Tootfinder

Opt-in global Mastodon full text search. Join the index!

No exact results. Similar results found.
@arXiv_csLG_bot@mastoxiv.page
2025-09-30 14:41:01

Advantage Weighted Matching: Aligning RL with Pretraining in Diffusion Models
Shuchen Xue, Chongjian Ge, Shilong Zhang, Yichen Li, Zhi-Ming Ma
arxiv.org/abs/2509.25050

Advantage Weighted Matching: Aligning RL with Pretraining in Diffusion Models
Reinforcement Learning (RL) has emerged as a central paradigm for advancing Large Language Models (LLMs), where pre-training and RL post-training share the same log-likelihood formulation. In contrast, recent RL approaches for diffusion models, most notably Denoising Diffusion Policy Optimization (DDPO), optimize an objective different from the pretraining objectives--score/flow matching loss. In this work, we establish a novel theoretical analysis: DDPO is an implicit form of score/flow matchi…

@arXiv_csSD_bot@mastoxiv.page
2025-09-24 09:42:54

MECap-R1: Emotion-aware Policy with Reinforcement Learning for Multimodal Emotion Captioning
Haoqin Sun, Chenyang Lyu, Xiangyu Kong, Shiwan Zhao, Jiaming Zhou, Hui Wang, Aobo Kong, Jinghua Zhao, Longyue Wang, Weihua Luo, Kaifu Zhang, Yong Qin
arxiv.org/abs/2509.18729

MECap-R1: Emotion-aware Policy with Reinforcement Learning for Multimodal Emotion Captioning
Speech Emotion Captioning (SEC) has emerged as a notable research direction. The inherent complexity of emotional content in human speech makes it challenging for traditional discrete classification methods to provide an adequate representation. Consequently, utilizing natural language to describe speech emotions presents a novel avenue for more effectively capturing and expressing affect. In this paper, we propose MECap-R1, a pioneering emotion-aware policy with reinforcement learning for mult…

@arXiv_csCL_bot@mastoxiv.page
2025-08-15 10:10:02

Making Qwen3 Think in Korean with Reinforcement Learning
Jungyup Lee, Jemin Kim, Sang Park, SeungJae Lee
arxiv.org/abs/2508.10355 arxiv.org…

Making Qwen3 Think in Korean with Reinforcement Learning
We present a two-stage fine-tuning approach to make the large language model Qwen3 14B "think" natively in Korean. In the first stage, supervised fine-tuning (SFT) on a high-quality Korean reasoning dataset establishes a strong foundation in Korean logical reasoning, yielding notable improvements in Korean-language tasks and even some gains in general reasoning ability. In the second stage, we employ reinforcement learning with a customized Group Relative Policy Optimization (GRPO) algorithm to…