Copertina

Don't Stop Me Now: Embedding Based Scheduling for LLMs

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Shahout, Rana, Malach, Eran, Liu, Chunwei, Jiang, Weifan, Yu, Minlan, Mitzenmacher, Michael
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Intra-request branch orchestration for efficient LLM reasoning
di: Jiang, Weifan, et al.
Pubblicazione: (2025)

SkipPredict: When to Invest in Predictions for Scheduling
di: Shahout, Rana, et al.
Pubblicazione: (2024)

Learning-Based Heavy Hitters and Flow Frequency Estimation in Streams
di: Shahout, Rana, et al.
Pubblicazione: (2024)

From Score Distributions to Balance: Plug-and-Play Mixture-of-Experts Routing
di: Shahout, Rana, et al.
Pubblicazione: (2025)

Learning-Augmented Frequency Estimation in Sliding Windows
di: Shahout, Rana, et al.
Pubblicazione: (2024)

Fast Inference for Augmented Large Language Models
di: Shahout, Rana, et al.
Pubblicazione: (2024)

Orla: A Library for Serving LLM-Based Multi-Agent Systems
di: Shahout, Rana, et al.
Pubblicazione: (2026)

Queueing, Predictions, and LLMs: Challenges and Open Problems
di: Mitzenmacher, Michael, et al.
Pubblicazione: (2025)

Auto-Regressive Next-Token Predictors are Universal Learners
di: Malach, Eran
Pubblicazione: (2023)

Don't Stop Me Yet: Sampling Loss Minima via Dissipative Riemannian Mechanics
di: Jacobsen, Albert Kjøller, et al.
Pubblicazione: (2026)

Federated Learning Clients Clustering with Adaptation to Data Drifts
di: Li, Minghao, et al.
Pubblicazione: (2024)

The Power of Random Features and the Limits of Distribution-Free Gradient Descent
di: Karchmer, Ari, et al.
Pubblicazione: (2025)

Repeat After Me: Transformers are Better than State Space Models at Copying
di: Jelassi, Samy, et al.
Pubblicazione: (2024)

Don't Waste Your Time: Early Stopping Cross-Validation
di: Bergman, Edward, et al.
Pubblicazione: (2024)

Let Me Think! A Long Chain-of-Thought Can Be Worth Exponentially Many Short Ones
di: Mirtaheri, Parsa, et al.
Pubblicazione: (2025)

Don't Fool Me Twice: Adapting to Adversity in the Wild with Experience-Driven Reasoning
di: Ravie, Navin Sriram, et al.
Pubblicazione: (2026)

LLM Priors for ERM over Programs
di: Singhal, Shivam, et al.
Pubblicazione: (2025)

How Reinforcement Learning After Next-Token Prediction Facilitates Learning
di: Tsilivis, Nikolaos, et al.
Pubblicazione: (2025)

HACK: Homomorphic Acceleration via Compression of the Key-Value Cache for Disaggregated LLM Inference
di: Zhang, Zeyu, et al.
Pubblicazione: (2025)

Don't Stop Me Now: Investigating the Information Interactions Involved in Overcoming Creative Blocks
di: Patricia Sanchez, et al.
Pubblicazione: (2025)

To Backtrack or Not to Backtrack: When Sequential Search Limits Model Reasoning
di: Qin, Tian, et al.
Pubblicazione: (2025)

Experts Don't Cheat: Learning What You Don't Know By Predicting Pairs
di: Johnson, Daniel D., et al.
Pubblicazione: (2024)

Show Me What You Don't Know: Efficient Sampling from Invariant Sets for Model Validation
di: Rousselot, Armand, et al.
Pubblicazione: (2026)

Universal Length Generalization with Turing Programs
di: Hou, Kaiying, et al.
Pubblicazione: (2024)

Whitespaces Don't Lie: Feature-Driven and Embedding-Based Approaches for Detecting Machine-Generated Code
di: Nirob, Syed Mehedi Hasan, et al.
Pubblicazione: (2026)

Quantizing With Randomized Hadamard Transforms: Efficient Heuristic Now Proven
di: Ben-Basat, Ran, et al.
Pubblicazione: (2026)

Ignore Me But Don't Replace Me: Utilizing Non-Linguistic Elements for Pretraining on the Cybersecurity Domain
di: Jang, Eugene, et al.
Pubblicazione: (2024)

The Evolution of Statistical Induction Heads: In-Context Learning Markov Chains
di: Edelman, Benjamin L., et al.
Pubblicazione: (2024)

Don't Be Greedy, Just Relax! Pruning LLMs via Frank-Wolfe
di: Roux, Christophe, et al.
Pubblicazione: (2025)

Don't Transform the Code, Code the Transforms: Towards Precise Code Rewriting using LLMs
di: Cummins, Chris, et al.
Pubblicazione: (2024)

THC: Accelerating Distributed Deep Learning Using Tensor Homomorphic Compression
di: Li, Minghao, et al.
Pubblicazione: (2023)

If You Don't Understand It, Don't Use It: Eliminating Trojans with Filters Between Layers
di: Hernandez, Adriano
Pubblicazione: (2024)

Don't Get Me Wrong: How to Apply Deep Visual Interpretations to Time Series
di: Loeffler, Christoffer, et al.
Pubblicazione: (2022)

Bayesian Mixture-of-Experts: Towards Making LLMs Know What They Don't Know
di: Li, Albus Yizhuo
Pubblicazione: (2025)

Don't Mesh with Me: Generating Constructive Solid Geometry Instead of Meshes by Fine-Tuning a Code-Generation LLM
di: Mews, Maximilian, et al.
Pubblicazione: (2024)

PALS: Power-Aware LLM Serving for Mixture-of-Experts Models
di: Hankendi, Can, et al.
Pubblicazione: (2026)

Don't Freeze, Don't Crash: Extending the Safe Operating Range of Neural Navigation in Dense Crowds
di: Zhang, Jiefu, et al.
Pubblicazione: (2026)

Loss-to-Loss Prediction: Scaling Laws for All Datasets
di: Brandfonbrener, David, et al.
Pubblicazione: (2024)

What LLMs Think When You Don't Tell Them What to Think About?
di: Kwon, Yongchan, et al.
Pubblicazione: (2026)

Position: Don't be Afraid of Over-Smoothing And Over-Squashing
di: Kormann, Niklas, et al.
Pubblicazione: (2026)