Deep Delta Learning

arXiv:2601.00417 · cs.LG, cs.AI, cs.CL, cs.CV · Submitted 2026-01-01 · Read on arXiv

cs.LG, cs.AI, cs.CL, cs.CV

Submitted: 2026-01-01

Updated: 2026-09-25

Code: https://github.com/yifanzhang-pro/deep-delta-learning

Terminology

• Transformer — 33× in this paper · explained in 2 episodes
• Deep Delta Learning — 10× in this paper
• Ablation — 5× in this paper · explained in 1 episode
• Embeddings — 5× in this paper · explained in 2 episodes
• Perplexity — 5× in this paper · explained in 3 episodes
• Interpretability — 3× in this paper · explained in 15 episodes
• Adaptation — 2× in this paper · explained in 1 episode
• Accuracy — 1× in this paper · explained in 1 episode
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Inverse Problem — 1× in this paper · explained in 2 episodes
• KV cache — 1× in this paper · explained in 3 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Transformer Models — 1× in this paper · explained in 2 episodes

Sources

• HOFT: Householder Orthogonal Fine-tuning
• BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions
• Cross-Layer Retrospective Retrieving via Layer Attention
• O-ViT: Orthogonal Vision Transformer
• Chaos Meets Attention: Transformers for Large-Scale Dynamical Prediction
• Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering
• SocialIQA: Commonsense Reasoning about Social Interactions
• GLU Variants Improve Transformer
• Highway Networks
• Crowdsourcing Multiple Choice Science Questions
• mHC: Manifold-Constrained Hyper-Connections
• Quick and (not so) Dirty: Unsupervised Selection of Justification Sentences for Multi-hop Question Answering
• Tensor Programs V: Tuning Large Neural Networks via Zero-Shot Hyperparameter Transfer
• PaTH Attention: Position Encoding via Accumulating Householder Transformations

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