Pith. sign in

Megrez2 technical report

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.CL 1

years

2025 1

verdicts

CONDITIONAL 1

representative citing papers

Scaling Latent Reasoning via Looped Language Models

cs.CL · 2025-10-29 · conditional · novelty 5.0

A 1.4B and a 2.6B looped (weight-tied, recurrent-depth) language model trained on 7.7T tokens match or exceed several 4B–8B transformer baselines on selected reasoning benchmarks.

citing papers explorer

Showing 1 of 1 citing paper.

  • Scaling Latent Reasoning via Looped Language Models cs.CL · 2025-10-29 · conditional · none · ref 26

    A 1.4B and a 2.6B looped (weight-tied, recurrent-depth) language model trained on 7.7T tokens match or exceed several 4B–8B transformer baselines on selected reasoning benchmarks.