# Classifier-Free Guidance

Human motion generation has mostly been steered by naming an action or a place to move; StepControl instead takes only a future left/right foot-contact schedule, with no target root or body poses and no semantic prompt. It treats contacts as explicit temporal events, injects them through dedicated cross-attention with classifier-free guidance, and adds a stochastic mixture noise schedule and warmup for stable long-horizon autoregressive generation. Experiments report that it follows prescribed contact timing more accurately than adapting existing spatially guided generators to contact constraints, keeps contact control over long continuous rollouts, and responds to edited schedules such as cadence changes, stop-and-go pauses, limping gaits and bilateral jumping.

Human motion generation has mostly been steered by naming an action or a place to move; StepControl instead takes only a future left/right foot-contact schedule, with no target root or body poses and no semantic prompt. It treats contacts as explicit temporal events, injects them through dedicated cross-attention with classifier-free guidance, and adds a stochastic mixture noise schedule and warmup for stable long-horizon autoregressive generation. Experiments report that it follows prescribed contact timing more accurately than adapting existing spatially guided generators to contact constraints, keeps contact control over long continuous rollouts, and responds to edited schedules such as cadence changes, stop-and-go pauses, limping gaits and bilateral jumping.

Decoupling guided sampling from the optimization anchor lets a video flow model keep the gains of guided exploration under CFG-free single-branch inference while preserving the original semantics of inference-time guidance.

Decoupling guided sampling from the optimization anchor lets a video flow model keep the gains of guided exploration under CFG-free single-branch inference while preserving the original semantics of inference-time guidance.

Classifier-free guidance for flow-matching models has applied one shared scale to all latent tokens, even though their velocity predictions evolve differently during sampling. TrajCFG maps historical changes in guided velocity direction to bounded per-token scales, giving stronger guidance to larger directional changes and weaker guidance to more consistent directions, and fuses adjacent-step with interval-normalized longer-span feedback without extra model evaluations. Across text-to-video, image-to-video, text-to-audio-video, text-to-image and image-to-3D generation it improves on base samplers; on text-to-video it raises VBench Total by 0.30 to 0.75 points over the strongest evaluated baseline on each of three backbones.

Classifier-free guidance for flow-matching models has applied one shared scale to all latent tokens, even though their velocity predictions evolve differently during sampling. TrajCFG maps historical changes in guided velocity direction to bounded per-token scales, giving stronger guidance to larger directional changes and weaker guidance to more consistent directions, and fuses adjacent-step with interval-normalized longer-span feedback without extra model evaluations. Across text-to-video, image-to-video, text-to-audio-video, text-to-image and image-to-3D generation it improves on base samplers; on text-to-video it raises VBench Total by 0.30 to 0.75 points over the strongest evaluated baseline on each of three backbones.

Subsurface fracture networks were previously sampled fracture by fracture from prescribed statistics, which made sparse well observations hard to enforce. Here 2D and 3D networks are represented as binary occupancy fields, compressed by a variational autoencoder into a compact latent space, and learned by a diffusion model, with well observations injected through a learned conditioning encoder, classifier-free guidance, and diffusion posterior sampling. The 2D conditional model satisfies 99.6% of prescribed well observations, while the native 3D volumetric field satisfies 84.2% of observed well voxels while keeping fracture volume fraction close to the reference ensemble.

Subsurface fracture networks were previously sampled fracture by fracture from prescribed statistics, which made sparse well observations hard to enforce. Here 2D and 3D networks are represented as binary occupancy fields, compressed by a variational autoencoder into a compact latent space, and learned by a diffusion model, with well observations injected through a learned conditioning encoder, classifier-free guidance, and diffusion posterior sampling. The 2D conditional model satisfies 99.6% of prescribed well observations, while the native 3D volumetric field satisfies 84.2% of observed well voxels while keeping fracture volume fraction close to the reference ensemble.