csm
Datasets
All datasets matching “csm”layergen-eval-latents
LayerGen — Eval-Set Latents (VAE latents + baked text embeddings)
Pre-encoded evaluation-set inputs for the LayerGen layer-decomposition / harmonization models,
so inference can run anywhere (off-AIP) without the raw video → VAE-encode → umT5-encode pipeline.
Each *.parquet is one clip and is fully self-contained:
column group
contents
{composite,mask,fg,bg}_latent_bytes (+ _shape, _dtype)
4-stream Wan-VAE latents, 81f/21 latent-T, fp16, [16,21,60,104]… See the full description on the dataset page: https://huggingface.co/datasets/cs-mshah/layergen-eval-latents.layergen-evalslayergen-evals-baselinescsmar-legacycsmd
Dataset Card for "Continuous Scale Meaning Dataset" (CSMD)
CSMD was created for MeaningBERT: Assessing Meaning Preservation Between Sentences.
It contains 1,355 English text simplification meaning preservation annotations. Meaning preservation measures how well the meaning of the output text corresponds to the meaning of the source (Saggion, 2017).
The annotations were taken from the following four datasets:
ASSET
QuestEVal,
SimpDa_2022 and,
Simplicity-DA.
It contains a data… See the full description on the dataset page: https://huggingface.co/datasets/graalul/csmd.SynMirror
Dataset Card for SynMirror
This repository hosts the data for Reflecting Reality: Enabling Diffusion Models to Produce Faithful Mirror Reflections (accepted at 3DV'25).SynMirror is a first-of-its-kind large scale synthetic dataset on mirror reflections, with diverse mirror types, objects, camera poses, HDRI backgrounds and floor textures.
Dataset Details
Dataset Description
SynMirror consists of samples rendered from 3D assets of two widely used 3D… See the full description on the dataset page: https://huggingface.co/datasets/cs-mshah/SynMirror.