Page Not Found
Page not found. Your pixels are in another canvas.
Sitemap
A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.
Pages
Page not in menu
This is a page not in th emain menu
Posts
2024 New Year Resolution
Published:
At the beginning of last year, I also scheduled ten things I planned for 2023 and a 3-day challenge for myself.
2023 Rewind
Published:
Hello everyone, the following is my rewind of 2023.
Machine Learning Enivorment Settings for Windows
Published:
This post will show you how to set up a machine learning enivorment for windows.
Rebuild ubuntu 22.04
Published:
This is a post about how to rebuild ubuntu 22.04, and install some useful tools.
New Year’s Resolution
Published:
Happy new year, everyone👋
New York
Published:
「The Big Apple. The dream of every lad that ever threw a leg over a thoroughbred and the goal of all horsemen. There’s only one Big Apple. That’s New York.」 —— The New York Morning Telegraph, John J. Fitz Gerald, 1921
My experience for watching NBA
Published:
「大江東去，浪淘盡，千古風流人物」 NBA 悠久歷史，出現許許多多傳奇，相信籃球迷也都津津樂到 在此不多贅述，只分享我這觀看幾年的心路歷程
Niagara Falls
Published:
「震懾與驚艷，無數條河流匯聚起，萬馬奔騰」，這是我對尼加拉瓜瀑布的評語，目前生平兩度造訪，第一次的初窺，第二次的領略，讓我大致體驗，無數水花飛濺，迷濛的霧氣環顧四周，那美好的記憶被錄製在腦中。
experiences
Academic Sinica Summer Internship
Summer Internship, Academic Sinica, Institute of Information Science, 2020
Duration: Jul. 2020 - Sep. 2020 (3 months)
Teaching Assistant
Part-time, National Yang Ming Chiao Tung University, Department of Communication Engineering, 2023
Duration: Sep. 2023 - Jan. 2024 (5 months)
Teaching Assistant
Part-time, National Yang Ming Chiao Tung University, Department of Communication Engineering, 2024
Duration: Feb. 2024 - Present
portfolio
Posture
Published:
College graduation project
P2P Object detection system
Published:
Graduated project in National Taipei Tech. 
Mental Health Chatbot
Published:
Team project in National Yang-Ming Chiao-Tung University
Machine Learning From Scratch
Published:
Personal Side Project
Kotlin is all you need
Published:
Personal Side Project
Engineering Design
Published:
Course homework
publications
2022-Fall-NYCU Course Note
Published in NCTU CS Course, 2022
Those are my notes for taking courses
2023-Spring-NYCU Course Note
Published in NCTU CS Course, 2023
Those are my notes for taking courses
Empowering NLG: Offline Reinforcement Learning for Informal Summarization in Online Domains
Published in arXiv, 2023
Research paper for Natural Language Generation (NLG)
Download here
2023-Fall-NYCU Course Note
Published in NCTU CS Course, 2023
Those are my notes for taking courses
NYCUKA: A Self‐Disclosure Mental Health Spoken Dialogue System
Published in IEEE Workshop on Automatic Speech Recognition and Understanding, 2023
Demo paper for Natural Language Processing (NLP)
Download here
2024-Spring-NYCU Course Note
Published in NCTU CS Course, 2024
Those are my notes for taking courses
talks
NIST Fingerprint Evaluations and Developments
Published:
Paper presentation for the course called Computer Security in Chang Gung University
Computer and Storage System Paper Collection
Published:
All of my slides which were presented while I was in Taipei Tech.
EDF-SSD: An Improved Feature Fused SSD for Onjection Detection
Published:
Paper presentation for the course called File and Storage system in National Taipei Tech.
Leveraging BERT for Extractive Text Summarization on Lectures
Published:
Paper presentation and implemenation for the course called Machine Learning in National Taipei Tech.
Addressing Function Approximation Error in Actor-Critic Methods
Published:
In value-based reinforcement learning methods, function approximation errors are known to lead to overestimated value estimates and sub-optimal policies.
Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems
Published:
This paper provide the reader with the conceptual tools needed to get started on research on offline reinforcement learning algorithms:
reinforcement learning algorithms that utilize previously collected data, without additional online data collection.
Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables
Published:
Previous methods rely heavily on on-policy experience, limiting their sample efficiency.
They also lack mechanisms to reason about task uncertainty when adapting to new tasks, limiting their effectiveness in sparse reward problems.
This paper developing an off-policy meta-RL algorithm that disentangles task inference and control.
- Achieving excellent sample efficiency during meta-training, enables fast adaptation by accumulating experience online
- Performing structured exploration by reasoning about uncertainty over tasks
BEIT:BERT Pre-training of Image Transformers
Published:
Motivated by BERT, they turn to the denoising auto-encoding idea to pretrain vision transformers, which has not been well studied by the vision community.
Second Thoughts are Best: Learning to Re-Align With Human Values from Text Edits
Published:
This paper present SECOND THOUGHTS, a new learning paradigm that enables language models (LMs) to re-align with human values.
Training language models to follow instructions with human feedback
Published:
This paper show a method to align language models with user intent on a wide range of tasks by fine-tuning with human feedback.
HyperPrompt:Prompt-based Task-Conditioning of Transformers
Published:
This paper proposes HyperPrompt, a novel architecture for prompt-based task-conditioning of self-attention in Transformers.
Is Reinforcement Learning (Not) for Natural Language Processing
Published:
In this paper, they first introduce an open-source modular library RL4LMs, for optimizing language generators with RL.
A Mixture-of-Expert Approach to RL-based Dialogue Management
Published:
In this paper, they introduce RL-based DM using a novel mixture of expert language model (MoE-LM) that consists of
Off-Policy Deep Reinforcement Learning without Exploration
Published:
This paper proposes a new algorithm for off-policy reinforcement learning that combines state-of-the-art deep Q-learning algorithms with a state-conditioned generative model for producing only previously seen actions.
Evaluating Parameter Efficient Learning for Generation
Published:
In this paper, they present a comprehensive evaluation of parameter efficient learning methods (PERMs) for generation tasks in natural language processing.
Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
Published:
This study proposes a fine-tuning recipe for retrieval-augmented generation (RAG) models that combine pre-trained parametric and non-parametric memory for language generation.
Active Retrieval Augmented Generation
Published:
Most existing retrieval-augmented LMs employ a retrieve-and-generate setup that only retrieves information once based on the input.
LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention
Published:
This paper proposes LLaMA-Adapter, a lightweight adaption method to efficiently finetune LLaMA into an instruction-following model.
AdaMix: Mixture-of-Adaptations for Parameter-efficient Model Tuning
Published:
This paper proposes a parameter-efficient fine-tuning method called $\texttt{AdaMix}$, a general parameter-efficient fine-tuning (PEFT) techniques that tunes a mixture of adaptation modules.
A Neural Corpus Indexer for Document Retrieval
Published:
Current SOTA for document retrieval solutions mainly follow an index-retrieve, where the index is hard to be directly optimized for the final retrieval target.
A Statistical Perspective on Retrieval-Based Models
Published:
This paper uses a formal treatment of retrieval-based models to characterize their performance via a novel statistical perspective.
GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers
Published:
Nowadays, Generative Pre-trained Transformer models has not only breakthrough performance across complex language modelling tasks, but also by their extremely high computational and storage costs.
On the Effectiveness of Offline RL for Dialogue Response Generation
Published:
For language models, many methods using teacher forcing (TF) to train.
Empathetic Dialogue Generation via Sensitive Emotion Recognition and Sensible Knowledge Selection
Published:
In this research, the authors address challenges in empathetic dialogue generation.
Quark: Controllable Text Generation with Reinforced [Un]learning
Published:
Large language models may generate content that is misaligned with the user’s expectations. For example, generating toxic words, repeated content, and undesired responses for users.
Effective Structured Prompting by Meta-Learning and Representative Verbalizer
Published:
This paper utilizes a prompt pool to leverage task-specific knowledge and generate instance-specific prompts using attention mechanisms.
E-CORE: Emotion Correlation Enhanced Empathetic Dialogue Generation
Published:
Empathetic dialogue generation task aims at generating empathetic responses, based on perceived emotions instead of definite annotated emotions.