跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 2026-10-22AI 評分49

MMVistaReason:邁向多模態推理的開放數據與後訓練方案

MMVistaReason: Toward Open-Data and Post-Training Recipes for Multimodal Reasoning

AI 導讀

MMVistaReason 提出開放數據後訓練方案,結合難度感知蒸餾、強化學習及多教師訓練,以提升多模態推理能力。在 15 項基準測試中,MVR-4B 平均得分為 72.8,使用的樣本比 MMFineReason 少約 70%,並勝過 Qwen3.5-9B (Instruct) 和 MMFineReason-8B。

正文

Published on Oct 22

·

Submitted by

JueJue

on Oct 26

Authors:

,

,

,

,

,

,

,

,

Abstract

MMVistaReason improves open multimodal reasoning through structured data construction, difficulty-aware distillation, and specialized reinforcement learning integration.

Open multimodal reasoning models have benefited from large-scale reasoning supervision, yet reliable post-training remains challenging due to uneven data quality, inefficient supervision construction, imbalanced difficulty, and cross-domain interference. We introduce MMVistaReason (MVR), an open-data post-training recipe with three components: (1) broader capability coverage across complementary Analytical and Real-World reasoning groups, emphasizing structured reasoning versus visual perception and spatial grounding; (2) efficient SFT and RL data construction, standardizing heterogeneous open data through staged cleaning and annotation, combining difficulty-aware cascaded teacher distillation with answer-likelihood-based trajectory selection to construct MVR-SFT-528K, and applying scale-specific frontier filtering for MVR-RL-63K; and (3) specialize-then-integrate training, which trains complementary RL experts and consolidates their capabilities through multi-teacher on-policy distillation (MOPD). Our analyses reveal a capacity-dependent interaction between supervision difficulty, trajectory quality, and model capacity: smaller students benefit more from selected supervision, while larger students are robust to trajectory variation and mixed-domain interference. Mixed-domain RL introduces benchmark-level negative transfer, whereas MOPD provides consistent capability integration, with the preferred KL direction varying across model scales. Across 15 multimodal benchmarks, MVR-4B achieves an average score of 72.8, outperforming Qwen3.5-9B (Instruct) and MMFineReason-8B while using about 70% fewer samples than MMFineReason. Scaling to 9B improves the average to 74.4, surpassing Qwen3.5-35B-A3B (Instruct). Overall, MMVistaReason demonstrates that systematic open-data construction and capacity-aware post-training provide a practical and scalable path toward reliable multimodal reasoning.

View arXiv page View PDF GitHub 2 Add to collection

Get this paper in your agent:

hf papers read 2610.01352

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2610.01352 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2610.01352 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2610.01352 in a Space README.md to link it from this page.

Collections including this paper 2

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co