Cache or Denoise Less? Residual Reuse in a Flow-Matching World Action Model
Organizations: Independent Researcher
Abstract
Flow-matching robot policies generate each action chunk through repeated network evaluations, one per denoising step. Cross-cycle caches such as Cache reuse computation from earlier replanning calls, but whether they beat simply taking fewer steps is unclear. We compare the two in Fast-WAM, a 6B-parameter world action model, on LIBERO-Goal. Two uncached steps keep the success of ten: on all 500 initial states they are non-inferior within two percentage points, for one checkpoint and noise seed. Under PyTorch's default compile mode, they also cut a replanning call on an RTX A6000 from 202 to 92 ms. This leaves little room for caching. A cache that keeps two fresh steps cannot be faster than two uncached steps: every call still encodes the images, runs the video expert and computes those two steps. Caching the first of two steps, refreshed every fourth call, saves at most 11--14% of a call by our cost model. Cached policies are also fragile. Their losses tracked the share of the flow path the cached steps cover: under Fast-WAM's current time shift, Cache's eight cached steps cover 80% of the path instead of 44%, and the cached policy succeeds on 63% of states against 95% uncached. Resampling the noise on every call cost caches covering 60% or more of the path 14--40 points. These results argue for fewer-step baselines and for testing reuse under the deployed sampler and noise settings. We release our evaluation harness, logs and a checklist.
Figures & tables
| path cached (%) | success (%) | mean latency (ms) | p95 latency (ms) | ||||||
| Configuration | IDM | orig. | IDM | orig. | IDM | orig. | IDM | orig. | |
| Uncached | 1 | – | – | 88 | 93 | 81 | 81 | 82 | 82 |
| Uncached | 2 | – | – | 95 | 96 | 94 | 92 | 96 | 95 |
| Uncached | 4 | – | – | 95 | 95 | 119 | 118 | 125 | 122 |
| Uncached | 10 | – | – | 95 | 95 | 202 | 202 | 209 | 209 |
| Cache, | 4 | 50 | 17 | 96 | 95 | 104 | 105 | 123 | 124 |
Appendix figures & tables9 assets
Supplementary material from the paper’s appendix.
Appendix
| Ckpt. | Contrast (A vs. B) | A (%) | B (%) | A B | Tango 90% | Holm | |
|---|---|---|---|---|---|---|---|
| IDM | 2 vs. 10 steps | 95 | 95 | 0 | 1.00 | 1.00 | |
| IDM | 2 steps vs. cache | 95 | 63 | +32 | |||
| IDM | 2 steps vs. attenuated | 95 | 81 | +14 | 0.0026 | 0.023 | |
| IDM | 2 steps vs. cache | 95 | 97 | -2 | 0.69 | 1.00 | |
| IDM | 2 steps vs. 4-step cache | 95 | 96 | -1 | 1.00 | 1.00 | |
| IDM | attenuated vs. plain | 81 | 63 | +18 | 0.0021 | 0.021 |
| Ckpt. | cached | share (%) | fresh | fixed (%) | fresh (%) | ||
|---|---|---|---|---|---|---|---|
| IDM | 1 | 0 | 0 | – | 96 | 96 | 1.00 |
| IDM | 1 | 3 | 30 | 0.70 | 94 | – | – |
| IDM | 1 | 4 | 40 | 0.60 | 94 | 96 | 1.00 |
| IDM | 1 | 5 | 50 | 0.50 | 98 | – | – |
| IDM | 1 | 6 | 60 | 0.40 | 96 | 82 | 0.039 |
| IDM | 1 | 7 | 70 | 0.30 | 88 | 62 | 0.0023 |
