Search papers, labs, and topics across Lattice.
7
0
9
4
Adapting supervision weights based on the evolution of divergence histories boosts reasoning performance in language models without extra computational overhead.
The shift from parameter-centric to system-level adaptation in continual learning could redefine how we build and interact with AI models.
T2I models struggle significantly with spatial instructions based on object orientation, achieving only 44.3% accuracy on frame-of-reference prompts.
Learned attention allocation patterns reveal that SWA is best positioned in lower layers, challenging conventional wisdom on attention distribution in LLMs.
Forget brute-force hinting: KnowRL distills knowledge into atomic units, then uses subset selection to find the *least* amount of guidance needed to supercharge LLM reasoning.
Ditch slow, verbose chain-of-thought reasoning: PLUME's latent reasoning slashes inference time by 30x while boosting multimodal embedding performance.
Training-free zero-shot image retrieval just got a whole lot better: WISER's "retrieve-verify-refine" pipeline achieves state-of-the-art results by intelligently fusing text-to-image and image-to-image retrieval.
