I looked a little into the Gzip OOD results and there seems to be another big problem: train-test overlap. E.g. DengueFilipino has the same train and test set. KirundiNews has 90% overlap… Still nice to see people revisit old ideas and the use of information theory for ML 🙂 x.com/giffmana/statu…
RESEARCH
-
Critical Analysis of ML Research Evaluation Methodology
By
–
Fun Fact : ce papier semble avoir commis des erreurs assez grave en termes d’évaluation et n’est pas aussi bon qu’attendu. Il est même pire. Donc non ça ne révolutionnera pas le monde du ML si ce n’est pour rappeler des bases de ML… Les chercheurs ont pris un top2 accuracy à
-
Synthetic Data: AI’s Solution to High-Quality Data Scarcity
By
–
High-quality data is a major limiting resource in advancing AI – it’s expensive, hard to obtain & increasingly being locked down. So what do AI companies do? My
@FT
piece on the trend of creating “synthetic data” to push forward AI development. -
NU-MCC: Multiview Compressive Coding for 3D Reconstruction
By
–
NU-MCC: Multiview Compressive Coding with Neighborhood Decoder and Repulsive UDF
— AK (@_akhaliq) 19 juillet 2023
paper page: https://t.co/fy7pygMD5w
Remarkable progress has been made in 3D reconstruction from single-view RGB-D inputs. MCC is the current state-of-the-art method in this field, which achieves… pic.twitter.com/XFYUp3ddxPNU-MCC: Multiview Compressive Coding with Neighborhood Decoder and Repulsive UDF paper page: https://
huggingface.co/papers/2307.09
112
… Remarkable progress has been made in 3D reconstruction from single-view RGB-D inputs. MCC is the current state-of-the-art method in this field, which achieves -
Biomaker CA: Growing Plant-Like Forms with Cellular Automata
By
–
Biomaker CA: a Biome Maker project using Cellular Automata paper page: https://
huggingface.co/papers/2307.09
320
… introduce Biomaker CA: a Biome Maker project using Cellular Automata (CA). In Biomaker CA, morphogenesis is a first class citizen and small seeds need to grow into plant-like -
Circuit Analysis Interpretability Scaling in Chinchilla Language Models
By
–
Does Circuit Analysis Interpretability Scale? Evidence from Multiple Choice Capabilities in Chinchilla paper page: https://
huggingface.co/papers/2307.09
458
… Circuit analysis is a promising technique for understanding the internal mechanisms of language models. However, existing analyses are done -
Llama 2 Paper Page Now Available on Hugging Face
By
–
paper page for llama 2 is up: https://
huggingface.co/papers/2307.09
288
… -
Augmenting CLIP with Improved Visio-Linguistic Reasoning
By
–
Augmenting CLIP with Improved Visio-Linguistic Reasoning paper page: https://
huggingface.co/papers/2307.09
233
… Image-text contrastive models such as CLIP are useful for a variety of downstream applications including zero-shot classification, image-text retrieval and transfer learning. However, -
ChatGPT’s Behavior Changes Over Time: March to June 2023
By
–
How is ChatGPT's behavior changing over time? paper page: https://
huggingface.co/papers/2307.09
009
… GPT-3.5 and GPT-4 are the two most widely used large language model (LLM) services. However, when and how these models are updated over time is opaque. Here, we evaluate the March 2023 and June -
OpenAI Funds Democratic Process for AI Governance Rules
By
–
Democratic Inputs to AI https://
bit.ly/42d6nDo
OpenAI has announced a grant program to fund experiments aimed at establishing a democratic process for determining the rules that AI systems should follow #AI #MachineLearning #DeepLearning #LLMs #DataScience