NeurIPS 2026 Spotlight: WTF Flow Maps Enable Simulation-Free RL Finetuning for Diffusion Models
sedielem · x · 2026-10-15
A NeurIPS 2026 Spotlight paper tackles the costly rollouts that RL finetuning of diffusion and flow models usually requires. The proposed Wasserstein-Tilted Flow Maps (WTF) enable simulation-free RL finetuning, replacing the standard KL regularization with a transport-based alternative.
Related event: WTF Flow Maps Enable Simulation-Free RL Fine-Tuning, 280x Cheaper(3 posts)→
More from Research
- Intern-S2 credited in math paper as post-trained Qwen 3.5-397B, sparking AI-for-math debate — teortaxesTex · 2026-10-15
- DecisionRobust benchmark stress-tests 30 decision models against prompt injection and perturbations — Yifan Lan · 2026-10-15
- Continuum Attention: continuous integration beats softmax attention in all paired comparisons — Afshin Khadangi · 2026-10-15
- Microsoft's LensErase: a foundation model for erasing anything from images — microsoft · 2026-10-15
- LatentLoop: asymmetric compute for looped MoE saves 19% FLOPs — Zefeng He · 2026-10-15
- SJTU: VLA skill recombination fails at the "start state gap" — AutoLab-SJTU · 2026-10-15