Search papers, labs, and topics across Lattice.
4
0
6
Purely autoregressive VLAs no longer require awkward hybrid diffusion heads to achieve fine-grained robot control: structuring discrete action tokenization as causally annealed flow matching recovers continuous diffusion precision while preserving end-to-end token efficiency.
Human raters overwhelmingly prefer JoyAI-VL-Interaction over existing video-call assistants, showcasing a leap in real-time interaction capabilities.
CapRL++ redefines caption quality through utility, enabling models to produce high-fidelity descriptions without the constraints of traditional supervised fine-tuning.
By mimicking how humans use visual anchors, ChartVSR lets models iteratively correct their own visual perception errors, leading to more accurate chart parsing.
