2 papers
cs.CV2025
MoDoMoDo: Multi-Domain Data Mixtures for Multimodal LLM Reinforcement Learning
Yiqing Liang, Jielin Qiu, Wenhao Ding +7
Reinforcement Learning with Verifiable Rewards (RLVR) has recently emerged as a powerful paradigm for post-training large language models (LLMs), achieving state-of-the-art perform…
cs.CV2024
Evaluating Durability: Benchmark Insights into Multimodal Watermarking
Jielin Qiu, William Han, Xuandong Zhao +3
With the development of large models, watermarks are increasingly employed to assert copyright, verify authenticity, or monitor content distribution. As applications become more mu…