Tagged articles

latent compression

1 articles · Page 1 of 1
Xiaohongshu Tech REDtech
Xiaohongshu Tech REDtech
Jul 10, 2026 · Artificial Intelligence

PIPO: Pair‑In Pair‑Out Architecture Cuts Input Length in Half and Doubles Token Output for LLMs

The PIPO (Pair‑In, Pair‑Out) architecture compresses two input tokens into one latent vector and expands each hidden state to emit an extra draft token, halving effective input length and doubling per‑step output, achieving up to +7.15 pass@4 improvement and 2.64× TTFT / 2.07× TPOT speedups on benchmarks such as AIME 2025, GPQA‑Diamond, LiveCodeBench v6 and LongBench v2 with Qwen3.5‑4B/9B backbones.

Multi-Token PredictionSpeculative Decodingefficiency
0 likes · 14 min read
PIPO: Pair‑In Pair‑Out Architecture Cuts Input Length in Half and Doubles Token Output for LLMs