Write Back the: Revisiting the Same Tokens with Fresh Representations
cs.LG
Submitted: 2026-09-26
Updated: 2026-09-26
Code: https://github.com/gooogleshanghai/reflux
Terminology
Sources
- PonderNet: Learning to Ponder
- Eliciting Latent Predictions from Transformers with the Tuned Lens
- Understanding (Un)Reliability of Steering Vectors in Language Models
- T^2MLR: Transformer with Temporal Middle-Layer Recurrence
- Training-Free Looped Transformers
- Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
- Training Verifiers to Solve Math Word Problems
- Universal Transformers
- Implicit Chain of Thought Reasoning via Knowledge Distillation
- The Pile: An 800GB Dataset of Diverse Text for Language Modeling
- Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models
- Adaptive Computation Time for Recurrent Neural Networks
- Training Large Language Models to Reason in a Continuous Latent Space
- Measuring Massive Multitask Language Understanding
- LoRA: Low-Rank Adaptation of Large Language Models
- Global Evolutionary Steering: Refining Activation Steering Control via Cross-Layer Consistency
- Less is More: Recursive Reasoning with Tiny Networks
- Loop, Think, & Generalize: Implicit Reasoning in Recurrent-Depth Transformers
- Encode, Think, Decode: Scaling test-time reasoning with recursive latent thoughts
- Mix-LN: Unleashing the Power of Deeper Layers by Combining Pre-LN and Post-LN
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks