Search papers, labs, and topics across Lattice.
4
0
8
FQA slashes area and power consumption by over 50% for Sigmoid activation functions while maintaining optimal approximation accuracy.
Embodied agents can now exhibit coherent, long-horizon, self-directed behavior by reasoning about abstract value trade-offs, a capability previously absent in instruction-following or needs-driven approaches.
Seedance 2.0 leapfrogs existing models by unifying multi-modal inputs (text, image, audio, video) into a single architecture for generating high-quality, longer-duration audio-video content.
Audio-specific KV cache eviction lets you compress LALMs by 40% with almost no accuracy loss, while generic methods fall apart.
