arXiv subjects

Liang Gong

Publications and source records attributed to Liang Gong.

9 recordsLinked to original sources

arXiv2025

Generative AI for Industrial Contour Detection: A Language-Guided Vision System

Industrial computer vision systems often struggle with noise, material variability, and uncontrolled imaging conditions, limiting the effectiveness of classical edge detectors and handcrafted pipelines. In this work, we present a language-guided generative vision system for remnant contour detection in manufacturing, designed to achieve CAD-level precision. The system is organized into three stages: data acquisition and preprocessing, contour generation using a conditional GAN, and multimodal contour refinement through vision-language modeling, where standardized prompts are crafted in a human-in-the-loop process and applied through image-text guided synthesis. On proprietary FabTrack datasets, the proposed system improved contour fidelity, enhancing edge continuity and geometric alignment while reducing manual tracing. For the refinement stage, we benchmarked several vision-language models, including Google's Gemini 2.0 Flash, OpenAI's GPT-image-1 integrated within a VLM-guided workflow, and open-source baselines. Under standardized conditions, GPT-image-1 consistently outperformed Gemini 2.0 Flash in both structural accuracy and perceptual quality. These findings demonstrate the promise of VLM-guided generative workflows for advancing industrial computer vision beyond the limitations of classical pipelines.

cs.CV↗

arXiv2025

CO2 adsorption mechanisms in hydrated silica nanopores: Insights from grand canonical Monte Carlo to classical and ab initio molecular dynamics

Understanding interfacial phenomena in confined systems is important for optimizing CO2 capture technologies. Here, we present a comprehensive investigation of CO2 adsorption in hydrated amorphous silica nanopores through an integrated computational approach combining grand canonical Monte Carlo (GCMC), classical molecular dynamics (MD), and ab initio molecular dynamics (AIMD) simulations. The excess adsorption isotherms reveal a marked hydration dependence, with CO2 uptake decreasing from 7.6 to 2.6 mmol/g as water content increases from 1 to 15 wt%. Analysis of adsorption kinetics demonstrates a distinctive bimodal process, characterized by rapid initial uptake followed by slower diffusion-limited adsorption, with the latter becoming increasingly dominant at higher hydration levels. Classical MD simulations reveal an inverse correlation between hydration and CO2 mobility, with self-diffusion coefficients decreasing across the studied hydration range. Density profile analysis indicates a hydration-induced transition in CO2 distribution from central pore regions to surface-proximate domains, accompanied by restructuring of interfacial water networks. Notably, AIMD simulations capture previously unrecognized chemical processes, including proton transfer mechanisms leading to surface silanol formation with characteristic O-O distances of 2.4-2.5 {\AA}, and spontaneous CO2 hydration yielding carbonate species through water-mediated reaction pathways. These findings demonstrate the dual role of confined water as both a spatial competitor and reaction medium for CO2 capture, providing molecular-level insights with quantum mechanical accuracy for design of carbon capture materials.

cond-mat.mtrl-sci↗

arXiv2024

Well-separated soliton-antisoliton pairs with an adjoint Higgs field in 4D space

We present single soliton states and soliton-antisoliton states with an adjoint Higgs field in 4D flat space. The action of a single soliton state diverges, while the action of soliton-antisoliton states converges. This means such solitons can exist in soliton-antisoliton states, although they cannot exist individually. The interaction in a soliton-antisoliton state takes a logarithmic dependence on separation. Such soliton-antisoliton states exhibit stability under a scaling transformation.

hep-th↗

arXiv2024

Safe Reinforcement Learning via Hierarchical Adaptive Chance-Constraint Safeguards

Ensuring safety in Reinforcement Learning (RL), typically framed as a Constrained Markov Decision Process (CMDP), is crucial for real-world exploration applications. Current approaches in handling CMDP struggle to balance optimality and feasibility, as direct optimization methods cannot ensure state-wise in-training safety, and projection-based methods correct actions inefficiently through lengthy iterations. To address these challenges, we propose Adaptive Chance-constrained Safeguards (ACS), an adaptive, model-free safe RL algorithm using the safety recovery rate as a surrogate chance constraint to iteratively ensure safety during exploration and after achieving convergence. Theoretical analysis indicates that the relaxed probabilistic constraint sufficiently guarantees forward invariance to the safe set. And extensive experiments conducted on both simulated and real-world safety-critical tasks demonstrate its effectiveness in enforcing safety (nearly zero-violation) while preserving optimality (+23.8%), robustness, and fast response in stochastic real-world settings.

cs.RO↗

arXiv2023

POAR: Efficient Policy Optimization via Online Abstract State Representation Learning

