AI2-THOR
PulseAugur coverage of AI2-THOR — every cluster mentioning AI2-THOR across labs, papers, and developer communities, ranked by signal.
-
New MEMENTO framework evolves code-as-policy for embodied AI tasks
Researchers have developed MEMENTO, a novel framework for evolving policies represented as executable code. This memory-guided approach uses a combination of evolutionary methods and local search techniques to improve p…
-
New framework SENTINEL formally evaluates safety of AI embodied agents
Researchers have introduced SENTINEL, a novel framework designed to formally evaluate the physical safety of embodied agents powered by foundation models. This framework offers a multi-level safety assessment, covering …
-
New research tackles annotation efficiency for object detection models
Two new research papers explore advanced methods for improving object detection annotation efficiency. The first paper introduces a foundation-model-collaborative active learning framework that uses dual-source uncertai…
-
New models and frameworks advance embodied AI capabilities
Researchers are developing advanced models and frameworks to enable more capable embodied artificial intelligence. One approach, Athena-Brain-8B, is an 8B LLM designed for on-device robot brains, showing strong general …
-
Embodied AI research advances grounded world models and agent collaboration · 8 sources tracked
Recent research explores advancements in embodied AI, focusing on how biological systems acquire grounded world models through environmental interaction. Papers discuss frameworks for integrating AI intelligence into ph…
-
New DRL framework improves robot navigation by predicting and avoiding collisions
Researchers have developed a new method for object-goal visual navigation that explicitly addresses collisions, a common limitation in real-world applications. This approach introduces a collision-aware evaluation metri…