Search papers, labs, and topics across Lattice.
IIT Delhi, IIIT Delhi
3
0
6
8
SNIPER achieves a remarkable CRAFT score of 0.98, ensuring near-perfect adherence to compression budgets while maintaining model performance.
LLMs with similar benchmark scores can have wildly different internal representations and dynamics, revealing hidden strengths and weaknesses traditional benchmarks miss.
Vision-language models can significantly enhance language models through knowledge distillation, even without direct textual understanding, challenging conventional KD paradigms.
