Search papers, labs, and topics across Lattice.
3
0
5
2
LVLMs may not be as adept at reasoning as previously thought, with new benchmarks revealing significant gaps in their performance.
SHIFT transforms LLMs into reasoning-efficient retrievers, achieving superior performance on complex retrieval tasks by rethinking how we align retrieval objectives with implicit reasoning.
Instead of forcing modalities to imitate each other, IIBalance lets each modality contribute according to its intrinsic information budget, leading to better multimodal fusion.
