Cover Image

You Only Need Your Transformer 25% of the Time: Meaning-First Execution for Eliminating Unnecessary Inference

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Shamim, Ryan
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

You Only Debias Once: Towards Flexible Accuracy-Fairness Trade-offs at Inference Time
by: Han, Xiaotian, et al.
Published: (2025)

Attention Once Is All You Need: Efficient Streaming Inference with Stateful Transformers
by: Norgren, Victor
Published: (2026)

Adaptive Test-Time Training for Predicting Need for Invasive Mechanical Ventilation in Multi-Center Cohorts
by: Lu, Xiaolei, et al.
Published: (2025)

The Residual Stream Is All You Need: On the Redundancy of the KV Cache in Transformer Inference
by: Qasim, Kaleem Ullah, et al.
Published: (2026)

Attention Is All You Need But You Don't Need All Of It For Inference of Large Language Models
by: Tyukin, Georgy, et al.
Published: (2024)

Probabilities Are All You Need: A Probability-Only Approach to Uncertainty Estimation in Large Language Models
by: Nguyen, Manh, et al.
Published: (2025)

Context is All You Need
by: Delanois, Jean Erik, et al.
Published: (2026)

You Only Accept Samples Once: Fast, Self-Correcting Stochastic Variational Inference
by: Dayta, Dominic B.
Published: (2024)

Catch-Up Distillation: You Only Need to Train Once for Accelerating Sampling
by: Shao, Shitong, et al.
Published: (2023)

You Only Need Minimal RLVR Training: Extrapolating LLMs via Rank-1 Trajectories
by: Wei, Zhepei, et al.
Published: (2026)

Occam's Razor is Only as Sharp as Your ELBO
by: Harvey, Ethan, et al.
Published: (2026)

Scalable Data Attribution via Forward-Only Test-Time Inference
by: Ma, Sibo, et al.
Published: (2025)

Mamba or Transformer for Time Series Forecasting? Mixture of Universals (MoU) Is All You Need
by: Peng, Sijia, et al.
Published: (2024)

SmartMem: Layout Transformation Elimination and Adaptation for Efficient DNN Execution on Mobile
by: Niu, Wei, et al.
Published: (2024)

You Only Train Once
by: Sakaridis, Christos
Published: (2025)

Attention is All You Need Until You Need Retention
by: Yaslioglu, M. Murat
Published: (2025)

Harnesses for Inference-Time Alignment over Execution Trajectories
by: Wang, Boyuan, et al.
Published: (2026)

FUNU: Boosting Machine Unlearning Efficiency by Filtering Unnecessary Unlearning
by: Li, Zitong, et al.
Published: (2025)

Accuracy is Not All You Need
by: Dutta, Abhinav, et al.
Published: (2024)

Attention Is Not All You Need: The Importance of Feedforward Networks in Transformer Models
by: Gerber, Isaac
Published: (2025)

Are High-Degree Representations Really Unnecessary in Equivariant Graph Neural Networks?
by: Cen, Jiacheng, et al.
Published: (2024)

Embedding Is (Almost) All You Need: Retrieval-Augmented Inference for Generalizable Genomic Prediction Tasks
by: Datta, Nirjhor, et al.
Published: (2025)

Triplet Interaction Improves Graph Transformers: Accurate Molecular Graph Learning with Triplet Graph Transformers
by: Hussain, Md Shamim, et al.
Published: (2024)

Masked Generative Transformer Is What You Need for Image Editing
by: Chow, Wei, et al.
Published: (2026)

Simple Feedfoward Neural Networks are Almost All You Need for Time Series Forecasting
by: Sun, Fan-Keng, et al.
Published: (2025)

Relevance Isn't All You Need: Scaling RAG Systems With Inference-Time Compute Via Multi-Criteria Reranking
by: LeVine, Will, et al.
Published: (2025)

Grokking as Structural Inference: Transformers Need Bayesian Lottery Tickets
by: Hidajat, Kai, et al.
Published: (2026)

Optimisation Is Not What You Need
by: Ibias, Alfredo
Published: (2025)

Some Attention is All You Need for Retrieval
by: Michalak, Felix, et al.
Published: (2025)

Half Search Space is All You Need
by: Rumiantsev, Pavel, et al.
Published: (2025)

Top-$nσ$: Not All Logits Are You Need
by: Tang, Chenxia, et al.
Published: (2024)

Transformers Don't Need LayerNorm at Inference Time: Scaling LayerNorm Removal to GPT-2 XL and the Implications for Mechanistic Interpretability
by: Baroni, Luca, et al.
Published: (2025)

Positional Knowledge is All You Need: Position-induced Transformer (PiT) for Operator Learning
by: Chen, Junfeng, et al.
Published: (2024)

Improving Prediction of Need for Mechanical Ventilation using Cross-Attention
by: Mohanty, Anwesh, et al.
Published: (2024)

You Only Spike Once: Improving Energy-Efficient Neuromorphic Inference to ANN-Level Accuracy
by: P, Srivatsa, et al.
Published: (2020)

Deterministic Inference across Tensor Parallel Sizes That Eliminates Training-Inference Mismatch
by: Zhang, Ziyang, et al.
Published: (2025)

Memory Is All You Need: An Overview of Compute-in-Memory Architectures for Accelerating Large Language Model Inference
by: Wolters, Christopher, et al.
Published: (2024)

Ask Your Distribution Shift if Pre-Training is Right for You
by: Cohen-Wang, Benjamin, et al.
Published: (2024)

You Only Train Once: Differentiable Subset Selection for Omics Data
by: Chopard, Daphné, et al.
Published: (2025)

Attention-Only Transformers via Unrolled Subspace Denoising
by: Wang, Peng, et al.
Published: (2025)