TECH·2 days agoDark Horse Muka Robotics Charges WorldArena With Only 32 Zhenwu 810E GPUs: LJM World Model Achieves Global Second Place, Marking a Breakthrough From Video Quality to Physical LogicPandaily
PAPER·3 days agoTurboVLA: Real-Time Vision-Language-Action Model at 32 Hz on an RTX 4090 with <1 GB VRAMHugging Face Papers
PAPER·4 days agoWorldDiT: A Unified Diffusion Architecture for World and Action ModelingHugging Face Papers
PAPER·4 days agoCoTinyVLA: Chain-of-Thought Distillation for a Sub-Billion-Parameter Vision-Language-Action ModelarXiv
PAPER·June 1, 2026Hide-and-Seek in Trajectories: Discovering Failure Signals for VLA Runtime MonitoringHugging Face Papers
PAPER·May 29, 2026Qwen-VLA: Unifying Vision-Language-Action Modeling across Tasks, Environments, and Robot EmbodimentsHugging Face Papers
PAPER·May 28, 2026Ω-QVLA: Robust Quantization for Vision-Language-Action Models via Composite Rotation and Per-step ScalingarXiv
TECH·May 26, 2026Uber One free for one year with "Rakuten Saikyo U-NEXT," plus points backImpress Watch
