Feng Zheng

Associate Professor@Southern University of Science and Technology·中国·OpenReview

研究方向

Vision-based Anomaly Detection · Multi-model Perception: RGBD · or RGBT tracking and video object segmentation · Robustness of Crossmodal Models · Vision Language Navigation · Vision Language Manipulation · Embodied Artificial Intelligence · Visual Lauguage Models · Machine learning: Deep learning · Computer vision: person re-identification

Feng Zheng

Spatially Guided Training for Vision-Language-Action Model

iCAS: A In-Context Anomaly Segmentation Framework for Industrial Visual Inspection

S$^2$MAM: Semi-supervised Meta Additive Model for Robust Estimation and Variable Selection

Color Blindness Test Images as Seen by Large Vision-Language Models

Detecting LLM Hallucinations via Nonlinear Manifold Separation

MesaTask: Towards Task-Driven Tabletop Scene Generation via 3D Spatial Reasoning

Sample then Identify: A General Framework for Risk Control and Assessment in Multimodal Large Language Models

OptiScene: LLM-driven Indoor Scene Layout Generation via Scaled Human-aligned Data Synthesis and Multi-Stage Preference Optimization

MMAD: A Comprehensive Benchmark for Multimodal Large Language Models in Industrial Anomaly Detection

On the Generalization Ability of Next-Token-Prediction Pretraining

MV3D-MAE: 2D Pre-trained MAEs are Effective 3D Representation Learners

HYBRID MODEL COLLABORATION FOR SIGN LANGUAGE TRANSLATION WITH VQ-VAE AND RAG ENHANCED LLMS

S$^2$MAM: Semi-supervised Meta Additive Model for Robust Estimation and Variable Selection

CAR: Controllable Autoregressive Modeling for Visual Generation