Search papers, labs, and topics across Lattice.
3
0
4
16
Instruction-following speech models can be trained effectively without the cumbersome instruction tuning process, challenging the status quo in SLM development.
Retaining visual figures in skill artifacts boosts CUA performance by over 23 points, proving that seeing is believing in agent training.
LLM agent skills, despite their promise, often fail in realistic settings, with performance plummeting to no-skill baselines when agents must retrieve skills from a large, uncurated collection.
