Trendoday

M3OPD-Reasoner: An Open Recipe for Post-Training Multimodal Reasoning with Multi-Teacher On-Policy Distillation

Multi-Teacher On-Policy Distillation (MOPD) enables a single student to absorb the skills of several domain teachers by learning from its own generated responses. We present Multimodal Model Multi-Tea

  • Upvotes8
–Rank now
#25Peak rank
1Days on list
28Score · 7d
Nov 18, 2026First seen
Rank · 7 days

About this paper

Multi-Teacher On-Policy Distillation (MOPD) enables a single student to absorb the skills of several domain teachers by learning from its own generated responses. We present Multimodal Model Multi-Teacher On-Policy Distillation Reasoner (M3OPD-Reasoner), a fully open recipe for post-training vision-language models (VLMs) over three reasoning domains: image STEM, image perception, and video. We curate two datasets, M3OPD-SFT-1.35M for supervised fine-tuning (SFT) and M3OPD-RL-193K for reinforcement learning (RL) with verifiable rewards. On these data, we compare post-training recipes that start from Qwen3.5-9B: training one model on the mixed data of all domains (MixSFT and MixRL), and…

Upvotes
8
Authors
5
Published
Nov 17, 2026

Summary and abstract excerpt via Hugging Face Papers ↗ · arXiv.

Trending history

M3OPD-Reasoner: An Open Recipe for Post-Training Multimodal Reasoning with Multi-Teacher On-Policy Distillation was first seen on Hugging Face · Daily papers on Nov 18, 2026. Since then it has appeared in 2 checks on 1 different day. Its best position was #25 of 30, reached on Nov 18, 09:28 UTC. It dropped off the list after Nov 18, 11:28 UTC.

Rank history

Position on Hugging Face · Daily papers at every check (lower is better).

#1#11#20#30 09:2809:5810:2810:5811:28 Nov 18, 09:28 UTC · #25Nov 18, 11:28 UTC · #26

Last 14 days

Best rank per day (UTC).

Nov 9today

Metric history

Platform metric as reported by Hugging Face.

0358 09:2809:5810:2810:5811:28 Nov 18, 09:28 UTC · 8Nov 18, 11:28 UTC · 8

Questions

Is M3OPD-Reasoner: An Open Recipe for Post-Training Multimodal Reasoning with Multi-Teacher On-Policy Distillation trending on HF Daily Papers right now?

Not at the moment. It was last on the list on Nov 18, 11:28 UTC, after 1 day of trending.

What is the highest rank M3OPD-Reasoner: An Open Recipe for Post-Training Multimodal Reasoning with Multi-Teacher On-Policy Distillation reached?

#25 on Hugging Face · Daily papers, on Nov 18, 09:28 UTC. Trendoday checks this list every 120 minutes.

How long has M3OPD-Reasoner: An Open Recipe for Post-Training Multimodal Reasoning with Multi-Teacher On-Policy Distillation been trending?

It was first seen on Nov 18, 2026 and has been on the list on 1 day (2 checks) since.