January 16, 2024 front

ML Newsnew | past | best | rss | submit

Stories from January 16, 2024 (UTC)

Go back a day, month, or year. Go forward a day.

1.	V*: Guided Visual Search as a Core Mechanism in Multimodal LLMs (arxiv.org)
	58 points by jonbaer on Jan 16, 2024 \| hide \| past \| pdf \| 4 comments
2.	Transformers Are Multi-State RNNs (arxiv.org)
	41 points by DreamGen on Jan 16, 2024 \| hide \| past \| pdf \| 9 comments
3.	Linear Attention Mechanism: An Efficient Attention for Semantic Segmentation (arxiv.org)
	3 points by TaurenHunter on Jan 16, 2024 \| hide \| past \| pdf \| 2 comments
4.	Generating Long Sequences with Sparse Transformers (arxiv.org)
	3 points by TaurenHunter on Jan 16, 2024 \| hide \| past \| pdf \| 1 comment
5.	Towards Conversational Diagnostic AI (arxiv.org)
	2 points by ano-ther on Jan 16, 2024 \| hide \| past \| pdf \| 1 comment
6.	Tokenizer Choice for LLM Training: Negligible or Crucial? (arxiv.org)
	2 points by sp332 on Jan 16, 2024 \| hide \| past \| pdf \| discuss
7.	FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness (arxiv.org)
	1 point by TaurenHunter on Jan 16, 2024 \| hide \| past \| pdf \| 1 comment
8.	Masked Audio Generation Using a Single Non-Autoregressive Transformer (arxiv.org)
	1 point by mvoodarla on Jan 16, 2024 \| hide \| past \| pdf \| discuss
9.	Mission: Impossible Language Models (arxiv.org)
	1 point by todsacerdoti on Jan 16, 2024 \| hide \| past \| pdf \| discuss