Search papers, labs, and topics across Lattice.
2
0
5
Current video benchmarks are too simple; UniVBench offers the first unified framework to measure the integrated capabilities of video foundation models using complex, multi-shot videos and a standardized evaluation system.
Forget hand-tuning pipelines: a new RL framework lets LLMs dynamically assemble Text-to-SQL workflows at inference time, outperforming even the best static configurations.
