Loopback Transformer: Towards a Unified View of Residual Looped Transformers
cs.LG
Submitted: 2026-11-04
Updated: 2026-11-04
Code: https://github.com/yancyou/Loopback
Terminology
Sources
- Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality
- Universal Transformers
- Mamba: Linear-Time Sequence Modeling with Selective State Spaces
- Efficiently Modeling Long Sequences with Structured State Spaces
- Densely Connected Convolutional Networks
- ALBERT: A Lite BERT for Self-supervised Learning of Language Representations
- Delta Attention Residuals
- Multi-Head Attention Residuals
- RWKV-7 "Goose" with Expressive Dynamic State Evolution
- HGRN2: Gated Linear RNNs with State Expansion
- Highway Networks
- Retentive Network: A Successor to Transformer for Large Language Models
- Kimi Linear: An Expressive, Efficient Attention Architecture
- Attention Residuals
- Uncovering mesa-optimization algorithms in Transformers
- mHC: Manifold-Constrained Hyper-Connections
- Gated Linear Attention Transformers with Hardware-Efficient Training
- Stabilizing Recurrent Dynamics for Test-Time Scalable Latent Reasoning in Looped Language Models
- Hyperloop Transformers
- Scaling Latent Reasoning via Looped Language Models
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis