3rd Place Report of LSVOS 2025 MeViS Track: Sa2VA-i: Improving Sa2VA Results with Consistent Training and Inference Paper β’ 2509.19082 β’ Published Sep 23
Scaling Laws for Robust Comparison of Open Foundation Language-Vision Models and Datasets Paper β’ 2506.04598 β’ Published Jun 5 β’ 7
Alice in Wonderland: Simple Tasks Showing Complete Reasoning Breakdown in State-Of-the-Art Large Language Models Paper β’ 2406.02061 β’ Published Jun 4, 2024 β’ 2
DataComp-LM: In search of the next generation of training sets for language models Paper β’ 2406.11794 β’ Published Jun 17, 2024 β’ 54
Scaling Laws for Robust Comparison of Open Foundation Language-Vision Models and Datasets Paper β’ 2506.04598 β’ Published Jun 5 β’ 7