GLM-5: from Vibe Coding to Agentic Engineering
Paper • 2602.15763 • Published • 144
260313
-
-
DeepVision-103K: A Visually Diverse, Broad-Coverage, and Verifiable Mathematical Dataset for Multimodal Reasoning
Paper • 2602.16742 • Published • 12 -
From Perception to Action: An Interactive Benchmark for Vision Reasoning
Paper • 2602.21015 • Published • 23 -
Thinking to Recall: How Reasoning Unlocks Parametric Knowledge in LLMs
Paper • 2603.09906 • Published • 75 -
RoboMME: Benchmarking and Understanding Memory for Robotic Generalist Policies
Paper • 2603.04639 • Published • 29 -
VGGT-Det: Mining VGGT Internal Priors for Sensor-Geometry-Free Multi-View Indoor 3D Object Detection
Paper • 2603.00912 • Published • 40 -
RealWonder: Real-Time Physical Action-Conditioned Video Generation
Paper • 2603.05449 • Published • 12 -
Holi-Spatial: Evolving Video Streams into Holistic 3D Spatial Intelligence
Paper • 2603.07660 • Published • 86 -
CAST: Modeling Visual State Transitions for Consistent Video Retrieval
Paper • 2603.08648 • Published • 5 -
MA-EgoQA: Question Answering over Egocentric Videos from Multiple Embodied Agents
Paper • 2603.09827 • Published • 30