When Lower Privileges Suffice: Investigating Over-Privileged Tool Selection in LLM Agents Paper • 2606.20023 • Published 10 days ago • 4
MemPrivacy: Privacy-Preserving Personalized Memory Management for Edge-Cloud Agents Paper • 2605.09530 • Published May 10 • 149
Audio-Omni: Extending Multi-modal Understanding to Versatile Audio Generation and Editing Paper • 2604.10708 • Published Apr 12 • 44
Matrix-Game 3.0: Real-Time and Streaming Interactive World Model with Long-Horizon Memory Paper • 2604.08995 • Published Apr 10 • 51
ReVSI: Rebuilding Visual Spatial Intelligence Evaluation for Accurate Assessment of VLM 3D Reasoning Paper • 2604.24300 • Published Apr 27 • 68
GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents Paper • 2604.26752 • Published Apr 29 • 112
Seedance 2.0: Advancing Video Generation for World Complexity Paper • 2604.14148 • Published Apr 15 • 167
LLaDA2.0-Uni: Unifying Multimodal Understanding and Generation with Diffusion Large Language Model Paper • 2604.20796 • Published Apr 22 • 244