nkkbr
/

ViCA

Video-Text-to-Text

text-generation

vision-language

video understanding

spatial reasoning

visuospatial cognition

Model card Files Files and versions

nkkbr commited on May 7

Commit

738d65b

·

1 Parent(s): 1f5a21f

update readme

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -95,8 +95,8 @@ ViCA-7B is fine-tuned on two complementary datasets:
 | Configuration        | Avg Score |
 |----------------------|-----------|
-| Base-only (281K)     | 55.39     |
-| Full with CSR (322K) | **60.14** |
 > CSR(Complex Spatial Reasoning) boosts generalization and **accelerates learning**, with notable performance jumps at intermediate checkpoints (e.g., +2.02 at 50–55%).

 | Configuration        | Avg Score |
 |----------------------|-----------|
+| Base-only (281K)     | 55.35     |
+| Full with CSR (322K) | **60.56** |
 > CSR(Complex Spatial Reasoning) boosts generalization and **accelerates learning**, with notable performance jumps at intermediate checkpoints (e.g., +2.02 at 50–55%).