Hi, I am a Ph.D. student@ECNU, and I am also passionate about my research intern@Inclusion AI, Ant Group.
DeepScan. Official implement for "DeepScan: A Training-Free Framework for Visually Grounded Reasoning in Large Vision-Language Models"
242DS-TDNN. Official implement of "Dual-stream Time-Delay Neural Network with Dynamic Global Filter for Speaker Verification" in PyTorch
41DFCG. An official implement of "DeflickerCycleGAN: Learning to Detect and Remove Flickers in a Single Image"
13UniVR. An official implement of "UniVR: A Unified Framework for Pitch-Shifted Voice Restoration in Speaker Identification"
9EasyR1. Python
6FLCL. Official implement of "Free Lunch: Frame-level Contrastive Learning with Text Perceiver for Robust Scene Text Recognition in Lightweight Models" in PyTorch.
3Perceptual-Flow-Network. Source code for the ICML 2026 paper "Perceptual Flow Network for Visually Grounded Reasoning"
3Conv-AttNet. An official implement of "A Conv-Attention Network for detecting the Presence of ENF Signal in Short-Duration Audios"
2Flex-RAG. A flexible framework for RAG engineering
1Light-weight-OCR-systems. A repo for light-weight ocr systems
1PyTorch-based-Image-blur. A PyTorch-based acceleration for straug library
1