HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds Paper • 2604.14268 • Published 3 days ago • 73
Nemotron 3 Super: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning Paper • 2604.12374 • Published 4 days ago • 28
Habitat-GS: A High-Fidelity Navigation Simulator with Dynamic Gaussian Splatting Paper • 2604.12626 • Published 4 days ago • 14
Audio Flamingo Next: Next-Generation Open Audio-Language Models for Speech, Sound, and Music Paper • 2604.10905 • Published 5 days ago • 26
ClawGUI: A Unified Framework for Training, Evaluating, and Deploying GUI Agents Paper • 2604.11784 • Published 5 days ago • 134
Attention Sink in Transformers: A Survey on Utilization, Interpretation, and Mitigation Paper • 2604.10098 • Published 7 days ago • 74
GameWorld: Towards Standardized and Verifiable Evaluation of Multimodal Game Agents Paper • 2604.07429 • Published 10 days ago • 109
WildDet3D: Scaling Promptable 3D Detection in the Wild Paper • 2604.08626 • Published 9 days ago • 237
ELT: Elastic Looped Transformers for Visual Generation Paper • 2604.09168 • Published 8 days ago • 19
Matrix-Game 3.0: Real-Time and Streaming Interactive World Model with Long-Horizon Memory Paper • 2604.08995 • Published 8 days ago • 46
Small Vision-Language Models are Smart Compressors for Long Video Understanding Paper • 2604.08120 • Published 9 days ago • 20
HY-Embodied-0.5: Embodied Foundation Models for Real-World Agents Paper • 2604.07430 • Published 10 days ago • 182
Structured Distillation of Web Agent Capabilities Enables Generalization Paper • 2604.07776 • Published 9 days ago • 20
ClawBench: Can AI Agents Complete Everyday Online Tasks? Paper • 2604.08523 • Published 9 days ago • 255
OpenSpatial: A Principled Data Engine for Empowering Spatial Intelligence Paper • 2604.07296 • Published 10 days ago • 39
Flux Attention: Context-Aware Hybrid Attention for Efficient LLMs Inference Paper • 2604.07394 • Published 10 days ago • 16
SkillClaw: Let Skills Evolve Collectively with Agentic Evolver Paper • 2604.08377 • Published 9 days ago • 277
MolmoWeb: Open Visual Web Agent and Open Data for the Open Web Paper • 2604.08516 • Published 9 days ago • 41