| Condition | Ckpt. | states | 10 steps | 2 steps | 2 10, Tango 90% | 1 step | cache |
|---|---|---|---|---|---|---|---|
| LIBERO-Goal, all states | IDM | 500 | 96.4 | 96.6 | – | – | |
| Camera jitter 1.5 cm | IDM | 50 | 66 | 66 | 68 | 24 | |
| Camera jitter 1.5 cm | IDM | 250 | 64.8 | 70.0 | – | – | |
| Camera jitter 1.5 cm | orig. | 50 | 48 | 44 | – | – | |
| Fresh noise per call | IDM | 50 | 96 | 96 | – | 26 | |
| Fresh noise per call | orig. | 50 | 96 | 92 | – | 94 |
| Host and checkpoint | 1 step | 2 steps | 4 steps | 10 steps | cache | |
|---|---|---|---|---|---|---|
| Table 1 host, IDM | 81 | 94 | 119 | 202 | 116 | 4.9 |
| Table 1 host, orig. | 81 | 92 | 118 | 202 | 120 | 4.8 |
| Table 1 host, orig., CUDA graphs | 79 | 86 | 100 | 143 | – | 10.0 |
| Follow-up host, IDM (round 1) | 186 | 192 | – | 477 | 240 | 3.4 |
| Shared host, IDM | 173 | 185 | – | – | – | – |
| Shared host, orig. | 158 | 190 | – | – | – | – |
| Host | success (%) | reuse (ms) | refresh (ms) | reuse/refresh | saving (%) | vs. 2 steps |
|---|---|---|---|---|---|---|
| quiet A6000, IDM | 94 | 83 | 95 | 0.870 | 10 | – |
| quiet A6000, orig. | 95 | 83 | 95 | 0.869 | 10 | – |
| shared A6000, IDM | 94 | 165 | 197 | 0.838 | 12 | 0.93 |
| shared A6000, orig. | 95 | 163 | 196 | 0.835 | 12 | 0.91 |
| follow-up A6000, IDM, round 1 | – | 178 | 211 | 0.843 | 12 | 0.98 |
| follow-up A6000, IDM, round 2 | – | 154 | 184 | 0.835 | 12 | 0.80 |
| Ckpt. | noise | cached | share (%) | success (%) | pred. (%) | |||
| IDM | 1 | fixed | 3 | 8 | 30 | 0.017 | 94 | – |
| IDM | 1 | fixed | 4 | 8 | 40 | 0.028 | 94 | – |
| IDM | 1 | fixed | 5 | 8 | 50 | 0.052 | 98 | – |
| IDM | 1 | fixed | 6 | 8 | 60 | 0.190 | 96 | – |
| IDM | 1 | fixed | 7 | 8 | 70 | 0.344 | 88 | – |
| IDM | 1 | fixed | 8 | 8 | 80 | 0.401 | 54 | – |
| A | B | A (%) | B (%) | A B | Tango 90% | |
| IDM, 6 of 10 cached, episode latent | fresh noise | 96 | 82 | +14 | 0.065 | |
| IDM, 6 of 10 cached, episode latent | fixed latent | 96 | 96 | 0 | 1.00 | |
| IDM, 8 of 10 cached, episode latent | fresh noise | 64 | 26 | +38 | 0.0002 | |
| IDM, 8 of 10 cached, episode latent | fixed latent | 64 | 54 | +10 | 0.18 | |
| IDM, 2 steps, delay 2 | 10 steps, delay 5 | 96 | 86 | +10 | 0.12 | |
| IDM, 2 steps, delay 2 | 2 steps, no delay | 96 | 94 | +2 | 1.00 |
| IDM | orig. | ||||||
|---|---|---|---|---|---|---|---|
| Task | 2 steps | 10 steps | 2 steps | 10 steps | |||
| 0 | open the middle drawer of the cabinet | 10 | 10 | 9 | 10 | 10 | 10 |
| 1 | put the bowl on the stove | 9 | 10 | 8 | 10 | 10 | 10 |
| 2 | put the wine bottle on top of the cabinet | 9 | 7 | 10 | 10 | 9 | 8 |
| 3 | open the top drawer and put the bowl inside | 8 | 9 | 3 | 9 | 9 | 9 |
| 4 | put the bowl on top of the cabinet | 10 | 10 | 9 | 10 | 10 | 10 |
Efficient Inference for World Action Models
Efficient inference for world action models cuts the cost of predicting action-conditioned futures for responsive control and planning.
See all 103 papers