Search papers, labs, and topics across Lattice.
3
0
8
3
Current egocentric video generation models fail to execute multi-step manipulation tasks realistically, often skipping crucial actions and exhibiting poor physical dynamics.
Fixing your parallelism strategy while tuning batch size (or vice versa) leaves performance on the table: COPUS adaptively co-tunes both for faster LLM training.
VLMs can regain lost linguistic prowess without extra parameters or architectural changes, thanks to a clever KV-cache sharing trick for distillation.
