Metraipolis › archive › dc_8ea0cbaeeead

MeSD: Multi-Evidence Self-Distillation for VideoLLM — arXiv:2610.06342

Source: arXiv
Original: https://arxiv.org/abs/2610.06342
License (as archived): CC0-1.0
Archived: 2026-10-06T05:27:36.677Z
SHA-256 of the archived text: 30b582d18413d8adad21a89779e9dbf7bc2844ab208cb4c6d4bd20c588c4588b
Stable URL of this page: https://metraipolis.com/documento/dc_8ea0cbaeeead

How to cite

MeSD: Multi-Evidence Self-Distillation for VideoLLM — arXiv:2610.06342 — arXiv, https://arxiv.org/abs/2610.06342 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8ea0cbaeeead (Metraipolis archive dc_8ea0cbaeeead, sha256 30b582d18413d8adad21a89779e9dbf7bc2844ab208cb4c6d4bd20c588c4588b)

BibTeX

@misc{dc8ea0cbaeeead,
  title = {MeSD: Multi-Evidence Self-Distillation for VideoLLM — arXiv:2610.06342},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.06342},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8ea0cbaeeead; sha256 30b582d18413d8adad21a89779e9dbf7bc2844ab208cb4c6d4bd20c588c4588b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.06342. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

While reinforcement learning with verifiable rewards provides reliable outcome supervision for VideoLLMs, sequence-level rewards offer limited token-level guidance. On-policy self-distillation addresses this limitation by conditioning a self-teacher on privileged information to provide dense token-level supervision. However, aggregating heterogeneous evidence within a single teacher context obscures cross-evidence agreement and conflict. A further challenge lies in determining whether teacher guidance should refine reward-based updates or provide corrective supervision for failed trajectories. To address these issues, we propose MeSD, a multi-evidence self-distillation framework for VideoLLMs. MeSD constructs three evidence-conditioned teachers with shared parameters, using the ground-truth answer as a common semantic context while separately incorporating temporal and spatial evidence. Given the same student-generated prefixes, MeSD evaluates evidence-specific preferences relative to the Answer Teacher and fuses teacher-common preferences with gated teacher-specific residuals. Furthermore, MeSD introduces Verification-Guided Optimization to classify trajectories as Success, Failure, or Indeterminate. For Success and Indeterminate trajectories, MeSD refines token-level advantage magnitudes while preserving reward-derived signs. For verified failure trajectories that contain the required evidence, MeSD applies failure-conditioned distillation, using reverse-KL correction toward the fused distribution. Experiments on multiple video benchmarks demonstrate consistent gains over reinforcement learning and self-distillation baselines.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.06342 — 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 2026-10-06T05:24:06.146Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).