Apple researcher lands two NeurIPS 2026 papers on normalizing flows, including Normalizing Trajectory Models
thoma_gu · x · 2026-10-06
Apple MLR researcher thomagu announced that both STARFlow2 and Normalizing Trajectory Models (NTM) were accepted to NeurIPS 2026.
NTM tackles a core question: can fast generative models still be likelihood-based? It leverages normalizing flows to achieve high-quality few-step generation with exact trajectory likelihood, a step forward for scalable flow-based generation.
The author will also attend COLM 2026 in San Francisco (Oct 6–9) to chat about LLMs and world models.
More from Multimodal
- AI-generated video is so funny netizens say the compute was worth it — hexiang · 2026-10-06
- Midjourney + Threejs + Seedance workflow for multi-angle AI cinematography — Ror_Fly · 2026-10-06
- Suno turns pictures into songs — and it even recognized the Gram-Schmidt meme — anderssandberg · 2026-10-06
- SemanTok: 49M autoregressive video model beats SOTA rivals 47x its size — CSProfKGD · 2026-10-06
- Magnific teases October 8 launch, simple prompts already yield impressive results — aziz4ai · 2026-10-06
- Gaussian GRPO normalizes multimodal RL reward distributions, boosting OpenVLThinker v2 — kaiwei_chang · 2026-10-06