arXiv subjects

Ming Ouyang

Publications and source records attributed to Ming Ouyang.

7 recordsLinked to original sources

arXiv2026

Dual-Stream LLM-Guided Reward Design for Reject-Inference-Aware Reinforcement Learning in E-Commerce Payment Fraud Detection

Production fraud-detection models learn from a censored slice of their own traffic: transactions a legacy system blocked never receive fraud labels, so models train on a biased, approved-only distribution. We extend LLM-guided reward design, the framework of Qu et al. (2025) in which an LLM evolves the reward of a two-step REINFORCE fraud-blocking policy, to attack this reject-inference problem inside the reward. A single LLM designs a dual-stream reward: stream 1 applies the standard dollar-weighted precision objective to labeled transactions; stream 2 scores legacy-blocked, unlabeled transactions by contrasting the newest gradient-boosted risk signal against the legacy scores that drove the original block. Rather than prescribe which signals matter, we expose a superset of evidence and let the LLM decide for itself which to use, guided by evaluation feedback alone; because it writes the reward as code, that choice is directly auditable. On a held-out four-month out-of-time test, the dual-stream agent beats the prior labeled-only agent at every target recall, by +4.7, +2.4 and +3.0 points of dollar-weighted precision at 80%, 85% and 90% recall, and the production baseline by +6.8 points on average. The resulting policy is architecturally identical to that of Qu et al. (2025) and adds no inference cost.

cs.LG↗

arXiv2026

AgentDecept: Benchmarking Deceptive Behavior in Tool-Using LLM Agents under Pressure

LLM agents increasingly carry out multi-turn tasks across everyday applications, yet users often see only the agent's report rather than the observations, API calls, and state changes behind it. Existing deception benchmarks have studied long-horizon interactions and tool-use settings, but whether agents faithfully report their actions across realistic, stateful application workflows remains underexplored. To address this gap, we introduce AgentDecept, an executable benchmark for evaluating behavioral deception under pressure. AgentDecept contains 477 pressure variants derived from 257 source tasks across six pressure sources, each paired with a pressure-free counterpart. Interventions enter through event messages, task context, application state, tool responses, and service quotas, spanning explicit events and implicit task or environment changes. Our evidence-grounded protocol evaluates full trajectories by relating user-facing claims to time-ordered observations and executed outcomes, distinguishing falsification, concealment, and equivocation from honest failure and disclosed limitations. The resulting behavioral labels also provide a setting for testing existing activation-based probes. AgentDecept enables controlled analysis of when multi-turn agents' reports diverge from execution in realistic application interactions.

cs.AI↗

arXiv2023

Sparse Depth-Guided Attention for Accurate Depth Completion: A Stereo-Assisted Monitored Distillation Approach

This paper proposes a novel method for depth completion, which leverages multi-view improved monitored distillation to generate more precise depth maps. Our approach builds upon the state-of-the-art ensemble distillation method, in which we introduce a stereo-based model as a teacher model to improve the accuracy of the student model for depth completion. By minimizing the reconstruction error of a target image during ensemble distillation, we can avoid learning inherent error modes of completion-based teachers. We introduce an Attention-based Sparse-to-Dense (AS2D) module at the front layer of the student model to enhance its ability to extract global features from sparse depth. To provide self-supervised information, we also employ multi-view depth consistency and multi-scale minimum reprojection. These techniques utilize existing structural constraints to yield supervised signals for student model training, without requiring costly ground truth depth information. Our extensive experimental evaluation demonstrates that our proposed method significantly improves the accuracy of the baseline monitored distillation method.

cs.CV↗

arXiv2022

Computer Vision-Aided Reconfigurable Intelligent Surface-Based Beam Tracking: Prototyping and Experimental Results

In this paper, we propose a novel computer vision-based approach to aid Reconfigurable Intelligent Surface (RIS) for dynamic beam tracking and then implement the corresponding prototype verification system. A camera is attached at the RIS to obtain the visual information about the surrounding environment, with which RIS identifies the desired reflected beam direction and then adjusts the reflection coefficients according to the pre-designed codebook. Compared to the conventional approaches that utilize channel estimation or beam sweeping to obtain the reflection coefficients, the proposed one not only saves beam training overhead but also eliminates the requirement for extra feedback links. We build a 20-by-20 RIS running at 5.4 GHz and develop a high-speed control board to ensure the real-time refresh of the reflection coefficients. Meanwhile we implement an independent peer-to-peer communication system to simulate the communication between the base station and the user equipment. The vision-aided RIS prototype system is tested in two mobile scenarios: RIS works in near-field conditions as a passive array antenna of the base station; RIS works in far-field conditions to assist the communication between the base station and the user equipment. The experimental results show that RIS can quickly adjust the reflection coefficients for dynamic beam tracking with the help of visual information.

eess.SP↗

arXiv2021

Hierarchical Segment-based Optimization for SLAM

This paper presents a hierarchical segment-based optimization method for Simultaneous Localization and Mapping (SLAM) system. First we propose a reliable trajectory segmentation method that can be used to increase efficiency in the back-end optimization. Then we propose a buffer mechanism for the first time to improve the robustness of the segmentation. During the optimization, we use global information to optimize the frames with large error, and interpolation instead of optimization to update well-estimated frames to hierarchically allocate the amount of computation according to error of each frame. Comparative experiments on the benchmark show that our method greatly improves the efficiency of optimization with almost no drop in accuracy, and outperforms existing high-efficiency optimization method by a large margin.

cs.RO↗

arXiv2021

A Collaborative Visual SLAM Framework for Service Robots

We present a collaborative visual simultaneous localization and mapping (SLAM) framework for service robots. With an edge server maintaining a map database and performing global optimization, each robot can register to an existing map, update the map, or build new maps, all with a unified interface and low computation and memory cost. We design an elegant communication pipeline to enable real-time information sharing between robots. With a novel landmark organization and retrieval method on the server, each robot can acquire landmarks predicted to be in its view, to augment its local map. The framework is general enough to support both RGB-D and monocular cameras, as well as robots with multiple cameras, taking the rigid constraints between cameras into consideration. The proposed framework has been fully implemented and verified with public datasets and live experiments.

cs.RO↗

arXiv2014

A new method of peak detection for analysis of comprehensive two-dimensional gas chromatography mass spectrometry data

We develop a novel peak detection algorithm for the analysis of comprehensive two-dimensional gas chromatography time-of-flight mass spectrometry (GC$\times$GC-TOF MS) data using normal-exponential-Bernoulli (NEB) and mixture probability models. The algorithm first performs baseline correction and denoising simultaneously using the NEB model, which also defines peak regions. Peaks are then picked using a mixture of probability distribution to deal with the co-eluting peaks. Peak merging is further carried out based on the mass spectral similarities among the peaks within the same peak group. The algorithm is evaluated using experimental data to study the effect of different cutoffs of the conditional Bayes factors and the effect of different mixture models including Poisson, truncated Gaussian, Gaussian, Gamma and exponentially modified Gaussian (EMG) distributions, and the optimal version is introduced using a trial-and-error approach. We then compare the new algorithm with two existing algorithms in terms of compound identification. Data analysis shows that the developed algorithm can detect the peaks with lower false discovery rates than the existing algorithms, and a less complicated peak picking model is a promising alternative to the more complicated and widely used EMG mixture models.

stat.AP↗