ABOUT

Hi, I'm 谷雨.

I'm an undergraduate student in Electronic Information Engineering at Shenzhen University.

My current interests lie at the intersection of multimodal AI, computer vision, computational imaging, and increasingly, large language model systems.

I enjoy projects where I can understand the whole pipeline: preparing data, implementing models, training them, evaluating their behavior, and figuring out why something works — or why it unexpectedly doesn't.

My previous work has focused mainly on image and video problems, including SDR-to-HDR conversion, video quality assessment, and image captioning. More recently, I've been exploring retrieval, language models, and the engineering behind modern LLM systems.

INTERESTS

Research Interests

01

Multimodal Learning

Connecting visual information with language and other modalities.

02

Image & Video Understanding

Learning representations for visual perception, restoration, generation, and quality assessment.

03

Computational Imaging

Learning-based image enhancement, reconstruction, and SDR-to-HDR conversion.

04

LLM Systems

Retrieval-augmented generation, language model architectures, lightweight training, and inference.

RESEARCH

Research

2026

Universal SDR-to-HDR Conversion via Bidirectional Degradation Source Prompt Learning

Research on universal SDR-to-HDR conversion and inverse tone mapping.

IEEE Transactions on Image Processing · Manuscript under review

PROJECTS

Selected Projects

01

SDR → HDR Inverse Tone Mapping

Research

Deep-learning-based SDR-to-HDR conversion experiments, including model reproduction, training, evaluation, and investigation of abnormal luminance behavior.

Source code is not publicly available.

PyTorch / Computer Vision / Computational Imaging
02

Flickr30k Image Captioning

Completed

Image captioning experiments with ResNet / ConvNeXt encoders, Attention-LSTM and Transformer decoders, beam search, and CIDEr-oriented SCST optimization.

PyTorch / Transformer / Multimodal Learning
03

KSVQE Video Quality Assessment

Completed

Reproduction and experimentation with KSVQE, including multi-view preprocessing, distortion analysis, cross-dataset evaluation, and inference.

Video / Quality Assessment / Deep Learning
04

Paper RAG Lab

In progress

A lightweight RAG laboratory for academic documents, comparing sparse, dense, hybrid retrieval, reranking, citation, and retrieval evaluation.

RAG / FAISS / Retrieval / LLM
05

Tiny LLM Lab

In progress

A small decoder-only language model implemented in PyTorch, exploring pretraining, autoregressive generation, and LoRA instruction tuning.

LLM / Transformer / LoRA / PyTorch

EXPERIENCE

Experience

2026

Hisense Visual Technology

SDR-to-HDR · Inverse Tone Mapping

Worked on a research project involving model reproduction, dataset preparation, training, evaluation, and analysis of SDR-to-HDR conversion behavior.

2025

Fengnong Holdings · AI R&D

LLM Knowledge Data Pipeline

Built and optimized data collection and cleaning pipelines for domain knowledge used in an agricultural large language model.

TOOLBOX

Things I Work With

Languages

Python · C · C++

Deep Learning

PyTorch · CNN · Transformer · ResNet · ConvNeXt · ViT · Swin Transformer · CLIP · Attention-LSTM

Vision

OpenCV · Image Processing · Video Processing

LLM / Retrieval

RAG · FAISS · Embeddings · LoRA

Data & Automation

Requests · aiohttp · Selenium

Engineering

Git · Linux · CUDA

I don't try to collect technologies for the sake of a longer list. Most things here come from projects I've actually worked on or am currently exploring.