docs(dynamic): link frozen external generalization evidence
Browse files
README.md
CHANGED
|
@@ -56,3 +56,7 @@ Data: [xju-arlab/vbench-repair](https://huggingface.co/datasets/xju-arlab/vbench
|
|
| 56 |
Third-party base-model and dataset terms continue to apply.
|
| 57 |
|
| 58 |
Object Class and Color publish the paper-final step 300 at the user's explicit request. **These two models were not selected by development evaluation.** Their original runs used a fixed 300-step schedule and have no dev comparison between the retained steps 200 and 300. The checkpoint hashes, training results and selection rationale are preserved in each dimension directory. Prompt-only inference source and the frozen vocabulary are in `code/object_color/`.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 56 |
Third-party base-model and dataset terms continue to apply.
|
| 57 |
|
| 58 |
Object Class and Color publish the paper-final step 300 at the user's explicit request. **These two models were not selected by development evaluation.** Their original runs used a fixed 300-step schedule and have no dev comparison between the retained steps 200 and 300. The checkpoint hashes, training results and selection rationale are preserved in each dimension directory. Prompt-only inference source and the frozen vocabulary are in `code/object_color/`.
|
| 59 |
+
|
| 60 |
+
## Dynamic external generalization: LASIESTA and BMC (2026-09-23)
|
| 61 |
+
|
| 62 |
+
The unchanged aligned-v1 checkpoint was evaluated on two external real-video datasets; [frozen results and limitations](https://huggingface.co/datasets/xju-arlab/vbench-repair/blob/e64af55bd59324fb3f5ce934776e091fd70843eb/dimensions/dynamic_degree/generalization/external-v1-20260923/README.md). LASIESTA contributes 43 clips/9 recordings and BMC 84 clips/7 recordings. No retraining or posthoc score mapping. BMC mean repair score 0.282374→0.292002 versus Origin 0.261905→1.000000 under 8px local texture jitter. BMC labels are exploratory agent review and LASIESTA native timing is unverified. Individual failures, confidence intervals and original dev failures are retained. This update changes documentation only; pinned weight revisions remain valid.
|