← Search

Junfeng Fan

7 accepted papers

2026

Mesh-Pro: Asynchronous Advantage-guided Ranking Preference Optimization for Artist-style Quadrilateral Mesh Generation

CVPR 2026

Reinforcement learning (RL) has demonstrated remarkable success in text and image generation, yet its potential in 3D generation remains largely unexplored. Existing attempts typically rely on offline direct preference optimization (DPO) method, which suffers from low training efficiency and limited

Cited by 0SourceScholar
2026

Noise Suppression Method of Passive Electric Sense System for Robotic Shark

RA-L 2026

Passive electric sense, a unique underwater perception ability in aquatic species, enables fish to detect external electrical signals and perform essential life activities in dark or turbid environments. Inspired by the passive electrosensing capability of natural shark, this letter proposes a low-c

Cited by 0SourceScholar
2025

EPRecon: An Efficient Framework for Real-Time Panoptic 3D Reconstruction from Monocular Video

ICRA 2025

Panoptic 3D reconstruction from a monocular video is a fundamental perceptual task in robotic scene understanding. However, existing efforts suffer from inefficiency in terms of inference speed and accuracy, limiting their practical applicability. We present EPRecon, an efficient real-time panoptic

Cited by 0SourcecodeScholar
2025

Quantitative Analysis of Fish-Like Propulsion Mechanisms Based on the Discrete Vortex Method

RA-L 2025

Fish actively control their bodies to interact with the surrounding vortex flow field and generate thrust. Current research on the propulsion mechanisms of robotic fish primarily involves qualitative comparisons of vortex structures from simulations and experiments, lacking quantitative analysis. Th

Cited by 0SourceScholar
2023

Design and Modeling of a Sperm-Inspired Helical Propulsion Robot

RA-L 2023

The development of biomimetics and the demand for higher propulsion efficiency lead to more research in helical propulsion robots. This letter presents a novel sperm-inspired robot that utilizes flexible tail as propulsion and analyzes the motion performance. Firstly, the robot's propulsion system i

Cited by 1SourceScholar
2022

A Robotic End-Effector for Screwing and Unscrewing Bolts From the Side

RA-L 2022

This letter presents a novel robotic end-effector for screwing and unscrewing bolts. In many industrial scenarios, it is required to manipulate bolts from the side using robots with end-effectors. Besides, the reaction torque during tightening needs to be balanced to the stability of the robot. To a

Cited by 7SourceScholar
2022

SASH: Efficient secure aggregation based on SHPRG for federated learning

UAI 2022poster

To prevent private training data leakage in Federated Learning systems, we propose a novel secure aggregation scheme based on seed homomorphic pseudo-random generator (SHPRG), named SASH. SASH leverages the homomorphic property of SHPRG to simplify the masking and demasking scheme, which for each of…

Cited by 20SourcePDFScholar