Papers

Filtered to model efficiency · 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

Language Models Can Control Their Own Attention

49 upvotes · 2 SEP 2026 · Namgyu Ho, Huzama Ahmad, Woosung Koh et al.

This paper introduces a new attention mechanism, Declarative Attention (DA), that allows language models to more efficiently control their attention by specifying where they need to focus during generation, rather than scanning the entire context. Practitioners might care because this could lead to significant reductions in computation and memory usage, making large language models more practical for real-world applications.

language modelsattention mechanismssparse attentioncontextual generationmodel efficiency