Interleaves chain-of-thought reasoning with tool-using actions in one LLM loop: the model plans, queries a source like Wikipedia, then revises from results. Cuts hallucination versus reasoning-only prompting and beats trained agents on interactive tasks.
Zirui Guo, Lianghao Xia +3University of Hong Kong, Beijing University of Posts and Telecommunications
A graph-based RAG framework pairing a knowledge graph with vector retrieval and a dual-level (low/high) query mode. New documents merge into the graph via set operations instead of triggering a rebuild, cutting the cost of keeping the index current.
First model to make a decoder dynamically focus on different source words instead of cramming a whole sentence into one fixed vector — the soft-alignment idea that became "attention" and, three years later, powered the Transformer.
End-to-end encoder–decoder using deep LSTMs to map variable-length input sequences to output sequences; demonstrated competitive English→French translation (BLEU 34.8) and improved optimization by reversing source sentences, showing strong handling of long sentences.
AI Others2015
Processes and indexes seized digital evidence — disk images, files, timelines — for forensic examiners. Bundles high-speed carving, OCR, named-entity recognition, similar-image and face search, and audio transcription behind scriptable Java parsers.
The 2017 paper that replaced recurrence with pure self-attention, making sequence models fully parallelizable — and, almost as a side effect, laying the architectural foundation for nearly every large language model that followed, from BERT to GPT.
AI Train2017
Sequence modeling toolkit for training custom models for translation, summarization, and language modeling. Reference implementation behind RoBERTa, BART, mBART, XLM-R, and wav2vec 2.0, with multi-GPU and mixed-precision training.
Provides 150+ executed Jupyter notebooks and code that reproduce the book 'Machine Learning for Algorithmic Trading (2nd ed.)' — covers feature engineering, alternative-data signal extraction, backtesting, NLP, deep learning and reinforcement learning for trading; best for quant researchers and practitioners.
Embeds multi-head self-attention inside an LSTM-style memory, so stored memories can attend to one another instead of just sitting in separate slots — sharpening relational reasoning and topping WikiText-103, Project Gutenberg, and GigaWord.
Introduced the two-stage recipe behind the GPT lineage: unsupervised generative pre-training on unlabeled text, then supervised fine-tuning per task. A single 12-layer Transformer decoder beat bespoke architectures on 9 of 12 NLP benchmarks.
Pre-trains a deep bidirectional Transformer encoder with masked-language-modeling and next-sentence prediction, then fine-tunes one model on 11 NLP tasks, reaching state-of-the-art on GLUE, SQuAD, and MultiNLI with little task-specific tuning.
AI Model2018
Provides unified model definitions and a single API for pretrained text, vision, audio, and multimodal models for both training and inference. Emphasizes cross-framework compatibility (PyTorch/TF/JAX), pipeline-based inference, and direct access to 1M+ Hub checkpoints.