# Video Modeling on BAIR Robotic Pushing

Source: [Video Modeling on BAIR Robotic Pushing](<https://www.sota2.com/research/sota/video-modeling-on-bair-robotic-pushing>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-26T05:37:51.689Z

Evaluation of video modeling performance using the BAIR Robotic Pushing dataset, measured by bits/dim.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Video modeling |
| Dataset (including any stated split) | BAIR Robotic Pushing |
| Metric | Bits/Dim |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 3 of 3 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Bits/Dim](<https://www.sota2.com/research/sota/video-modeling-on-bair-robotic-pushing.md?metric=Bits%2FDim>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Bits/Dim | Result date | Report paper |
| --- | --- | --- | --- |
| Axial Transformer | 1.29 | Not recorded | 68fa66e71e209131cea130b2 |
| Video Transformer | 1.35 | Not recorded | 68fa66e71e209131cea130b2 |
| VideoFlow | 1.87 | Not recorded | 68fa66e71e209131cea130b2 |

### Axial Transformer

Bits/Dim: 1.29. Result ID: 698d0ff08b517eb4331eb73b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa66e71e209131cea130b2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66e71e209131cea130b2.md>)

Recorded evaluation configuration: {"Conditioning frames":"1 frame"}. This record does not assert independent reproduction.

### Video Transformer

Bits/Dim: 1.35. Result ID: 698d0ff08b517eb4331eb73a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa66e71e209131cea130b2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67061e209131cea13e6e.md>)

[Implementation](<https://bit.ly/2Zb017f>)

Recorded evaluation configuration: {"Conditioning frames":"1 frame"}. This record does not assert independent reproduction.

### VideoFlow

Bits/Dim: 1.87. Result ID: 698d0ff08b517eb4331eb739.

[Reporting paper](<https://www.sota2.com/research/paper/68fa66e71e209131cea130b2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67071e209131cea13f09.md>)

Recorded evaluation configuration: {"Conditioning frames":"3 prior frames"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.