Search papers, labs, and topics across Lattice.
Indian Institute of Technology
3
0
5
Tailoring counterspeech to specific hate speech categories can enhance effectiveness and reduce toxicity, achieving significant improvements over traditional methods.
Safety alignment in VLMs can suppress grounded visual reasoning, yet visual evidence remains influential during refusal, revealing a complex interplay between safety and perception.
SNIPER achieves a remarkable CRAFT score of 0.98, ensuring near-perfect adherence to compression budgets while maintaining model performance.
