Search papers, labs, and topics across Lattice.
5
0
8
20
The shift from parameter-centric to system-level adaptation in continual learning could redefine how we build and interact with AI models.
Adapting supervision weights based on the evolution of divergence histories boosts reasoning performance in language models without extra computational overhead.
Merging RL experts effectively requires balancing sharp, informative signals with stable, dispersed components, a challenge that ResMerge addresses with innovative spectral techniques.
Achieve near-lossless performance in autonomous driving VLMs with 90% token reduction – without any training.
Ditch slow, verbose chain-of-thought reasoning: PLUME's latent reasoning slashes inference time by 30x while boosting multimodal embedding performance.
