Upload tinyvla2/RESULTS.md with huggingface_hub

tinyvla2/RESULTS.md

@@ -740,11 +740,53 @@ two trained codes by 0.194 — comparable magnitudes, so there is no special "tr
 subspace" a new robot could be projected into. For an unseen robot every available
 code is somebody else's, and a random one is no worse.
 
-This is precisely the argument for the morphology descriptor, now measured on a model
-trained over 214M frames rather than asserted: a 16-number physical descriptor can be
-*computed* for a robot that has never been trained on, and the corrected cross-robot
-table shows that channel is read (dropping it costs 503.9 -> 756.4 mm). A learned id
-cannot be computed, only looked up.
+That looks like the argument for the morphology descriptor — a 16-number physical
+descriptor can be *computed* for an unseen robot where a learned id can only be looked
+up. **So it was tested, and the argument does not survive the test.**
+
+### Converting the GR00T checkpoint to morphology conditioning does NOT fix LeKiwi
+
+The checkpoint has no `morph_encoder` at all (the run discarded C-scaled's, since its
+config is `conditioning: id`). Two steps were tried:
+
+1. **Graft only** — set `conditioning: morph`, transplant tv2_C_scaled's trained
+   morph encoder. Result 1.30 / 1.11, *worse* than id. Expected: the expert spent 60k
+   steps reading a 1-token id and has never seen 2 morph tokens from another model's
+   encoder. (All six ids give identical numbers here, which confirms the morph path is
+   actually active and the id is ignored.)
+2. **Train it to read the descriptor** — 6k streaming steps with the six GR00T family
+   descriptors (`scripts/train_groot_morph.py`), everything else already trained.
+
+| conditioning | abs (7 dims) | delta (2 dims) |
+|---|---|---|
+| id, best of six (oracle) | 1.18 | 0.88 |
+| morph, grafted only | 1.30 | 1.11 |
+| morph, 1k steps | **1.13** | 0.83 |
+| morph, 2k steps | 1.16 | 1.00 |
+| morph, 4k steps | **1.12** | 0.87 |
+| morph, 6k steps | 1.17 | 0.93 |
+| oracle repeat-A₀ | 0.91 | 0.54 |
+
+**The improvement is 1.18 -> 1.12 at best, and it is not monotonic** (1.13, 1.16,
+1.12, 1.17 across checkpoints) — that spread is noise, not convergence. Both
+conditioning schemes stay above 1.0 on the absolute dims, i.e. worse than holding the
+current pose, and both lose to a dynamics-free predictor that repeats the first
+ground-truth action.
+
+So the honest conclusion is narrower than the one above: **being computable is
+necessary but not sufficient.** A descriptor gives you a well-defined input for an
+unseen robot, which an id cannot; it does not by itself give you transfer. This model
+was trained on six morphologies — three panda variants, two humanoids and an R1-Pro —
+none of them a small 5-DOF arm on a wheeled base, and no conditioning scheme extracts
+a LeKiwi policy from that.
+
+**Confound, stated rather than buried:** the morph run had to reweight the mixture,
+because the per-episode sampler starved the loader (every draw pulled a ~190 MB
+r1_pro episode and the first batch never arrived). The correction over-shot — realized
+shares became gr1 0.67 / panda_single 0.23 / g1 0.04 / bimanual 0.035 / r1_pro 0.02 —
+so the morph model saw a different mixture than the id model. This is not a matched
+pair, and a matched-pair version would need retraining the id model on the same
+reweighted stream.
 
 That id 15 (g1: a humanoid arm commanded in joint space) is the best of the six is
 the one sensible signal in the table — it is the closest morphology to an SO-100 arm