Search papers, labs, and topics across Lattice.
Beijing University of Posts and Telecommunications
2
0
5
Overcome reward sparsity in medical visual grounding by dynamically tightening reward criteria based on model performance, leading to improved localization accuracy and training stability.
Forget SVD: CARE aligns low-rank attention approximations with input activations, boosting accuracy up to 1.7x and slashing perplexity by 215x when converting models to multi-head latent attention.
