Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
The Hong Kong University of Science and Technology
3
0
3
Counterfactual outcomes reveal that existing embodied agents miss 20% of potential success by not exploring alternative skill branches.
Over 1,500 submissions revealed stark differences in model performance across diverse domains, highlighting the challenges of generalizing egocentric video understanding.
VLMs exhibit distinct failure modes under physical visual stress, revealing that traditional accuracy metrics can mask critical vulnerabilities in embodied AI systems.