SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models

• URL: http://arxiv.org/abs/2504.11468v1
• Date: Thu, 10 Apr 2025 16:54:05 GMT
• Title: SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models
• Authors: Hardy Chen, Haoqin Tu, Fali Wang, Hui Liu, Xianfeng Tang, Xinya Du, Yuyin Zhou, Cihang Xie,
• Abstract summary: This work revisits the dominant supervised fine-tuning (SFT) then reinforcement learning (RL) paradigm for training Large Vision-Language Models (LVLMs)<n>We show that SFT can significantly undermine subsequent RL by inducing pseudo reasoning paths'' imitated from expert models.<n>We introduce VLAA-Thinking, a new multimodal dataset designed to support reasoning in LVLMs.
• Score: 39.551767637896404
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This work revisits the dominant supervised fine-tuning (SFT) then reinforcement learning (RL) paradigm for training Large Vision-Language Models (LVLMs), and reveals a key finding: SFT can significantly undermine subsequent RL by inducing ``pseudo reasoning paths'' imitated from expert models. While these paths may resemble the native reasoning paths of RL models, they often involve prolonged, hesitant, less informative steps, and incorrect reasoning. To systematically study this effect, we introduce VLAA-Thinking, a new multimodal dataset designed to support reasoning in LVLMs. Constructed via a six-step pipeline involving captioning, reasoning distillation, answer rewrite and verification, VLAA-Thinking comprises high-quality, step-by-step visual reasoning traces for SFT, along with a more challenging RL split from the same data source. Using this dataset, we conduct extensive experiments comparing SFT, RL and their combinations. Results show that while SFT helps models learn reasoning formats, it often locks aligned models into imitative, rigid reasoning modes that impede further learning. In contrast, building on the Group Relative Policy Optimization (GRPO) with a novel mixed reward module integrating both perception and cognition signals, our RL approach fosters more genuine, adaptive reasoning behavior. Notably, our model VLAA-Thinker, based on Qwen2.5VL 3B, achieves top-1 performance on Open LMM Reasoning Leaderboard (https://huggingface.co/spaces/opencompass/Open_LMM_Reasoning_Leaderboard) among 4B scale LVLMs, surpassing the previous state-of-the-art by 1.8%. We hope our findings provide valuable insights in developing reasoning-capable LVLMs and can inform future research in this area.

Related papers

• Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model? [67.30809748319486]
  Reinforcement Learning with Verifiable Rewards (RLVR) has recently demonstrated notable success in enhancing the reasoning capabilities of LLMs. We re-examine this assumption by measuring the pass@textitk metric with large values of textitk to explore the reasoning capability boundary of the models. We find that the RL does emphnot, in fact, elicit fundamentally new reasoning patterns.
  arXiv  Detail & Related papers  (2025-04-18T17:59:56Z)
• Embodied-R: Collaborative Framework for Activating Embodied Spatial Reasoning in Foundation Models via Reinforcement Learning [58.86928947970342]
  Embodied-R is a framework combining large-scale Vision-Language Models for perception and small-scale Language Models for reasoning. After training on only 5k embodied video samples, Embodied-R with a 3B LM matches state-of-the-art multimodal reasoning models. Embodied-R also exhibits emergent thinking patterns such as systematic analysis and contextual integration.
  arXiv  Detail & Related papers  (2025-04-17T06:16:11Z)
• d1: Scaling Reasoning in Diffusion Large Language Models via Reinforcement Learning [31.531278643184656]
  Recent large language models (LLMs) have demonstrated strong reasoning capabilities that benefits from online reinforcement learning (RL)<n>We propose d1, a framework to adapt pre-trained dLLMs into reasoning models via a combination of supervised finetuning (SFT) and RL.<n>We find that d1 yields the best performance and significantly improves performance of a state-of-the-art dLLM.
  arXiv  Detail & Related papers  (2025-04-16T16:08:45Z)
• Exploring the Effect of Reinforcement Learning on Video Understanding: Insights from SEED-Bench-R1 [53.894789613838654]
  We introduce SEED-Bench-R1, a benchmark designed to evaluate post-training methods for MLLMs in video understanding.<n>It includes intricate real-world videos and complex everyday planning tasks in the format of multiple-choice questions.<n>Using Qwen2-VL-Instruct-7B as a base model, we compare RL with supervised fine-tuning (SFT)<n>Our detailed analysis reveals that RL enhances visual perception but often produces less coherent reasoning chains.
  arXiv  Detail & Related papers  (2025-03-31T17:55:23Z)
• OpenVLThinker: An Early Exploration to Complex Vision-Language Reasoning via Iterative Self-Improvement [91.88062410741833]
  This study investigates whether similar reasoning capabilities can be successfully integrated into large vision-language models (LVLMs)<n>We consider an approach that iteratively leverages supervised fine-tuning (SFT) on lightweight training data and Reinforcement Learning (RL) to further improve model generalization.<n>OpenVLThinker, a LVLM exhibiting consistently improved reasoning performance on challenging benchmarks such as MathVista, MathVerse, and MathVision, demonstrates the potential of our strategy for robust vision-language reasoning.
  arXiv  Detail & Related papers  (2025-03-21T17:52:43Z)
• MM-Eureka: Exploring the Frontiers of Multimodal Reasoning with Rule-based Reinforcement Learning [55.82649731348012]
  We introduce the MMK12 dataset and MM-EUREKA with 7B and 32B parameters.<n>The former is a high-quality multimodal mathematics reasoning dataset featuring diverse knowledge domains with human-verified answers and solution processes.<n>The latter is a multimodal model employing rule-based reinforcement learning utilizing online filtering and two-stage training strategy to enhance training stability.
  arXiv  Detail & Related papers  (2025-03-10T14:23:12Z)
• R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning [87.30285670315334]
  textbfR1-Searcher is a novel two-stage outcome-based RL approach designed to enhance the search capabilities of Large Language Models.<n>Our framework relies exclusively on RL, without requiring process rewards or distillation for a cold start.<n>Our experiments demonstrate that our method significantly outperforms previous strong RAG methods, even when compared to the closed-source GPT-4o-mini.
  arXiv  Detail & Related papers  (2025-03-07T17:14:44Z)
• On the Emergence of Thinking in LLMs I: Searching for the Right Intuition [34.32871896067864]
  We propose a post-training framework called Reinforcement Learning via Self-Play (RLSP)<n> RLSP involves three steps: supervised fine-tuning with human or synthetic demonstrations of the reasoning process, using an exploration reward signal to encourage diverse and efficient reasoning behaviors, and RL training with an outcome verifier to ensure correctness while preventing reward hacking.<n> Empirical studies in the math domain show that RLSP improves reasoning.
  arXiv  Detail & Related papers  (2025-02-10T18:52:04Z)
• Teaching Large Language Models to Reason with Reinforcement Learning [38.17625148525193]
  Reinforcement Learning from Human Feedback (textbfRLHF) has emerged as a dominant approach for aligning LLM outputs with human preferences. Inspired by the success of RLHF, we study the performance of multiple algorithms that learn from feedback.
  arXiv  Detail & Related papers  (2024-03-07T16:36:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.