We lifted 8 functions out of this paper's own repositories and ran 7 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| hanyangclarence/UniMuMo | canonical | 7 of 8 |
| Function | Status | Where it lives |
|---|---|---|
| angle_between | Ran | hanyangclarence/UniMuMo/unimumo/alignment/visual_beat.py pointer only (licence: NONE) · get_code("4bdc0cc9b4d0d928") |
| d_x | Ran | hanyangclarence/UniMuMo/unimumo/alignment/visual_beat.py pointer only (licence: NONE) · get_code("ed96da0641c14d4b") |
| get_obj_from_str | Ran | hanyangclarence/UniMuMo/unimumo/util.py pointer only (licence: NONE) · get_code("221b2d116fdf1032") |
| instantiate_from_config | Ran | hanyangclarence/UniMuMo/unimumo/util.py pointer only (licence: NONE) · get_code("230615b9581d6e9d") |
| interp | Ran | hanyangclarence/UniMuMo/unimumo/alignment/interpolation.py pointer only (licence: NONE) · get_code("158ff9eaa14b362d") |
| interpolate | Ran | hanyangclarence/UniMuMo/unimumo/alignment/interpolation.py pointer only (licence: NONE) · get_code("8eab2b6b52a23d15") |
| unit_vector | Ran | hanyangclarence/UniMuMo/unimumo/alignment/visual_beat.py pointer only (licence: NONE) · get_code("b504614ee071c480") |
| load_model_from_config | Not yet run | hanyangclarence/UniMuMo/unimumo/util.py pointer only (licence: NONE) · get_code("becfa63019187994") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
We introduce UniMuMo, a unified multimodal model capable of taking arbitrary text, music, and motion data as input conditions to generate outputs across all three modalities. To address the lack of time-synchronized data, we align unpaired music and motion data based on rhythmic patterns to leverage existing large-scale music-only and motion-only datasets. By converting music, motion, and text into token-based representation, our model bridges these modalities through a unified encoder-decoder transformer architecture. To support multiple generation tasks within a single framework, we introduce several architectural improvements. We propose encoding motion with a music codebook, mapping motion into the same feature space as music. We introduce a music-motion parallel generation scheme that unifies all music and motion generation tasks into a single transformer decoder architecture with a single training task of music-motion joint generation. Moreover, the model is designed by fine-tuning existing pre-trained single-modality models, significantly reducing computational demands. Extensive experiments demonstrate that UniMuMo achieves competitive results on all unidirectional generation benchmarks across music, motion, and text modalities. Quantitative results are available in the \href{https://hanyangclarence.github.io/unimumo_demo/}{project page}.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2410.04534")
get_code_for_paper("2410.04534")
have("2410.04534")
Connect an agent — have() is free.