CVApr 23, 2025

Skywork R1V2: Multimodal Hybrid Reinforcement Learning for Reasoning

arXiv:2504.16656v438 citationsh-index: 19Has Code
Originality Highly original
AI Analysis

This addresses the problem of developing more capable and generalizable multimodal reasoning systems for AI researchers and practitioners, representing a major leap forward from its predecessor but still incremental in the broader field.

The paper tackles the challenge of balancing sophisticated reasoning with broad generalization in multimodal models by introducing Skywork R1V2, a hybrid reinforcement learning model that achieves benchmark-leading performances such as 62.6 on OlympiadBench and 78.9 on AIME2024.

We present Skywork R1V2, a next-generation multimodal reasoning model and a major leap forward from its predecessor, Skywork R1V. At its core, R1V2 introduces a hybrid reinforcement learning paradigm that jointly leverages the Mixed Preference Optimization (MPO) and the Group Relative Policy Optimization (GRPO), which harmonizes reward-model guidance with rule-based strategies, thereby addressing the long-standing challenge of balancing sophisticated reasoning capabilities with broad generalization. To further enhance training efficiency, we propose the Selective Sample Buffer (SSB) mechanism, which effectively addresses the vanishing advantages dilemma inherent in GRPO by prioritizing high-value samples throughout the optimization process. Notably, we observe that excessive reinforcement signals can induce visual hallucinations--a phenomenon we systematically monitor and mitigate through calibrated reward thresholds throughout the training process. Empirical results affirm the exceptional capability of R1V2, with benchmark-leading performances such as 62.6 on OlympiadBench, 78.9 on AIME2024, 63.6 on LiveCodeBench, and 73.6 on MMMU. These results underscore R1V2's superiority over existing open-source models and demonstrate significant progress in closing the performance gap with premier proprietary systems, including Gemini 2.5 and OpenAI-o4-mini. The Skywork R1V2 model weights have been publicly released to promote openness and reproducibility https://huggingface.co/Skywork/Skywork-R1V2-38B.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes