jingtaozhan
Follow
Stars
Large Visual Language Model(LVLM), Large Language Model(LLM), Multimodal Large Language Model(MLLM), Alignment, Agent, AI System, Survey
Paper collections of the continuous effort start from World Models.
A general framework used on evaluating the performance of large language models (LLMs) based on the peer review mechanism among LLMs
The official repo for our SIGIR'23 Full paper: Structure-aware Pre-trained Language Model for Legal Case Retrieval
My postgraduate courses at THU-CST
[ACL 2023] One Embedder, Any Task: Instruction-Finetuned Text Embeddings
A curated list of awesome transformer models.
Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM
The implementation of deep learning models for EEG classification.
A Unified Library for Parameter-Efficient and Modular Transfer Learning
An easy-to-use python toolkit for flexibly adapting various neural ranking models to any target domain.
Our proposed evaluation metric for relevance judgment, refer "Evaluating Relevance Judgments with Pairwise Discriminative Power" in CIKM 2021 for more information
The homepage for ConvSearch Dataset.
程序员延寿指南 | A programmer's guide to live longer
CIKM 2022: Evaluating Interpolation and Extrapolation Performance of Neural Retrieval Models
SIGIR'22 paper: Axiomatically Regularized Pre-training for Ad hoc Search
Contriever: Unsupervised Dense Information Retrieval with Contrastive Learning
A simple tool to update bib entries with their official information (e.g., DBLP or the ACL anthology).
WSDM'22 Best Paper: Learning Discrete Representations via Constrained Clustering for Effective and Efficient Dense Retrieval
crowdsourced judgement data for shallow pooling for sparse labels paper
Our CIKM21 Paper "Incorporating Query Reformulating Behavior into Web Search Evaluation"
A curated list of awesome papers for Semantic Retrieval (TOIS Accepted: Semantic Models for the First-stage Retrieval: A Comprehensive Review).
proxychains ng (new generation) - a preloader which hooks calls to sockets in dynamically linked programs and redirects it through one or more socks/http proxies. continuation of the unmaintained p…
Acceptance rates for the major AI conferences
CIKM'21: JPQ substantially improves the efficiency of Dense Retrieval with 30x compression ratio, 10x CPU speedup and 2x GPU speedup.