Search papers, labs, and topics across Lattice.
3
0
9
Forget coarse-grained audio-visual tasks: RA-SSU offers frame-level sound source understanding with two new datasets and a transformer-based benchmark.
Ditch the likelihood approximations: LFPO directly optimizes denoising logits in diffusion LMs via contrastive updates, leading to faster inference and better code/reasoning performance.
LLMs learn faster and perform better when you optimize prompts and weights together, boosting performance by 30% and cutting interaction turns by 40%.
