Papers

Filtered to divergence-based optimization · clear filter

Browse by term

continual learning 64reinforcement learning 34large language models 17benchmarking 12vision-language models 10generative models 8language models 8video generation 7multimodal models 6natural language processing 6robotics 6world models 6benchmarks 5diffusion models 5on-policy distillation 5policy optimization 5scalability 5self-distillation 5vision-language-action models 5autoregressive models 4computer vision 4diffusion transformers 4LLMs 4multimodal large language models 4verifiable rewards 4attention mechanisms 3embodied intelligence 3image editing 3long-term memory 3multimodal learning 3

Matching papers

Predictive Divergence Masks for LLM RL

9 upvotes · 12 JUL 2026 · Xiangxin Zhou, Jiarui Yao, Penghui Qi et al.

This paper proposes a new method to improve reinforcement learning for large language models by using a predictive divergence mask, which helps stabilize off-policy updates. Practitioners caring about improving the stability and performance of LLM-based reinforcement learning might find this approach useful.

reinforcement learninglarge language modelstrust-region methodspredictive modelsdivergence-based optimization