Hugging Face's logo
Activity Feed

AI & ML interests

None defined yet.

Recent Activity

Zacharias030  updated a model about 5 hours ago
facebook/KernelLLM
Fbordes  authored a paper 6 days ago
VideoAuto-R1: Video Auto Reasoning via Thinking Once, Answering Twice
mikezhaocs  authored a paper 6 days ago
VideoAuto-R1: Video Auto Reasoning via Thinking Once, Answering Twice
View all activity

Papers

VideoAuto-R1: Video Auto Reasoning via Thinking Once, Answering Twice

PhyGDPO: Physics-Aware Groupwise Direct Preference Optimization for Physically Consistent Text-to-Video Generation

View all Papers

facebook 's collections 44

V-JEPA 2
A frontier video understanding model developed by FAIR, Meta, which extends the pretraining objectives of https://ai.meta.com/blog/v-jepa-yann
MobileLLM
Optimizing Sub-billion Parameter Language Models for On-Device Use Cases (ICML 2024) https://arxiv.org/abs/2402.14905
Seamless Communication
A significant step towards removing language barriers through expressive, fast and high-quality AI translation.
Wav2Vec 2.0
A collection for the first release of Wav2Vec 2.0, a speech encoder that learns powerful representations from unlabelled audio data.
XLSR
A collection of multilingual Wav2Vec 2.0 checkpoints pre-trained on 53 languages and fine-tuned for CTC speech recognition.
Robust Wav2Vec 2.0
A collection of "robust" Wav2Vec 2.0 checkpoints pre-trained on datasets from multiple domains.
VoxPopuli v2
A collection of checkpoints from the second VoxPopuli release.
DINOv3
DINOv3: foundation models producing excellent dense features, outperforming SotA w/o fine-tuning - https://arxiv.org/abs/2508.10104
Meta CLIP 1
Scaling CLIP data with transparent training distribution from an end-to-end pipeline.
VoxPopuli
A collection of open-source artefacts (datasets + checkpoints) from the first VoxPopuli release.
HuBERT
A collection of checkpoints from the HuBERT release, a speech encoder that learns powerful representations from unlabelled audio data.
DINOv2
DINOv2: foundation models producing robust visual features suitable for image-level and pixel-level visual tasks - https://arxiv.org/abs/2304.07193
DINOv3
DINOv3: foundation models producing excellent dense features, outperforming SotA w/o fine-tuning - https://arxiv.org/abs/2508.10104
Meta CLIP 1
Scaling CLIP data with transparent training distribution from an end-to-end pipeline.
V-JEPA 2
A frontier video understanding model developed by FAIR, Meta, which extends the pretraining objectives of https://ai.meta.com/blog/v-jepa-yann
MobileLLM
Optimizing Sub-billion Parameter Language Models for On-Device Use Cases (ICML 2024) https://arxiv.org/abs/2402.14905
Seamless Communication
A significant step towards removing language barriers through expressive, fast and high-quality AI translation.
Wav2Vec 2.0
A collection for the first release of Wav2Vec 2.0, a speech encoder that learns powerful representations from unlabelled audio data.
XLSR
A collection of multilingual Wav2Vec 2.0 checkpoints pre-trained on 53 languages and fine-tuned for CTC speech recognition.
Robust Wav2Vec 2.0
A collection of "robust" Wav2Vec 2.0 checkpoints pre-trained on datasets from multiple domains.
VoxPopuli
A collection of open-source artefacts (datasets + checkpoints) from the first VoxPopuli release.
VoxPopuli v2
A collection of checkpoints from the second VoxPopuli release.
HuBERT
A collection of checkpoints from the HuBERT release, a speech encoder that learns powerful representations from unlabelled audio data.
DINOv2
DINOv2: foundation models producing robust visual features suitable for image-level and pixel-level visual tasks - https://arxiv.org/abs/2304.07193