OmniShow: Unifying Multimodal Conditions for Human-Object Interaction Video Generation Paper β’ 2604.11804 β’ Published 3 days ago β’ 62
view article Article `LeRobotDataset:v3.0`: Bringing large-scale datasets to `lerobot` +9 Sep 16, 2025 β’ 51
SpecEyes: Accelerating Agentic Multimodal LLMs via Speculative Perception and Planning Paper β’ 2603.23483 β’ Published 22 days ago β’ 62
Manifold-Aware Exploration for Reinforcement Learning in Video Generation Paper β’ 2603.21872 β’ Published 23 days ago β’ 33
Astrolabe: Steering Forward-Process Reinforcement Learning for Distilled Autoregressive Video Models Paper β’ 2603.17051 β’ Published 29 days ago β’ 109