Search papers, labs, and topics across Lattice.
3
0
3
12
Chain-of-Thought prompting, a boon for logical reasoning in LLMs, surprisingly *harms* visual spatial reasoning in multimodal models.
MLLMs still struggle with core visuospatial reasoning skills like abstraction and transformation, lagging far behind human performance on a new cognitive benchmark.
Multimodal models may ace the test, but their reasoning is often a sham: FGRPO makes them explain their answers in a way that actually makes sense.
