Block-triangular joint drifting enables one-step generative surrogate models for stochastic trajectories
chaumian · x · 2026-09-23
New arXiv paper (Geissler et al.) introduces block-triangular joint drifting, addressing the data problem that trajectory datasets typically give only one realized next state per observed state. A projected drift field acts on the joint distribution of consecutive states; the block-triangular architecture preserves the current-state marginal while its second component directly samples the conditional distribution of next states.
The surrogate generates stochastic trajectories with one model evaluation per time step, no auxiliary generative steps. Experiments show accurate marginal and trajectory statistics and favorable accuracy-cost tradeoffs versus deterministic, diffusion-, flow-, and distillation-based baselines.
More from Research
- 10 Claude Opus 5.5 agents prove faster shortest-path algorithm in Lean within 15 hours — ricklamers · 2026-09-23
- ImIR replaces text prompts with image instructions for all-in-one restoration — Süleyman Aslan · 2026-09-23
- Quanta Explains How Pricing Algorithms Can Drive Up Prices Without Collusion — burny_tech · 2026-09-23
- CodeMidas: Turning Raw Source Code into Executable RL Environments for Coding Agents — burny_tech · 2026-09-23
- Researchers pine for pre-2000s methodological papers with no mathiness or defensive fluff — PMinervini · 2026-09-23
- Raw LLM probabilities aren't enough for decisions — calibration matters, researchers argue — PMinervini · 2026-09-23