While the rapid progress of deep learning fuels end-to-end reinforcement learning (RL), direct application, especially in high-dimensional space like robotic scenarios still suffers from low sample efficiency. Therefore State Representation Learning (SRL) is proposed to specifically learn to encode task-relevant features from complex sensory data into low-dimensional states. However, the pervasive implementation of SRL is usually conducted by a decoupling strategy in which the observation-state mapping is learned separately, which is prone to over-fit. To handle such problem, we summarize the state-of-the-art (SOTA) SRL sub-tasks in previous works and present a new algorithm called Policy Optimization via Abstract Representation which integrates SRL into the policy optimization phase. Firstly, We engage RL loss to assist in updating SRL model so that the states can evolve to meet the demand of RL and maintain a good physical interpretation. Secondly, we introduce a dynamic loss weighting mechanism so that both models can efficiently adapt to each other. Thirdly, we introduce a new SRL prior called domain resemblance to leverage expert demonstration to improve SRL interpretations. Finally, we provide a real-time access of state graph to monitor the course of learning. Experiments indicate that POAR significantly outperforms SOTA RL algorithms and decoupling SRL strategies in terms of sample efficiency and final rewards. We empirically verify POAR to efficiently handle tasks in high dimensions and facilitate training real-life robots directly from scratch.

cs.RO↗

arXiv2023

FLYOVER: A Model-Driven Method to Generate Diverse Highway Interchanges for Autonomous Vehicle Testing

It has become a consensus that autonomous vehicles (AVs) will first be widely deployed on highways. However, the complexity of highway interchanges becomes the bottleneck for deploying AVs. An AV should be sufficiently tested under different highway interchanges, which is still challenging due to the lack of available datasets containing diverse highway interchanges. In this paper, we propose a model-driven method, FLYOVER, to generate a dataset consisting of diverse interchanges with measurable diversity coverage. First, FLYOVER proposes a labeled digraph to model the topology of an interchange. Second, FLYOVER takes real-world interchanges as input to guarantee topology practicality and extracts different topology equivalence classes by classifying the corresponding topology models. Third, for each topology class, FLYOVER identifies the corresponding geometrical features for the ramps and generates concrete interchanges using k-way combinatorial coverage and differential evolution. To illustrate the diversity and applicability of the generated interchange dataset, we test the built-in traffic flow control algorithm in SUMO and the fuel-optimization trajectory tracking algorithm deployed to Alibaba's autonomous trucks on the dataset. The results show that except for the geometrical difference, the interchanges are diverse in throughput and fuel consumption under the traffic flow control and trajectory tracking algorithms, respectively.

cs.RO↗

arXiv2021

Efficiently Training On-Policy Actor-Critic Networks in Robotic Deep Reinforcement Learning with Demonstration-like Sampled Exploration

In complex environments with high dimension, training a reinforcement learning (RL) model from scratch often suffers from lengthy and tedious collection of agent-environment interactions. Instead, leveraging expert demonstration to guide RL agent can boost sample efficiency and improve final convergence. In order to better integrate expert prior with on-policy RL models, we propose a generic framework for Learning from Demonstration (LfD) based on actor-critic algorithms. Technically, we first employ K-Means clustering to evaluate the similarity of sampled exploration with demonstration data. Then we increase the likelihood of actions in similar frames by modifying the gradient update strategy to leverage demonstration. We conduct experiments on 4 standard benchmark environments in Mujoco and 2 self-designed robotic environments. Results show that, under certain condition, our algorithm can improve sample efficiency by 20% ~ 40%. By combining our framework with on-policy algorithms, RL models can accelerate convergence and obtain better final mean episode rewards especially in complex robotic context where interactions are expensive.

cs.LG↗

arXiv2020

Exploration-efficient Deep Reinforcement Learning with Demonstration Guidance for Robot Control

Although deep reinforcement learning (DRL) algorithms have made important achievements in many control tasks, they still suffer from the problems of sample inefficiency and unstable training process, which are usually caused by sparse rewards. Recently, some reinforcement learning from demonstration (RLfD) methods have shown to be promising in overcoming these problems. However, they usually require considerable demonstrations. In order to tackle these challenges, on the basis of the SAC algorithm we propose a sample efficient DRL-EG (DRL with efficient guidance) algorithm, in which a discriminator D(s) and a guider G(s) are modeled by a small number of expert demonstrations. The discriminator will determine the appropriate guidance states and the guider will guide agents to better exploration in the training phase. Empirical evaluation results from several continuous control tasks verify the effectiveness and performance improvements of our method over other RL and RLfD counterparts. Experiments results also show that DRL-EG can help the agent to escape from a local optimum.

cs.RO↗

arXiv2014

Locating Crashing Faults based on Crash Stack Traces

Software crashes due to its increasing complexity. Once a crash happens, a crash report could be sent to software developers for investigation upon user permission. Because of the large number of crash reports and limited information, debugging for crashes is often a tedious and labor-intensive task. In this paper, we propose a statistical fault localization framework to help developers locate functions that contain crashing faults. We generate the execution traces for the failing traces based on the crash stack, and the passing traces from normal executions. We form program spectra by combining generated passing and failing trace, and then apply statistical fault localization techniques such as Ochiai to locate the crashing faults. We also propose two heuristics to improve the fault localization performance. We evaluate our approach using the real-world Firefox crash report data. The results show that the performance of our method is promising. Our approach permits developers to locate 63.9% crashing faults by examining only 5% Firefox 3.6 functions in the spectra.

cs.SE↗