English translation is being prepared.
#Model releases#Video#Multimodal
#Model releases#Video#Multimodal
#Model releases#Speech#Multimodal
#Model releases#Image generation#Multimodal
#Product updates#English text is being prepared.#Reasoning
#Model releases#Open-source ecosystem#Reasoning
#Product updates#English text is being prepared.#Reasoning
Ai2 releases MolmoMotion: by inputting video frames, 3D points on objects, and action descriptions, it can predict the trajectories of these points in 3D space over the next few seconds, outperforming existing prediction methods. It also open-sources the MolmoMotion-1M dataset (derived from 1.16M videos) and the PointMotionBench benchmark (2.7K video clips), and releases the model weights. In simulation, a control policy based on MolmoMotion achieved a 76.3% success rate on pick-and-place tasks, higher than the 56.0% achieved by one based on Molmo 2.
#Model releases#Multimodal#Video
#Model releases#OpenAI#Agents
#Model releases#Google#OpenAI
#Model releases#RAG#Open-source ecosystem
#Model releases#Google#DeepMind
#Model releases#Google#Safety / alignment
#Model releases#Google#Evaluations / benchmarks
#Model releases#Google#Safety / alignment
#Model releases#Google#DeepMind
#Model releases#Agents#English text is being prepared.
#Model releases#Google#DeepMind
#Model releases#Google
#Model releases#Reasoning#Google
#Model releases#Google#Reasoning