Pinned Repositories
c3vqg-official
Code for the paper "C3VQG: Category Consistent Cyclic Visual Question Generation".
DeepSeek-Math
E-Diary
Voice Verification with Emotional Diary
easy-to-hard
Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision
expl
Can Small Models also learn to explain?
Friend-Pred
User-Friendly Sentence Prediction AI Model
hbin0701.github.io
My Website
Self-Explore
[EMNLP Findings 2024 & ACL 2024 NLRSE Oral] Enhancing Mathematical Reasoning in Language Models with Fine-grained Rewards
VT_with_NR_for_FER
[ICASSP 2022] Vision Transformer Equipped with Neural Resizer on Facial Expression Recognition Task
TAPP
[AAAI 2024] Investigating the Effectiveness of Task-Agnostic Prefix Prompt for Instruction Following
hbin0701's Repositories
hbin0701/Self-Explore
[EMNLP Findings 2024 & ACL 2024 NLRSE Oral] Enhancing Mathematical Reasoning in Language Models with Fine-grained Rewards
hbin0701/VT_with_NR_for_FER
[ICASSP 2022] Vision Transformer Equipped with Neural Resizer on Facial Expression Recognition Task
hbin0701/expl
Can Small Models also learn to explain?
hbin0701/hbin0701.github.io
My Website
hbin0701/c3vqg-official
Code for the paper "C3VQG: Category Consistent Cyclic Visual Question Generation".
hbin0701/DeepSeek-Math
hbin0701/E-Diary
Voice Verification with Emotional Diary
hbin0701/easy-to-hard
Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision
hbin0701/Flipped-Learning
[ICLR 2023] Guess the Instruction! Flipped Learning Makes Language Models Stronger Zero-Shot Learners
hbin0701/Friend-Pred
User-Friendly Sentence Prediction AI Model
hbin0701/handson_blockchain
hbin0701/hbin0701
Config files for my GitHub profile.
hbin0701/Map
Website to recommend hot places around you
hbin0701/One_MEAL
Place to find your best meal mate :)
hbin0701/QuaLITY_re
Re-Implementing Quality catering to Google Colab env.
hbin0701/FLOW_data
hbin0701/gpu-board
🚀 View NVIDIA-SMI from multiple nodes at once
hbin0701/Kpop_Lookism
Twitter & Instagram Data Analysis to find artifacts from K-Pop's promotion of Lookism.
hbin0701/LLM-Reverse-Curriculum-RL
Implementation of "Training Large Language Models for Reasoning through Reverse Curriculum Reinforcement Learning" presented by Zhiheng Xi et al.
hbin0701/MATES
Official repository for MATES: Model-Aware Data Selection for Efficient Pretraining with Data Influence Models
hbin0701/QIA2023
QIA2023 Code Submission
hbin0701/RL4LMs
A modular RL library to fine-tune language models to human preferences
hbin0701/Solo-Improvisor
Jazz Solo Improvisor Using Deep Learning
hbin0701/sparcs-newbie-project
hbin0701/sparcs.org-v3
sparcs.org v3
hbin0701/summary-reference-revision
hbin0701/Super_MARIO
hbin0701/TD-Advisor
Travel / Date Course Planner using Deep Learning
hbin0701/text-autoencoders
hbin0701/verify_cot