hybrid
2 notes tagged “hybrid”
-
[Token Fusion / ToFu] Bridging the Gap between Token Pruning and Token Merging
Switches between pruning (early layers) and merging (later layers) by each layer's functional linearity, with a norm-preserving MLERP merge.
-
[DiffRate] Differentiable Compression Rate for Efficient Vision Transformers
Makes the per-layer compression rate differentiable, and prunes + merges in one unified framework.
