Search papers, labs, and topics across Lattice.
4
0
9
The form of answer labels, not just their quantity, fundamentally shapes what LLMs learn during fine-tuning, revealing a surprising causal relationship that could redefine training strategies.
ProMSA achieves superior accuracy in KB-VQA by dynamically selecting retrieval strategies, outperforming traditional fixed pipelines.
Forget end-to-end fine-tuning: $M^2$-VLA unlocks the power of generalized VLMs for robotic manipulation by intelligently mixing layers and incorporating meta-skills.
Forget fixed pipelines: training an agent to *learn* when and how to search for knowledge dramatically improves performance on knowledge-based visual question answering.
