The paper introduces TACD, a Terminal‑Amplification‑Controlled Distillation method that trains efficient text‑to‑motion generators using on‑policy flow distillation from pretrained teachers, without requiring real‑motion data. TACD addresses a failure mode where velocity matching over‑weights errors near the denoising endpoint by tying the latest teacher query to the student’s step size, thereby bounding loss weights in clean‑motion space. Experiments on HumanML3D, KIT‑ML, HY‑Motion, and Kimodo show that TACD improves few‑step generation quality, reduces FID scores, and achieves significant speedups and memory savings compared to teacher models.
arXiv:2609.23010v1 Announce Type: new Abstract: Iterative text-to-motion generation delivers high-quality and semantically aligned motions but requires multiple network evaluations, resulting in subs...
Parametric Trajectory Distillation (PTD) is a new method for few-step video generation that allows a student model to learn teacher trajectory segments as polynomials, adapting curvature to the student’s predictive capacity. PTD improves dynamic quality and naturalness on the Wan2.1-14B model, outperforming the previous best trajectory-only method, PDD, and also enhances diversity and naturalness on the 33B MiniMax-H3 model compared to LightX2V Turbo. Human preference studies show PTD receiving 55.1% and 63.4% preference shares over PDD and LightX2V Turbo respectively.
DyMD introduces a Distribution Matching Distillation framework that adapts teacher supervision and critic fitting to preserve interaction dynamics in few-step video generation. By employing temporal affinity–conditioned re‑noise sampling and dynamics‑guided fake‑score tracking, DyMD balances motion recovery with visual quality. The method distills a 14B teacher into a 1.3B student that achieves significant gains on embodied‑video benchmarks and downstream action planning tasks.
arXiv:2608. 16333v1 Announce Type: cross Abstract: On-policy distillation (OPD) aligns a student model with a teacher's logit distribution on student-generated trajectories.
FastOPD is a framework that distills large Vision‑Language‑Action (VLA) models into lightweight versions by using on‑policy distillation with a flow map and a self‑consistency objective. The method trains a compact student to mimic the teacher’s dynamics, achieving performance close to the teacher while drastically reducing inference steps. Experiments on LIBERO, RoboTwin 2.0, and real‑robot deployments show significant latency reductions and higher success rates compared to existing few‑step distillation baselines.
On-policy distillation (OPD) aligns a student model with a teacher's logit distribution on student-generated trajectories. This approach has achieved strong empirical gains and can often surpass conve...
Efficient text-to-image generation requires both reinforcement-learning (RL)-based reward alignment and few-step distillation, yet these procedures are typically performed sequentially, increasing training cost and risking the loss of reward gains during compression. We instead take an RL-native perspective: diffusion RL already generates reward-scored finite-step trajectories, whose intermediate states provide a natural source of distillation supervision rather than a disposable byproduct of sampling.
We propose OPSD-V, an on-policy self-distillation paradigm for post-training few-step autoregressive (AR) video diffusion models. Existing few-step AR video generators can produce long videos with low latency, but still suffer from error accumulation and weakened motion dynamics during long autoregressive rollout.
arXiv:2608. 09226v1 Announce Type: cross Abstract: Efficient text-to-image generation requires both reinforcement-learning (RL)-based reward alignment and few-step distillation, yet these procedures are typically performed sequentially, increasing training cost and risking the loss of reward gains during compression.
arXiv:2602. 07339v2 Announce Type: replace Abstract: Diffusion-based trajectory planners can model multi-modal driving behavior, but their iterative denoising process introduces a latency bottleneck for real-time closed-loop deployment.
arXiv:2605. 30116v2 Announce Type: replace-cross Abstract: Distribution Matching Distillation (DMD) is a widely used paradigm for accelerating inference in few-step video diffusion models.
arXiv:2512.22802v2 Announce Type: replace-cross Abstract: Step distillation accelerates diffusion sampling by training a few-step student to imitate a many-step teacher, but distillation itself remai...