Video-language models that read V-JEPA dynamics (1B-30B, Qwen3 and Llama). Technical report and code: github.com/kkt94/Llama-V-JEPA-LM
👋 Open to Work
Keuntae Kim
kkt94
AI & ML interests
LLM, VLM, VLA post-training / AI safety & alignment / Reinforcement Learning
Recent Activity
updated a model 17 minutes ago
kkt94/Llama-V-JEPA-LM-Qwen3-8B updated a model 17 minutes ago
kkt94/Llama-V-JEPA-LM-Llama3.1-8B updated a model 17 minutes ago
kkt94/Llama-V-JEPA-LM-Qwen3-4BOrganizations
None yet