Papers

Filtered to concept-level objectives · clear filter

Browse by term

continual learning 83reinforcement learning 50large language models 12benchmarking 11benchmarks 11language models 11vision-language models 11robotics 7natural language processing 6world models 6generative models 5recursive self-improvement 5attention mechanisms 4diffusion Transformers 4multi-agent systems 4multimodal learning 4multimodal models 4on-policy distillation 4self-distillation 4self-supervised learning 4transformers 4video generation 4vision-language-action models 4agent-based systems 3agentic models 3agentic search 3autonomous systems 3coding agents 3diffusion models 3image generation 3

Matching papers

NCP-ArchPreview Technical Report: Moving towards Latent Space Language Models through Next Concept Prediction

304 upvotes · 9 SEP 2026 · NCP Team, Jiaqi Cao, Chiyu Chen et al.

This paper introduces a new type of language model called NCP-ArchPreview that can generate text by predicting both individual tokens and larger concepts, and how this approach can improve performance. Practitioners might care about this because it could lead to better language models that can handle more complex tasks.

latent-space language modelsnext concept predictioncontinual learningautoregressive pretrainingconcept-level objectives