When Less is More: Investigating Data Pruning for Pretraining LLMs at Scale https://
cohere.com/research/paper
s/when-less-is-more-investigating-data-pruning-for-pretraining-llms-at-scale-2023-09-08
… @maxdoesresearch @ahmetustun89 @luizapzbn @W4ngatang @mziizm @sarahookr
INNOVATION
-
Data Pruning Strategies for Large Language Model Pretraining
By
–
-
Mixture of Experts Parameter Efficiency for Instruction Tuning
By
–
Pushing Mixture of Experts to the Limit: Extremely Parameter Efficient MoE for Instruction Tuning https://
cohere.com/research/paper
s/pushing-mixture-of-experts-to-the-limit-extremely-parameter-efficient-moe-for-instruction-tuning-2023-09-11
… @tedzadouri Ahmet Üstün @aahmadian_ @beyzaermis @acyr_l @sarahookr -

RAG Reranking: Enhancing Retrieval with Pinecone Cohere
By
–
RAG with reranking – leveraging @pinecone and @cohere Reranking is a retrieval technique that performs an additional step on top of retrieved results This step uses a separate model to rerank the results, making sure the most relevant ones surface to the top @jamescalam
-

LangChain Templates GitHub Project Launches Community Contribution Initiative
By
–
Call for templates We've started a GitHub project to allow people to: Add or upvote ideas for LangChain Templates
Assign one of the template ideas to themselves and take a stab at building it Lots of cool ideas on there already – check it out, add some more -
Google Research Event Showcases AI Climate Education Healthcare Innovations
By
–
Research@ NYC has come to a close! The event highlighted how researchers at Google are exploring innovations in climate, education, generative AI, health, & more — important work they're doing at Google to help define the technology of today & tomorrow.
-
Advanced Math Solves Language Distance and Name Schema Problems
By
–
Extraordinary that sufficiently advanced math manages to cache obscure org charts while also solving distance-in-pronunciation for all words and languages simultaneously while also, no big deal, solving the problem of the human name schema that has bedeviled every program ever.
-
Exciting New AI Paradigm Developments and Opportunities
By
–
It is! Very exciting and fun to try though, especially with the new AI paradigm.
-

SDXL Fine-Tuned on Toy Story Characters Generates Quirky Images
By
–
I trained SDXL on the slightly weird looking people from Toy Story (1995). Inspired by @skirano
’s really good Toy Story tune. Just more weird. https://
replicate.com/fofr/sdxl-toy-
story-people
… -
Podcast with Logan Bartlett on AI and Innovation Ideas
By
–
check out my recent podcast with @loganbartlett !
— Alexandr Wang (@alexandr_wang) 3 novembre 2023
he prepared extremely well. we talked about nearly everything AI and some of my best ideas https://t.co/u3uUgND1qZcheck out my recent podcast with @loganbartlett ! he prepared extremely well. we talked about nearly everything AI and some of my best ideas
-
Multimodal AI, Synthetic Data, and Enterprise AI Readiness Trends
By
–
I could talk for hours about the future of AI, but right now, I’m really looking at multimodal AI, synthetic data, companion AI, GPU shortage mitigation, hyperpersonalization, and AI enterprise readiness trends (from training to LLM ops to quick deploy templates).