Elian(李子茉) ☕️

Elian(李子茉)

Hello everyone! I am Elian(李子茉), a Large Language Model algorithm researcher.

Click resume to view my details.

*
All Large Language Model Computer Vision Application
ReTRM: Re-Thinking the Reward Model Training Paradigm
This paper introduces a novel reward model training method, specifically an application of linear direct sum decomposition and SVD decomposition, which separates the inference space from the latent space to train the reward.
ReTRM: Re-Thinking the Reward Model Training Paradigm
From Policy Gradient (PG) to Group Sequence Policy Optimization (GSPO): Some Thoughts on RLHF
This article will introduce the policy gradient algorithm from the optimization objective of LLM-RL and gradually transition to the GSPO algorithm. It will also point out the current problems of RLHF and summarize the solutions summarized from some experiments I have conducted.
From Policy Gradient (PG) to Group Sequence Policy Optimization (GSPO): Some Thoughts on RLHF
HARP: Hallucination Detection Via Reasoning Subspace Projection
This is a very interesting work on LLM hallucination detection. It decomposes the hidden state into a linear sum of the semantic space and the reasoning space, using the idea of ​​direct sum decomposition in linear algebra. It is very interesting.
HARP: Hallucination Detection Via Reasoning Subspace Projection
Service material writing system based on RAG and NL2SQL fusion architecture
RAG process design and DeepSeek fine-tuning
Service material writing system based on RAG and NL2SQL fusion architecture
LLM reasoning system based on FastAPI and vLLM
vHPR is an LLM reasoning system built on FastAPI and vLLM. Its primary purpose is to evaluate LLM benchmarks. The system provides a complete benchmark evaluation API and performance monitoring system.
LLM reasoning system based on FastAPI and vLLM
ElianFactory: Fine-tuning large language models on Windows made easy
This project developed a tool that can perform fine-tuning training of large models on Windows systems. The fine-tuning inference framework is developed based on the transformers library.
ElianFactory: Fine-tuning large language models on Windows made easy