Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
139 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
46 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Reinforcement Fine-Tuning Enables MLLMs Learning Novel Tasks Stably (2506.23508v1)

Published 30 Jun 2025 in cs.CL and cs.AI

Abstract: Post-training algorithms such as Supervised Fine-Tuning (SFT) and Reinforcement Fine-Tuning (RFT) are widely used to adapt multimodal LLMs to downstream tasks. While effective at task adaptation, their impact on prior knowledge remains unclear. In this paper, we introduce jigsaw puzzles as a novel task absent from existing pretraining corpora and systematically study the behavior of SFT and RFT on an open-source multimodal model, Qwen2.5-VL. Our experiments reveal a sharp trade-off: SFT enables rapid task acquisition but leads to catastrophic forgetting, whereas RFT learns more slowly on novel tasks but maintains prior knowledge. We analyze this phenomenon through the lens of learning dynamics, showing that RFT reinforces correct samples that are naturally aligned with the base model's probability landscape, mitigating interference with prior knowledge. Moreover, supervised training on correct RFT-simulated rollouts allows SFT to preserve knowledge while rapidly learning new tasks. These findings suggest that data distribution, rather than algorithmic differences, plays a central role in forgetting, and highlight RFT's potential for stable continual learning in multimodal LLMs.

Summary

We haven't generated a summary for this paper yet.