Imagen de Portada

UniScale: Adaptive Unified Inference Scaling via Online Joint Optimization of Model Routing and Test-Time Scaling

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Huang, Kaiyu, Wang, Xingyu, Kong, Mingze, Shi, Zhubo, Hou, Yuqian, Xu, Hong, Dai, Zhongxiang, Yu, Minchen, Shi, Qingjiang
Formato:	Preprint
Publicado:	2026
Materias:	Artificial Intelligence Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

AdaSpec: Adaptive Speculative Decoding for Fast, SLO-Aware Large Language Model Serving
por: Huang, Kaiyu, et al.
Publicado: (2025)

UniScale: Unified Scale-Aware 3D Reconstruction for Multi-View Understanding via Prior Injection for Robotic Perception
por: Mahdavian, Mohammad, et al.
Publicado: (2026)

UniT: Unified Multimodal Chain-of-Thought Test-time Scaling
por: Chen, Leon Liangyu, et al.
Publicado: (2026)

Meta-Prompt Optimization for LLM-Based Sequential Decision Making
por: Kong, Mingze, et al.
Publicado: (2025)

ALSO: Adversarial Online Strategy Optimization for Social Agents
por: Li, Xiang, et al.
Publicado: (2026)

T-POP: Test-Time Personalization with Online Preference Feedback
por: Qu, Zikun, et al.
Publicado: (2025)

UniBlendNet: Unified Global, Multi-Scale, and Region-Adaptive Modeling for Ambient Lighting Normalization
por: Dai, Jiatao, et al.
Publicado: (2026)

UniMixer: A Unified Architecture for Scaling Laws in Recommendation Systems
por: Ha, Mingming, et al.
Publicado: (2026)

Workflow-R1: Group Sub-sequence Policy Optimization for Multi-turn Workflow Construction
por: Kong, Mingze, et al.
Publicado: (2026)

From Scale to Speed: Adaptive Test-Time Scaling for Image Editing
por: Qu, Xiangyan, et al.
Publicado: (2026)

RoBoN: Routed Online Best-of-n for Test-Time Scaling with Multiple LLMs
por: Geuter, Jonathan, et al.
Publicado: (2025)

Guided Trajectory Optimization with Sparse Scaling for Test-Time Diffusion
por: Dai, Gang, et al.
Publicado: (2026)

Heat Capacity and the Violation of Scaling Laws in Gravitational System
por: Kong, Shi-Bei
Publicado: (2025)

λScale: Enabling Fast Scaling for Serverless Large Language Model Inference
por: Yu, Minchen, et al.
Publicado: (2025)

LATTS: Locally Adaptive Test-Time Scaling
por: Uscidda, Theo, et al.
Publicado: (2025)

Online Clustering of Dueling Bandits
por: Wang, Zhiyong, et al.
Publicado: (2025)

Uni-Sign: Toward Unified Sign Language Understanding at Scale
por: Li, Zecheng, et al.
Publicado: (2025)

UniGen: Enhanced Training & Test-Time Strategies for Unified Multimodal Understanding and Generation
por: Tian, Rui, et al.
Publicado: (2025)

Adaptive Rectification Sampling for Test-Time Compute Scaling
por: Tan, Zhendong, et al.
Publicado: (2025)

Atom of Thoughts for Markov LLM Test-Time Scaling
por: Teng, Fengwei, et al.
Publicado: (2025)

Uni-MoE: Scaling Unified Multimodal LLMs with Mixture of Experts
por: Li, Yunxin, et al.
Publicado: (2024)

UniPinRec: Unifying Generative Retrieval and Ranking at Pinterest Scale
por: Li, Hanyu, et al.
Publicado: (2026)

EC-DIT: Scaling Diffusion Transformers with Adaptive Expert-Choice Routing
por: Sun, Haotian, et al.
Publicado: (2024)

Structure-Adaptive Conformal Inference for Large-Scale Out-of-Distribution Testing
por: Sun, Rongyi, et al.
Publicado: (2026)

Adaptive Inference-Time Scaling via Cyclic Diffusion Search
por: Lee, Gyubin, et al.
Publicado: (2025)

MASPOB: Bandit-Based Prompt Optimization for Multi-Agent Systems with Graph Neural Networks
por: Hong, Zhi, et al.
Publicado: (2026)

Online Statistical Inference of Constrained Stochastic Optimization via Random Scaling
por: Du, Xinchen, et al.
Publicado: (2025)

Chain of Methodologies: Scaling Test Time Computation without Training
por: Liu, Cong, et al.
Publicado: (2025)

MarkovScale: Towards Optimal Sequential Scaling at Inference Time
por: Wang, Youkang, et al.
Publicado: (2026)

Joint Node Selection and Resource Allocation Optimization for Cooperative Sensing with a Shared Wireless Backhaul
por: Chen, Mingxin, et al.
Publicado: (2024)

Agentar-Scale-SQL: Advancing Text-to-SQL through Orchestrated Test-Time Scaling
por: Wang, Pengfei, et al.
Publicado: (2025)

Dual-Scale Channel Estimation in Sensing-Assisted Communication Systems: Joint Time Allocation and Beamforming Design
por: Zhiyue, Bai, et al.
Publicado: (2024)

Linguistic Generalizability of Test-Time Scaling in Mathematical Reasoning
por: Son, Guijin, et al.
Publicado: (2025)

Scaling over Scaling: Exploring Test-Time Scaling Plateau in Large Reasoning Models
por: Wang, Jian, et al.
Publicado: (2025)

MetaScale: Test-Time Scaling with Evolving Meta-Thoughts
por: Liu, Qin, et al.
Publicado: (2025)

When to Vote, When to Rewrite: Disagreement-Guided Strategy Routing for Test-Time Scaling
por: Lin, Zhimin, et al.
Publicado: (2026)

Inference-Time Scaling for Diffusion Models beyond Scaling Denoising Steps
por: Ma, Nanye, et al.
Publicado: (2025)

Sample, Scrutinize and Scale: Effective Inference-Time Search by Scaling Verification
por: Zhao, Eric, et al.
Publicado: (2025)

ScalingNoise: Scaling Inference-Time Search for Generating Infinite Videos
por: Yang, Haolin, et al.
Publicado: (2025)

UniRoute: Unified Routing Mixture-of-Experts for Modality-Adaptive Remote Sensing Change Detection
por: Shu, Qingling, et al.
Publicado: (2026)