AI Papers of the Week
Every paper worth reading in AI, hand-picked one week at a time.
Discover and explore top AI papers withClaude CodeCodex
npx @dair-ai/mcp setup
DoReMi
Optimizes data mixtures for faster language model pretraining.
CodeT5+
An open code LLM family for code understanding and generation.
Symbol tuning
Fine-tunes LMs on in-context input-label pairs with natural-language labels replaced by arbitrary symbols.
Incidental Bilingualism in PaLM's Translation Capability
Explores where PaLM's translation ability actually comes from.
LLM Explains Neurons in LLMs
OpenAI's automated interpretability pipeline using GPT-4 to explain GPT-2 neurons.
PaLM 2
Google's second-generation PaLM powering Bard and Google products.
ImageBind
Meta's joint embedding across six modalities at once.
TidyBot
Combines LLM-based planning and perception with few-shot summarization to infer user preferences.
Unfaithful Explanations in Chain-of-Thought Prompting
Demonstrates CoT explanations can misrepresent the true reason for a model's prediction.
InstructBLIP
Visual-language instruction tuning built on BLIP-2.
Active Retrieval Augmented LLMs (FLARE)
Actively decides when and what to retrieve during generation.
FrugalGPT
Strategies to reduce LLM inference cost while improving performance.
StarCoder
An open-access 15.5B code LLM with 8K context and 80+ programming languages.
MultiModal-GPT
A vision-language model for multi-round dialogue fine-tuned from OpenFlamingo.
scGPT
A foundation model for single-cell multi-omics pretrained on 10 million cells.
GPTutor
A ChatGPT-powered VSCode extension for code explanation.
Shap-E
OpenAI's conditional generative model for 3D assets producing implicit functions.
Are Emergent Abilities of LLMs a Mirage?
Stanford's critical re-examination of emergent abilities.
Interpretable ML for Science with PySR
An open-source library for practical symbolic regression in the sciences.
PMC-LLaMA
A LLaMA model fine-tuned on 4.8 million medical papers.
Distilling Step-by-Step!
A mechanism to train smaller models that outperform larger LLMs using fewer examples.
Poisoning Language Models During Instruction Tuning
Shows adversaries can poison LLMs via instruction tuning data.
Unlimiformer
Long-range Transformers with unlimited length input via external datastores.
Learning to Reason and Memorize with Self-Notes
LLMs that deviate from input to explicitly "think" and memorize.