Pretraining Latent Information Feedback Transformers with Teacher Supervision
cs.CL
Submitted: 2026-09-29
Updated: 2026-09-29
Code: https://github.com/dortirosh1/LIFT
Terminology
Sources
- Program Synthesis with Large Language Models
- T^2MLR: Transformer with Temporal Middle-Layer Recurrence
- Evaluating Large Language Models Trained on Code
- Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
- Training Verifiers to Solve Math Word Problems
- DeepSeek-V3 Technical Report
- Gemma 2: Improving Open Language Models at a Practical Size
- Distilling the Knowledge in a Neural Network
- Pretraining Recurrent Networks without Recurrence
- Sequence Level Training with Recurrent Neural Networks
- The Illusion of Superposition? A Principled Analysis of Latent Thinking in Language Models
- GLU Variants Improve Transformer
- Olmo 3
- WhiteMatter: All-to-All Cross-Layer Connections via KV Source Mixing
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering