Search papers, labs, and topics across Lattice.
3
0
5
0
LLMs can automatically generate hierarchical concept-attribute knowledge that significantly boosts image clustering performance, even surpassing zero-shot CLIP in many cases.
Forget fixed Top-k retrieval: HingeMem's query-adaptive retrieval dynamically decides *what* and *how much* to retrieve from long-term memory, boosting dialogue performance by 20% while slashing token costs.
Image-to-video models can now generate more consistent and expressive animated storyboards than static diffusion models, thanks to a Disney-inspired multi-agent framework.
