregated data without access to precise information in individual data record. A widely studied \emph{perturbation-based PPDM} approach introduces random perturbation to individual values to preserve privacy before data is published. Previous solutions of this approach are limited in their tacit assumption of single-level trust on data miners. In this work, we relax this assumption and expand the scope of perturbation-based PPDM to Multi-Level Trust (MLT-PPDM). In our setting, the more trusted a data miner is, the less perturbed copy of the data it can access. Under this setting, a malicious data miner may have access to differently perturbed copies of the same data through various means, and may combine these diverse copies to jointly infer additional information about the original data that the data owner does not intend to release. Preventing such \emph{diversity attacks} is the key challenge of providing MLT-PPDM services. We address this challenge by properly correlating perturbation across copies at different trust levels. We prove that our solution is robust against diversity attacks with respect to our privacy goal. That is, for data miners who have access to an arbitrary collection of the perturbed copies, our solution prevent them from jointly reconstructing the original data more accurately than the best effort using any individual copy in the collection. Our solution allows a data owner to generate perturbed copies of its data for arbitrary trust levels on-demand. This feature offers data owners maximum flexibility.

Institution

Affiliation not imported yet

This author record came from a source that does not expose affiliation metadata. Once the author claims the profile or we enrich the record from another provider, this section will link to the concrete institution.

Topic footprint