Spider2-V: How Far Are Multimodal Agents From Automating Data Science and Engineering Workflows? — mentioned by larodi

Mon, 21 Apr 2025 21:09:36 GMT

Having done my masters on the topic of grammar-assisted text2sql let me add some additional context here: - first of all local inference can never beat cloud inference for the very simple reason that costs go down with batching. it took me two years to actually understand what batching is - the LLM tensors flowing through transformer layers has a dimension designed specifically for processing data in parallel. so no matter if you process a 1 sequence or 128 sequences the costs are the same. i've read very few articles overstating this, so bear in mind - this is the primary stopper for…

Paper and discussion history. A mention is not an endorsement.

Spider2-V: How Far Are Multimodal Agents From Automating Data Science and Engineering Workflows? — HN submission

Tue, 16 Jul 2024 12:45:01 GMT

How Far Are Multimodal Agents from Automating Data Science Workflows?

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Spider2-V: How Far Are Multimodal Agents From Automating Data Science and Engineering Workflows? · HackerPapers discussions

Spider2-V: How Far Are Multimodal Agents From Automating Data Science and Engineering Workflows? — mentioned by larodi

Spider2-V: How Far Are Multimodal Agents From Automating Data Science and Engineering Workflows? — HN submission