Search papers, labs, and topics across Lattice.
3
0
6
Zero-initialization emerges as the key driver behind the superior performance of adaLN-Zero in diffusion transformers, reshaping our understanding of conditioning mechanisms in image generation.
Current LLMs fail to effectively anticipate user needs, with even the latest models only succeeding in 26.7% of proactive scenarios.
Current audio-visual generation models struggle to maintain coherence and alignment when scaling to minute-long content, a problem exposed by the new LongAV-Compass benchmark.
