Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
6
0
0
10
A single dual-loop harness enables generalist VLAs to achieve preference-consistent task execution and robust failure recovery in real-world robotics.
A residual memory mechanism allows LLMs to retain crucial context for long-horizon tasks, achieving near full-context performance with only 5.2% of input positions.
Integration of diverse robot policies can be streamlined from hours to minutes, revolutionizing how we deploy and evaluate robotic systems.
Mage-VL slashes visual token usage by over 75% while enhancing real-time multimodal performance, outperforming larger models in video understanding.
Mage-Flow achieves high-resolution image generation and editing in under a second on a single GPU, challenging the notion that larger models are always necessary for quality.
A surprisingly simple VLA model, StarVLA-$\alpha$, beats more complex systems on real-world robotics tasks, suggesting that VLM backbones are more critical than intricate architectures.