OmniShow: Unifying Multimodal Conditions for Human-Object Interaction Video Generation Paper β’ 2604.11804 β’ Published 7 days ago β’ 69
TRACER: Trace-Based Adaptive Cost-Efficient Routing for LLM Classification Paper β’ 2604.14531 β’ Published 4 days ago β’ 6
TRACER: Trace-Based Adaptive Cost-Efficient Routing for LLM Classification Paper β’ 2604.14531 β’ Published 4 days ago β’ 6
HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds Paper β’ 2604.14268 β’ Published 5 days ago β’ 89
Running 80 Chinese Open Source Heatmap π₯ 80 Explore model release activity with interactive heatmaps
MOSS-Audio Collection An open-source audio understanding model supporting speech recognition, environmental sound analysis, music understanding, time-aware QA, and complex β’ 5 items β’ Updated 3 days ago β’ 35
Seedance 2.0: Advancing Video Generation for World Complexity Paper β’ 2604.14148 β’ Published 5 days ago β’ 140
Geometric Context Transformer for Streaming 3D Reconstruction Paper β’ 2604.14141 β’ Published 5 days ago β’ 5