Copertina

Robust Batch-Level Query Routing for Large Language Models under Cost and Capacity Constraints

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Markovic-Voronov, Jelena, Behdin, Kayhan, Xu, Yuanda, Zhou, Zhengze, Wang, Zhipeng, Mazumder, Rahul
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Sparse NMF with Archetypal Regularization: Computational and Robustness Properties
di: Behdin, Kayhan, et al.
Pubblicazione: (2021)

Sparse PCA: A New Scalable Estimator Based On Integer Programming
di: Behdin, Kayhan, et al.
Pubblicazione: (2021)

Reasoning Models Can be Accurately Pruned Via Chain-of-Thought Reconstruction
di: Lucas, Ryan, et al.
Pubblicazione: (2025)

Sampling for Quality: Training-Free Reward-Guided LLM Decoding via Sequential Monte Carlo
di: Markovic-Voronov, Jelena, et al.
Pubblicazione: (2026)

ALPS: Improved Optimization for Highly Sparse One-Shot Pruning for Large Language Models
di: Meng, Xiang, et al.
Pubblicazione: (2024)

Sparse Gaussian Graphical Models with Discrete Optimization: Computational and Statistical Perspectives
di: Behdin, Kayhan, et al.
Pubblicazione: (2023)

End-to-end Feature Selection Approach for Learning Skinny Trees
di: Ibrahim, Shibal, et al.
Pubblicazione: (2023)

Differentially Private High-dimensional Variable Selection via Integer Programming
di: Prastakos, Petros, et al.
Pubblicazione: (2025)

Beyond GRPO and On-Policy Distillation: An Empirical Sparse-to-Dense Reward Principle for Language-Model Post-Training
di: Xu, Yuanda, et al.
Pubblicazione: (2026)

Modeling with Categorical Features via Exact Fusion and Sparsity Regularisation
di: Behdin, Kayhan, et al.
Pubblicazione: (2026)

Overconfident Errors Need Stronger Correction: Asymmetric Confidence Penalties for Reinforcement Learning
di: Xu, Yuanda, et al.
Pubblicazione: (2026)

PACED: Distillation and On-Policy Self-Distillation at the Frontier of Student Competence
di: Xu, Yuanda, et al.
Pubblicazione: (2026)

Not all tokens are needed(NAT): token efficient reinforcement learning
di: Sang, Hejian, et al.
Pubblicazione: (2026)

TIP: Token Importance in On-Policy Distillation
di: Xu, Yuanda, et al.
Pubblicazione: (2026)

HASSLE-free: A unified Framework for Sparse plus Low-Rank Matrix Decomposition for LLMs
di: Makni, Mehdi, et al.
Pubblicazione: (2025)

OSSCAR: One-Shot Structured Pruning in Vision and Language Models with Combinatorial Optimization
di: Meng, Xiang, et al.
Pubblicazione: (2024)

Multi-Task Learning for Sparsity Pattern Heterogeneity: Statistical and Computational Perspectives
di: Behdin, Kayhan, et al.
Pubblicazione: (2022)

BP-Seg: A graphical model approach to unsupervised and non-contiguous text segmentation using belief propagation
di: Li, Fengyi, et al.
Pubblicazione: (2025)

Precision Tracked Transformer via Kalman Filtering, Kriging and Process Noise
di: Long, Bo, et al.
Pubblicazione: (2026)

Guarded Query Routing for Large Language Models
di: Šléher, Richard, et al.
Pubblicazione: (2025)

Graph Query Generation with Constraint-guided Large Language Agents
di: Wang, Mengying, et al.
Pubblicazione: (2026)

Beyond Query Memorization: Large Language Model Routing with Query Decomposition and Historical Matching
di: Lv, Bo, et al.
Pubblicazione: (2026)

CRISP: Compressed Reasoning via Iterative Self-Policy Distillation
di: Sang, Hejian, et al.
Pubblicazione: (2026)

Cequel: Cost-Effective Querying of Large Language Models for Text Clustering
di: Wang, Hongtao, et al.
Pubblicazione: (2025)

An Optimization Framework for Differentially Private Sparse Fine-Tuning
di: Makni, Mehdi, et al.
Pubblicazione: (2025)

ConsRoute:Consistency-Aware Adaptive Query Routing for Cloud-Edge-Device Large Language Models
di: Qiao, Haoyu, et al.
Pubblicazione: (2026)

An Aligned Constraint Programming Model For Serial Batch Scheduling With Minimum Batch Size
di: Huertas, Jorge A., et al.
Pubblicazione: (2025)

Hybrid LLM: Cost-Efficient and Quality-Aware Query Routing
di: Ding, Dujian, et al.
Pubblicazione: (2024)

Learning to Route Queries to Heads for Attention-based Re-ranking with Large Language Models
di: Tian, Yuxing, et al.
Pubblicazione: (2026)

Cocobo: Exploring Large Language Models as the Engine for End-User Robot Programming
di: Ge, Yate, et al.
Pubblicazione: (2024)

The Dark Side of Human Feedback: Poisoning Large Language Models via User Inputs
di: Chen, Bocheng, et al.
Pubblicazione: (2024)

Constraint Programming Models For Serial Batch Scheduling With Minimum Batch Size
di: Huertas, Jorge A., et al.
Pubblicazione: (2025)

RadialRouter: Structured Representation for Efficient and Robust Large Language Models Routing
di: Jin, Ruihan, et al.
Pubblicazione: (2025)

AnywhereVLA: Language-Conditioned Exploration and Mobile Manipulation
di: Gubernatorov, Konstantin, et al.
Pubblicazione: (2025)

Tula: Optimizing Time, Cost, and Generalization in Distributed Large-Batch Training
di: Tyagi, Sahil, et al.
Pubblicazione: (2026)

Competitive Facility Location under Random Utilities and Routing Constraints
di: Pham, Hoang Giang, et al.
Pubblicazione: (2024)

TSENOR: Highly-Efficient Algorithm for Finding Transposable N:M Sparse Masks
di: Meng, Xiang, et al.
Pubblicazione: (2025)

CP-Model-Zoo: A Natural Language Query System for Constraint Programming Models
di: Crespin, Augustin, et al.
Pubblicazione: (2025)

Doubly Robust Alignment for Large Language Models
di: Xu, Erhan, et al.
Pubblicazione: (2025)

NH-CROP: Robust Pricing for Governed Language Data Assets under Cost Uncertainty
di: Zheng, Xu, et al.
Pubblicazione: (2026)