Search papers, labs, and topics across Lattice.
6
0
8
OmniPack achieves a remarkable 98% performance retention with a staggering 83.3% reduction in computational load, revolutionizing token compression for omni-modal models.
Thinking Collapse can severely impair reasoning in LLMs, but a new adaptive framework boosts accuracy by over 4% while preserving cognitive capacity.
LLMs can misclassify harmless rephrasings as critical errors, but a new lightweight metric outperforms larger models in clinical significance evaluation.
MLLMs excel at precision but falter dramatically in extracting complete product specifications from multiple images, with a mere 49.9% recovery rate.
A single adaptive framework can boost the efficiency of zeroth-order optimization by up to 3x without increasing memory usage.
Multi-agent systems get a 6.3% accuracy boost on math problems thanks to a new "rectify-or-reject" pruning method that dynamically filters out bad information at test time.
