Papers by Margaret Capetz
Token Pruning for Improving Graph-Generating State Space Model Performance (2026.eacl-srw)
Copied to clipboard
| Challenge: | State Space Models (SSMs) are efficient alternatives to Transformers for sequence modeling, but extending them to two-dimensional vision tasks remains challenging. |
| Approach: | They propose a leaf-guided pruning strategy that accelerates GG-SSM inference . they selectively scales or bypasses secondary refinement computations associated with leaf nodes . |
| Outcome: | The proposed pruning strategy accelerates GG-SSM inference without modifying graph topology . the proposed pruning method achieves throughput improvements with controlled accuracy degradation . |