RVM skips diffusion likelihoods: velocity matching beats GRPO at far lower cost

Scaling Reinforcement Learning for Diffusion Models via Velocity Matching

Jaemoo Choi, Wei Guo, Yuchen Zhu, Arash Vahdat, Molei Tao, Julius Berner, Yongxin Chen

cs.CV, cs.LG

2026-08-25

RVM fine-tunes diffusion models by reward-weighted velocity regression, no likelihoods. Wan2.1-1.3B reaches VBench 84.13 at 525 GPU-h.

What problem this solves

Reward fine-tuning for diffusion models still arrives wearing language-model clothes. PPO and GRPO need a likelihood. Autoregressive models have one, token by token. Diffusion models do not: the marginal probability of a finished sample is intractable. Trajectory methods fake it with per-step Gaussian transitions, which forces SDE sampling and storage of the whole denoising path, then dumps a single terminal reward onto a chain of random intermediate states. ELBO methods drop the path and score the endpoint, but they still estimate a policy ratio.

Unroll an ELBO policy gradient and the parameter update is already reward-weighted velocity regression. Georgia Tech and NVIDIA cut the likelihood layer and write the update in the representation the model was trained in: reward-based velocity matching (RVM).

Method

Flow matching already regresses a velocity field. Clean sample x0 and noise ε interpolate to xt; the target is v = ε − x0. RVM does four things:

No policy ratio, no clipping, no stored trajectory. Video runs use a 16-step deterministic ODE, no CFG, and default β=0, so the update is pure reward-weighted regression. Wan2.1-T2V-1.3B is LoRA-tuned at rank 128 for 90 epochs on 8×H100.

RAM and DiffusionNFT sit inside the same gradient. RAM is on-policy RVM with a reference anchor and β=1. DiffusionNFT uses an EMA anchor and maps a [0, 1] reward onto a signed weight. The algebra of the loss barely moves the numbers. Reward shaping and the anchor do.

Video makes that concrete. VideoAlign and HPSv3 will happily reward a clean, nearly frozen clip. The fix is a dynamic-tracking (DT) reward: RAFT optical flow on the fastest 5% of pixels, compared against a resolution-aware threshold. The I2V variant subtracts median flow and only scores mid-range foreground motion, so a drifting background earns nothing. Default mix: text alignment 1.5, motion quality 1.0, HPSv3 0.2, DT 0.7.

Results

Wan2.1-T2V-1.3B on VBench, one video per prompt:

MethodDynamic DegreeOverallGPU-h (8×H100)
Base, no CFG54.1776.02n/a
Base, CFG=565.2883.10n/a
FlowGRPO55.5675.911,159
DanceGRPO†58.3379.466,171
TaRoS-72B†58.3380.566,171
DiffusionNFT63.8982.95n/a
RAM61.1181.95n/a
RVM75.0084.13525

†DanceGRPO / TaRoS numbers are cited under a different protocol (CFG, 50-step SDE, five videos per prompt). Against FlowGRPO the recipe is 2.2× cheaper; against the DanceGRPO / TaRoS protocol, 11.8×. The gap is a 16-step CFG-free ODE plus a single noised state per update.

Drop DT and dynamic degree collapses to 5.56, Overall 80.39. Add it and the scores jump to 75.00 / 84.13. Motion is a reward problem.

On SkyReels-I2V, FlowGRPO drags Overall from 81.68 to 77.97. RVM reaches 86.27 with dynamic degree 72.36 (base 64.63). NFT 86.16 and RAM 86.61 sit in the same cluster. On SD3.5-M OCR, RVM hits OCR 0.95 and PickScore 23.03, level with or slightly above the ELBO method PEPG (0.94 / 22.93).

Few-step sampling holds up. The CFG base falls from 83.10 at 16 steps to 73.62 at 5 and 64.39 at 4. CFG-free RVM loses 0.43 and 1.83; four-step RVM still matches the 16-step CFG base. Unanchored training wins on Total. Anchoring to a CFG=5 reference lifts Semantic from 76.29 to 78.48. RVM Semantic 76.28 still trails the CFG base at 80.64; Overall is carried by quality and motion.

Why it matters

Video diffusion post-training does not need trajectory likelihoods. The velocity field is the native interface, and reward-weighted regression plugs into a deterministic ODE. RVM, RAM, and DiffusionNFT land in a tight band, so a new loss functional is a weak use of time. Reward design is not. If motion is not scored, preference models will freeze the clip.

The claim is a change of coordinates: pose diffusion reward fine-tuning in velocity space. RVM does not add a sampler or a backbone. The increment is the recipe and the motion reward.

Limitations

There is no standalone limitations section. The 11.8× cost figure mixes iteration count and sampler settings with the algorithm, so it is not a same-protocol speedup. Main tables use one video per prompt and report no variance. Default video runs set β=0, which sits awkwardly next to the "anchored unification" story. The fixed-point remark is honest: the learned field need not equal the conditional velocity of its own endpoint distribution. DT depends on RAFT and hand-set thresholds; the I2V thresholds come from human labels on earlier fine-tuning runs. The only named follow-up is autoregressive video, with no experiment.

Terms

Source

What people are saying

Related papers

All paper explainers