Pith. sign in

Torchtitan: One-stop pytorch native solution for production ready LLM pretraining

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

fields

cs.CL 1 cs.CV 1

years

2026 1 2025 1

verdicts

CONDITIONAL 2

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 2 of 2 citing papers.

  • Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence cs.CV · 2026-07-08 · conditional · none · ref 55

    LingBot-Video is an open-source MoE video foundation model for embodied intelligence that scales to 120B parameters, integrates robot data, and uses multi-dimensional RL to improve physical plausibility.

  • Scaling Latent Reasoning via Looped Language Models cs.CL · 2025-10-29 · conditional · none · ref 49

    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.