Metraipolis › archive › dc_21663ed08bb6

OpenESM: Energy-Steered Models Are Scalable Foundation Learners — arXiv:2610.33005

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.33005
License (as archived)
CC0-1.0
Archived
2026-10-27T08:10:39.565Z
SHA-256 of the archived text
7b4e3f185e3a663ff2bc1fc8be19eefb35b2be0051fa2949ba680c6a5ebab6f5
Stable URL of this page
https://metraipolis.com/documento/dc_21663ed08bb6

How to cite

OpenESM: Energy-Steered Models Are Scalable Foundation Learners — arXiv:2610.33005 — arXiv (en), https://arxiv.org/abs/2610.33005 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_21663ed08bb6 (Metraipolis archive dc_21663ed08bb6, sha256 7b4e3f185e3a663ff2bc1fc8be19eefb35b2be0051fa2949ba680c6a5ebab6f5)
BibTeX
@misc{dc21663ed08bb6,
  title = {OpenESM: Energy-Steered Models Are Scalable Foundation Learners — arXiv:2610.33005},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.33005},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_21663ed08bb6; sha256 7b4e3f185e3a663ff2bc1fc8be19eefb35b2be0051fa2949ba680c6a5ebab6f5},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.33005. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Energy-based models have shown promising properties for domain-specific tasks but remain challenging in modeling general-purpose scenarios. To bridge this gap, we design energy-steered models (ESMs) for foundational language modeling. ESMs integrate energy steering and token generation within a single architecture to leverage the energy-guided search to refine token generation. Specifically, ESMs first optimize a latent state over the energy landscape, then leverages the refined latent state for token generation. By performing such energy-guided pre-training on large-scale corpora, ESMs learn generally effective energy landscape where favorable tokens correspond to lower energy values. To explore the scaling behavior of ESMs, we pre-train ESMs on three large-scale corpora, then evaluate across 26 downstream tasks spanning a broad range of domains. Our results demonstrate that ESMs have promising scaling behaviors with increasing model size and training data, and outperform GPTs on most downstream tasks. These findings highlight ESMs as a promising architecture for large-scale pre-training and general purpose problem solving. We fully release the model weights and training infrastructure to enable the community to completely reproduce and extend our results. GitHub: this https URL HuggingFace: this https URL

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.33005 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-27T07:56:00.177Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).