SparkJiao
Ph.D. candidate at Nanyang Technological University and Institute for Infocomm Research, A*STAR, Singapore. #NLP
NTU-NLP & I2R, A*STAR, SingaporeSinagpore
Pinned Repositories
pandallm
Panda项目是于2023年5月启动的开源海外中文大语言模型项目,致力于大模型时代探索整个技术栈,旨在推动中文自然语言处理领域的创新和合作。
LLMSanitize
An open-source library for contamination detection in NLP datasets and Large Language Models (LLMs).
dpo-trajectory-reasoning
Source code for the paper "Learning Planning-based Reasoning with Trajectory Collection and Process Rewards Synthesizing".
KK-s-Paperlist
A list of papers for machine learning, reinforcement learning, NLP or something interesting
llama-pipeline-parallel
A prototype repo for hybrid training of pipeline parallel and distributed data parallel with comments on core code snippets. Feel free to copy code and launch discussions about the problems you have encoured.
LogicLLM
Source code for paper "LogicLLM: Exploring Self-supervised Logic-enhanced Training for Large Language Models".
MERIt
Meta-Path Guided Contrastive Learning for Logical Reasoning of Text
MG-PFCM_outfit_rec
Personalized Fashion Compatibility Modeling via Metapath-guided Heterogeneous Graph Learning.
Self-Training-MRC
This is the pytorch implementation of the long paper on ACL 2020: A Self-Training Method for Machine Reading Comprehension with Soft Evidence Extraction.
SLQA
An Unofficial Pytorch Implementation of Multi-Granularity Hierarchical Attention Fusion Networks for Reading Comprehension and Question Answering
SparkJiao's Repositories
SparkJiao/llama-pipeline-parallel
A prototype repo for hybrid training of pipeline parallel and distributed data parallel with comments on core code snippets. Feel free to copy code and launch discussions about the problems you have encoured.
SparkJiao/MERIt
Meta-Path Guided Contrastive Learning for Logical Reasoning of Text
SparkJiao/MG-PFCM_outfit_rec
Personalized Fashion Compatibility Modeling via Metapath-guided Heterogeneous Graph Learning.
SparkJiao/dpo-trajectory-reasoning
Source code for the paper "Learning Planning-based Reasoning with Trajectory Collection and Process Rewards Synthesizing".
SparkJiao/LARCH
A novel contextuaL imAge seaRch sCHeme (LARCH)
SparkJiao/pytorch-transformers-template
This is a template for fast prototype relying on transformers, hydra, fairscale and deepspeed, etc.
SparkJiao/LogicLLM
Source code for paper "LogicLLM: Exploring Self-supervised Logic-enhanced Training for Large Language Models".
SparkJiao/NL2SQL-Financial
SparkJiao/BLIP
PyTorch code for BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation
SparkJiao/BSA-Net
Official implementation of AAAI2022 paper "I can find you! Boundary-guided Separated Attention Network for Camouflaged Object Detection"
SparkJiao/dst-multi-woz-2.1
SparkJiao/llm-agent-paper-list
SparkJiao/C2FNet-TSCVT
SparkJiao/DeepSpeed
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
SparkJiao/DST-STAR
Slot Self-Attentive Dialogue State Tracking
SparkJiao/ERICA
Source code for ACL 2021 paper "ERICA: Improving Entity and Relation Understanding for Pre-trained Language Models via Contrastive Learning"
SparkJiao/LAVT-RIS
SparkJiao/LLaVA
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
SparkJiao/LLM4VL
LLM application for vision-language task
SparkJiao/mae
PyTorch implementation of MAE https//arxiv.org/abs/2111.06377
SparkJiao/nimo-markdown-cv
Maintain your CV in Markdown :sparkles:
SparkJiao/NTU-CE7455-assignments
SparkJiao/OpenPSG
Benchmarking Panoptic Scene Graph Generation (PSG), ECCV'22
SparkJiao/panda-tutorial
SparkJiao/RAP
Reasoning with Language Model is Planning with World Model
SparkJiao/reflexion
[NeurIPS 2023] Reflexion: Language Agents with Verbal Reinforcement Learning
SparkJiao/single-page-markdown-cv
SparkJiao/SparkJiao
SparkJiao/SparkJiao.github.io
Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes
SparkJiao/ZoomNet
Zoom In and Out: A Mixed-scale Triplet Network for Camouflaged Object Detection, CVPR 2022