# BART Projects at AI Tinkerers > Canonical HTML: https://aitinkerers.org/technologies/bart > Markdown URL: https://aitinkerers.org/technologies/bart.md > Technology record last updated: 2026-03-10T20:38:47Z > Generated: 2026-08-26T05:26:31Z BART is a denoising autoencoder that combines bidirectional encoding with autoregressive decoding for superior text generation and comprehension. Developed by Facebook AI Research (FAIR), BART (Bidirectional and Auto-Regressive Transformers) bridges the gap between BERT-style understanding and GPT-style generation. It uses a standard sequence-to-sequence architecture with a 12-layer encoder and 12-layer decoder (in the large variant) to reconstruct original text from corrupted inputs. By applying noising techniques like sentence shuffling and token masking, the model learns deep contextual representations that excel at abstractive summarization and machine translation. On the CNN/Daily Mail dataset, BART achieved a significant 2.12 ROUGE-L gain over previous benchmarks, proving its efficiency in high-stakes natural language generation. - Official technology site: https://arxiv.org/abs/1910.13461 - Public AI Tinkerers demos and talks: 4 - Result page: 1 of 1 ## Recent Public Talks and Demos ### [Build an optimized agentic RAG agent!](https://dc.aitinkerers.org/talks/rsvp_I2_1__GU9oQ) We'll design, simulate, evaluate and optimize an Agentic RAG assistantβ€”trained on your data and tuned to your preferences! - Event context: AI Tinkerers x Trilligent: November Meetup β€” 2025-11-11 β€” DC - Public talk page: https://dc.aitinkerers.org/talks/rsvp_I2_1__GU9oQ ### [Tackling the ARC challenge as a side quest](https://london.aitinkerers.org/talks/rsvp_bKwAmYkOurk) The Abstraction and Reasoning Corpus, designed by FranΓ§ois Chollet, is a set of visual problems, known to be one of the hardest reasoning benchmarks which state of the art LLMs fail at. We'll be sharing our work and learnings from tackling the ARC challenge (arcprize.org) during the summer, and how we applied the intuition behind our reasoning engine to this benchmark. We will be open-sourcing a couple of elements including the solver and dataset, which we will present during that demo. - Event context: AI Tinkerers London - December Meetup πŸŽ„ β€” 2024-12-04 β€” London - Public talk page: https://london.aitinkerers.org/talks/rsvp_bKwAmYkOurk ### [AI Native React compiler](https://amsterdam.aitinkerers.org/talks/rsvp_a42GWjmALJw) I would give a talk on building a React compiler that’s optimized for interacting with LLMs. I want to highlight the opportunity that exists from creating optimizations in the toolkit that LLMs can use. I want to dive into what technical optimizations you can apply across a vertical level to achieve better performance. - Event context: AI Tinkerers Amsterdam - November β€” 2024-11-12 β€” Amsterdam - Public talk page: https://amsterdam.aitinkerers.org/talks/rsvp_a42GWjmALJw ### [Natural Language Compiler](https://toronto.aitinkerers.org/talks/rsvp_uRG4stRzPEM) A programming language compiler converts a document in one language to another lower-level representation, exactly capturing required semantics while linking it to external libraries or machine-dependent information. Similarly, my "natural language" compiler aims to convert a document to another lower-level representation (graphs), capturing all possible semantics while linking to external sources of data. The motivation is to form a human/machine-readable representation that facilitates explainable AI and RAG. - Event context: AI Tinkerers Toronto - Inaugural Meetup β€” 2024-04-11 β€” Toronto - Public talk page: https://toronto.aitinkerers.org/talks/rsvp_uRG4stRzPEM ## Related Technologies - [T5](https://aitinkerers.org/technologies/t5) ([Markdown](https://aitinkerers.org/technologies/t5.md)) β€” 5 public demos - [DPR](https://aitinkerers.org/technologies/dpr) ([Markdown](https://aitinkerers.org/technologies/dpr.md)) β€” 3 public demos - [FAISS](https://aitinkerers.org/technologies/faiss) ([Markdown](https://aitinkerers.org/technologies/faiss.md)) β€” 17 public demos - [Haystack](https://aitinkerers.org/technologies/haystack) ([Markdown](https://aitinkerers.org/technologies/haystack.md)) β€” 5 public demos - [LangChain](https://aitinkerers.org/technologies/langchain) ([Markdown](https://aitinkerers.org/technologies/langchain.md)) β€” 444 public demos - [RAG-Sequence](https://aitinkerers.org/technologies/rag-sequence) ([Markdown](https://aitinkerers.org/technologies/rag-sequence.md)) β€” 3 public demos - [RAG-Token](https://aitinkerers.org/technologies/rag-token) ([Markdown](https://aitinkerers.org/technologies/rag-token.md)) β€” 3 public demos - [BERT](https://aitinkerers.org/technologies/bert) ([Markdown](https://aitinkerers.org/technologies/bert.md)) β€” 179 public demos - [GPT-3](https://aitinkerers.org/technologies/gpt-3) ([Markdown](https://aitinkerers.org/technologies/gpt-3.md)) β€” 191 public demos - [GPT-4](https://aitinkerers.org/technologies/gpt-4) ([Markdown](https://aitinkerers.org/technologies/gpt-4.md)) β€” 529 public demos - [RoBERTa](https://aitinkerers.org/technologies/roberta) ([Markdown](https://aitinkerers.org/technologies/roberta.md)) β€” 118 public demos - [Agentic](https://aitinkerers.org/technologies/agentic) ([Markdown](https://aitinkerers.org/technologies/agentic.md)) β€” 3 public demos - [Agentic RAG](https://aitinkerers.org/technologies/agentic-rag) ([Markdown](https://aitinkerers.org/technologies/agentic-rag.md)) β€” 3 public demos - [AI infrastructure](https://aitinkerers.org/technologies/ai-infrastructure) ([Markdown](https://aitinkerers.org/technologies/ai-infrastructure.md)) β€” 2 public demos - [alBERT](https://aitinkerers.org/technologies/albert) ([Markdown](https://aitinkerers.org/technologies/albert.md)) β€” 4 public demos - [arcprize](https://aitinkerers.org/technologies/arcprize) ([Markdown](https://aitinkerers.org/technologies/arcprize.md)) β€” 1 public demo - [BLOOM](https://aitinkerers.org/technologies/bloom) ([Markdown](https://aitinkerers.org/technologies/bloom.md)) β€” 115 public demos - [CanDoo](https://aitinkerers.org/technologies/candoo) ([Markdown](https://aitinkerers.org/technologies/candoo.md)) β€” 1 public demo