LeanK: Learnable K Cache Channel Pruning for Efficient Decoding Paper β’ 2508.02215 β’ Published 15 days ago β’ 11
AndroidLab: Training and Systematic Benchmarking of Android Autonomous Agents Paper β’ 2410.24024 β’ Published Oct 31, 2024 β’ 51
CogVLM2: Visual Language Models for Image and Video Understanding Paper β’ 2408.16500 β’ Published Aug 29, 2024 β’ 58
VisualAgentBench: Towards Large Multimodal Models as Visual Foundation Agents Paper β’ 2408.06327 β’ Published Aug 12, 2024 β’ 17
CogVLM: Visual Expert for Pretrained Language Models Paper β’ 2311.03079 β’ Published Nov 6, 2023 β’ 28