Author

Sriman Achanta

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning Preprint Sep 2026

FoldAttention: Declared-Reference Softmax for Fast Decode and Deterministic Backward

FoldAttention is presented, an additive formulation of softmax attention that fixes a finite reference $Z_i$ before scanning the KV cache and removes the determinism tax.

Sriman Achanta · 0 citations