Search papers, labs, and topics across Lattice.
4
1
6
1
LLMs may excel at predicting outcomes in sports, but they often converge on incorrect answers, revealing a critical flaw in their forecasting abilities.
LLMs struggle with social forecasting, achieving only 75% accuracy on a benchmark that reveals critical gaps in their understanding of temporal dynamics and probability calibration.
Image editing can boost multimodal LLM reasoning by 5 points, but only if the editor is trained to understand the reasoning process itself.
By mimicking how humans use visual anchors, ChartVSR lets models iteratively correct their own visual perception errors, leading to more accurate chart parsing.
