Search papers, labs, and topics across Lattice.
National University of Sciences and Technology (NUST)
3
0
2
Riazi-8B outperforms existing Urdu models in mathematical reasoning, proving that targeted language adaptation can bridge the gap in low-resource AI applications.
ROMEVA reveals that prioritizing embedding stability can compromise downstream performance, challenging conventional wisdom in low-resource NLP.
Textual semantics excel at predicting current affect but fail to capture future changes, which are better modeled by numeric trajectories.
