Search papers, labs, and topics across Lattice.
4
2
9
15
Achieve near-dense Video-LLM performance on long videos with up to 57% fewer FLOPs by adaptively selecting which video cubes and tokens to process.
Forget fixed workflows: SEMAG's self-evolving agents dynamically adapt their coding process and even upgrade their backbone LLM, leading to state-of-the-art code generation performance.
Forget RLHF and massive datasets: SAGE co-evolves reasoning abilities in LLMs using only a small seed set and a clever quartet of self-improving agents.
Forget slow visual token concatenation: LaVi modulates LLM features directly with visual context, slashing FLOPs by 94% while boosting speed and accuracy.
