arXiv subjects

Xiaogang Yuan

Publications and source records attributed to Xiaogang Yuan.

3 recordsLinked to original sources

arXiv2025

DBINDS -- Can Initial Noise from Diffusion Model Inversion Help Reveal AI-Generated Videos?

AI-generated video has advanced rapidly and poses serious challenges to content security and forensic analysis. Existing detectors rely mainly on pixel-level visual cues and generalize poorly to unseen generators. We propose DBINDS, a diffusion-model-inversion based detector that analyzes latent-space dynamics rather than pixels. We find that initial noise sequences recovered by diffusion inversion differ systematically between real and generated videos. Building on this, DBINDS forms an Initial Noise Difference Sequence (INDS) and extracts multi-domain, multi-scale features. With feature optimization and a LightGBM classifier tuned by Bayesian search, DBINDS (trained on a single generator) achieves strong cross-generator performance on GenVidBench, demonstrating good generalization and robustness in limited-data settings.

cs.CV↗

arXiv2024

Admittance Visuomotor Policy Learning for General-Purpose Contact-Rich Manipulations

Contact force in contact-rich environments is an essential modality for robots to perform general-purpose manipulation tasks, as it provides information to compensate for the deficiencies of visual and proprioceptive data in collision perception, high-precision grasping, and efficient manipulation. In this paper, we propose an admittance visuomotor policy framework for continuous, general-purpose, contact-rich manipulations. During demonstrations, we designed a low-cost, user-friendly teleoperation system with contact interaction, aiming to gather compliant robot demonstrations and accelerate the data collection process. During training and inference, we propose a diffusion-based model to plan action trajectories and desired contact forces from multimodal observation that includes contact force, vision and proprioception. We utilize an admittance controller for compliance action execution. A comparative evaluation with two state-of-the-art methods was conducted on five challenging tasks, each focusing on different action primitives, to demonstrate our framework's generalization capabilities. Results show our framework achieves the highest success rate and exhibits smoother and more efficient contact compared to other methods, the contact force required to complete each tasks was reduced on average by 48.8%, and the success rate was increased on average by 15.3%. Videos are available at https://ryanjiao.github.io/AdmitDiffPolicy/.

cs.RO↗

arXiv2020

Concept of SUb-atmospheric Radio-frequency Engine (SURE) for near space environment

A concept of SUb-atmospheric Radio-frequency Engine (SURE) designed for near space environment is reported. The antenna wrapping quartz tube consists of two solenoid coils with variable separation distance, and is driven by radio-frequency power supply (13.56~MHz-1~kW). The discharge involves inductive coupling under each solenoid coil and capacitive coupling between them. This novel scheme can ionize the filling air efficiently for the entire pressure range of 32\sim 5332 Pa in near space. The formed plasma density and temperature are up to 2.23\times 10^{18}~m^{-3} and 2.79 eV, respectively. The influences of separation distance, input power, filling pressure and the number of solenoid turns on discharge are presented in detail. This air-breathing electric propulsion system has no plasma-facing electrode and does not require external magnetic field, and is thereby durable and structurally compact and light.

physics.plasm-ph↗