Search papers, labs, and topics across Lattice.
6
2
9
3
Experiments show that MoRE consistently achieves lower perplexity and stronger downstream performance than standard MoEs and state-of-the-art weight-sharing architectures at matched compute and parameter budgets, with only minimal modifications to existing MoE implementations.
Co-evolving knowledge bases with reasoning capabilities can dramatically enhance the accuracy and relevance of answers in knowledge-intensive tasks.
A 5-step sampling schedule can deliver nearly the same quality as a 50-step one, slashing inference costs by 90%.
CO-LMLM achieves lower perplexity than models trained on 40 times more data, revolutionizing how we leverage knowledge bases in language generation.
Forget expensive human annotations or hallucination-prone LLM-generated data: rule-generated synthetic data can teach LLMs to compose knowledge and significantly boost multi-hop reasoning on real-world tasks.
By pausing to "think" with latent diffusion, STAR-LDM achieves superior language understanding, narrative coherence, and controllable generation compared to standard autoregressive models of similar size.
