Scaling Latent Reasoning via Looped Language Models · HackerPapers discussions

Scaling Latent Reasoning via Looped Language Models — mentioned by tedd4u

Mon, 19 Oct 2026 21:17:22 GMT

There are a huge number of citations about looping on this Ouro page [1]. Ouro is an open looped LLM with a very instructive paper at [2] (also containing references to lots of helpful papers). Basically they get these four results from looping: • Parameter efficiency. 1.4B and 2.6B parameter looping Ouro models match 4B and 8B transformers on most benchmarks. • Adaptive computation. Looping is trained in a novel way to avoid exiting too early or too late. • Reasons to use looping. Looping does not increase raw knowledge storage (approximately 2 bits per parameter for looped and non-looped…

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

Scaling Latent Reasoning via Looped Language Models — mentioned by skerit

Tue, 10 Mar 2026 16:59:04 GMT

This is kind of what LoopLM is doing, no? https://arxiv.org/abs/2510.25741

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

Scaling Latent Reasoning via Looped Language Models — HN submission

Sat, 03 Jan 2026 21:34:33 GMT

Scaling Latent Reasoning via Looped Language Models

84 points; 15 discussion replies on HN. Paper and source history. A submission is not an endorsement.