RynnWorld-4D: 4D Embodied World Models for Robotic Manipulation Paper • 2607.06559 • Published 2 days ago • 72
Embodied.cpp: A Portable Inference Runtime of Embodied AI Models on Heterogeneous Robots Paper • 2607.02501 • Published 7 days ago • 50
MemSlides: A Hierarchical Memory Driven Agent Framework for Personalized Slide Generation with Multi-turn Local Revision Paper • 2606.17162 • Published 24 days ago • 176
DataClaw0: Agentic Tailoring Multimodal Data from Raw Streams Paper • 2606.21337 • Published 20 days ago • 74
Moebius: 0.2B Lightweight Image Inpainting Framework with 10B-Level Performance Paper • 2606.19195 • Published 22 days ago • 139
OmniDirector: General Multi-Shot Camera Cloning without Cross-Paired Data Paper • 2606.13432 • Published 28 days ago • 113
Toward Generalist Autonomous Research via Hypothesis-Tree Refinement Paper • 2606.11926 • Published 29 days ago • 126
WeaveBench: A Long-Horizon, Real-World Benchmark for Computer-Use Agents with Hybrid Interfaces Paper • 2606.09426 • Published about 1 month ago • 104
Imaginative Perception Tokens Enhance Spatial Reasoning in Multimodal Language Models Paper • 2606.03988 • Published Jun 3 • 126
DCAgent3/financeagent_terminal_a3_rl_laion_nemotron_gym_instruction_following_structured515095c6 Viewer • Updated Jun 3 • 158 • 16 • 1
On the Scaling of PEFT: Towards Million Personal Models of Trillion Parameters Paper • 2606.02437 • Published Jun 1 • 237