Papers

Filtered to open-ended domains · 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

Flux-OPD: On-Policy Distillation with Evolving Contexts

40 upvotes · 30 JUL 2026 · Yuran Wang, Zekun Wang, Bohan Zeng et al.

This paper proposes a new method for training large language models in open-ended domains, using evolving contexts as in-training supervision to capture task preferences. Practitioners may care about this approach because it can lead to better performance on open-ended tasks.

on-policy distillationevolving contextsopen-ended domainsteacher supervisionreverse KL objective