V-JEPA-LM open-source video language model released
The story so far
Research team releases open-source video language model Llama-V-JEPA-LM, combining the frozen V-JEPA 2.1 world model encoder with Qwen3 / Llama (1B–8B), using single-stage training and counterfactual supervision: the same segment and its transformed copies (reversed, mirrored, temporal changes) paired with the same question but different answers, making the model answer only based on the changes themselves. The team states that all 6 checkpoints, code, and online demos are open.
AI-written from the reports · Updated 10 hours ago
Coverage timeline
Follow the coverage to see every side of the story.
- Hugging Face Daily PapersFeaturedV-JEPA-LM, an open-source video language model, Llama-V-JEPA-LM, has been released.
The research team released the open-source video language model Llama-V-JEPA-LM, combining the frozen V-JEPA 2.1 world model encoder with Qwen3 / Llama (1B–8B), using single-stage training and counterfactual supervision: the same segment and its transformed copies (reversed, mirrored, changed temporally) are paired with the same question but different answers, making the model answer only based on the changes themselves.
Heat over time
- Now
- 5
- Peak
- 617 Nov, 00:00
- 24h change
- –
Hover or tap the chart to see each hour; use the arrow keys on a keyboard.