AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

BiCycle: Group-wise Recursive Transformer Based on ASR Mechanism

Min Ho Jang, Eun Seo Seo, Jin Young Kim, Hyeongsoo Lim, Ji Won Yoon

AAAI 2026 · Architectures and efficiency › Attention and transformers · approach: Efficient language transformers · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use BiCycle group-wise recursion instead of CYCLEConformer-CTC · LibriSpeech test-other (depth ~16-18)WER: 9.30% -> 9.11%Improved
increase recursion steps (depth 16 to 20) in BiCycle (ablation)BiCycle · LibriSpeech test-otherWER: 9.11% -> 8.93%Improved
increase recursion depth for conventional RT (CYCLE 18 to 27) (ablation)CYCLE · LibriSpeech test-otherWER: 9.30% -> 10.23%Hurt
use SEQUENCE structure with depth 27 (ablation)SEQUENCE · LibriSpeechWER: did not convergeHurt
add recursion to BiCycle (vs w/o recursion) (ablation)BiCycle · Common Voice 7.0 French testWER: 13.16% -> 12.38%Improved
use Relaxed Recursive Transformer with LoRA-style relaxationRelaxed Recursive Transformer · LibriSpeech test-otherWER: 11.44% -> 16.55%Hurt
add logit KD to BiCycle (ablation)BiCycle · LibriSpeech test-otherWER: 9.11% -> 8.64%Improved
use group-wise feature distillation instead of FitNets final-layer distillation (ablation)BiCycle · LibriSpeech test-otherWER: 8.51% -> 8.43% (depth 20); 8.53% -> 8.14% (depth 23)Improved
use GFD instead of FitNets (ablation)BiCycle depth 23 · LibriSpeech test-cleanWER: 3.50% -> 3.53%Mixed
single recursion step in each group (RP:1 RK:1) (ablation)BiCycle · LibriSpeech test-otherWER: 11.44% -> 9.88%Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy