content type videopublished September 23, 2025
Apple Workshop on Natural Language and Interactive Systems 2025: Speculative Streaming: Fast LLM Inference Without Auxiliary Models
AuthorsIrina Belousova (Apple)
Related readings and updates.
Normalizing Trajectory Models
October 8, 2026research area Computer Vision, research area Methods and Algorithmsconference NeurIPS
Diffusion-based models decompose sampling into many small Gaussian denoising steps, an assumption that breaks down when generation is compressed to a few coarse transitions. Existing few-step methods address this through distillation, consistency training, or adversarial objectives, but sacrifice the likelihood framework in the process. We introduce Normalizing Trajectory Models (NTM), which models each reverse step as an expressive conditional…
RISED: Rubrics for Agentic Multi-Environment Selection and Self-Distillation
October 6, 2026research area Data Science and Annotation, research area Speech and Natural Language Processing
Training a single LLM agent jointly across diverse interactive environments has attracted increasing attention as a route to generalist agents. Existing curriculum and data-selection strategies often allocate training at the environment level or prioritize local reward-based signals, without explicitly considering relationships between current rollouts across environments for prompt-group selection. Meanwhile, as environments are learned at…
Discover opportunities in Machine Learning.
Our research in machine learning breaks new ground every day.