Imagen de Portada

STEER: Inference-Time Risk Control via Constrained Quality-Diversity Search

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Yang, Eric, Lee, Jong Ha, Amar, Jonathan, Ye, Elissa, Jia, Yugang
Formato:	Preprint
Publicado:	2026
Materias:	Artificial Intelligence Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

DEI: Diversity in Evolutionary Inference for Quality-Diversity Search
por: Donaghy, John, et al.
Publicado: (2026)

The Geometry of Queries: Query-Based Innovations in Retrieval-Augmented Generation for Healthcare QA
por: Yang, Eric, et al.
Publicado: (2024)

LPDP: Inference-Time Reward Control for Variable-Length DNA Generation with Edit Flows
por: Kim, Jeongchan, et al.
Publicado: (2026)

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

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

Controllable Graph Generation with Diffusion Models via Inference-Time Tree Search Guidance
por: Zhao, Jiachi, et al.
Publicado: (2025)

Rating Quality of Diverse Time Series Data by Meta-learning from LLM Judgment
por: Wu, Shunyu, et al.
Publicado: (2025)

Optimizing Diversity and Quality through Base-Aligned Model Collaboration
por: Wang, Yichen, et al.
Publicado: (2025)

Dynamic Search for Inference-Time Alignment in Diffusion Models
por: Li, Xiner, et al.
Publicado: (2025)

RosettaSearch: Multi-Objective Inference-Time Search for Protein Sequence Design
por: Kshirsagar, Meghana, et al.
Publicado: (2026)

Thermodynamic Focusing for Inference-Time Search: Practical Methods for Target-Conditioned Sampling and Prompted Inference
por: Zhang, Zhan
Publicado: (2025)

Sleepless Nights, Sugary Days: Creating Synthetic Users with Health Conditions for Realistic Coaching Agent Interactions
por: Yun, Taedong, et al.
Publicado: (2025)

CCS: Controllable and Constrained Sampling with Diffusion Models via Initial Noise Perturbation
por: Song, Bowen, et al.
Publicado: (2025)

Beyond Inference-Time Search: Reinforcement Learning Synthesizes Reusable Solvers
por: Massoudi, Soheyl, et al.
Publicado: (2026)

DARC: Disagreement-Aware Alignment via Risk-Constrained Decoding
por: Zou, Mingxi, et al.
Publicado: (2026)

Progressive Weight Loading: Accelerating Initial Inference and Gradually Boosting Performance on Resource-Constrained Environments
por: Kim, Hyunwoo, et al.
Publicado: (2025)

SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning
por: Pan, Rui, et al.
Publicado: (2025)

GuidedSampling: Steering LLMs Towards Diverse Candidate Solutions at Inference-Time
por: Handa, Divij, et al.
Publicado: (2025)

Controlling the Risk of Corrupted Contexts for Language Models via Early-Exiting
por: Wynn, Andrea, et al.
Publicado: (2025)

When LLM Meets Time Series: Can LLMs Perform Multi-Step Time Series Reasoning and Inference
por: Ye, Wen, et al.
Publicado: (2025)

Foundation Model of Electronic Medical Records for Adaptive Risk Estimation
por: Renc, Pawel, et al.
Publicado: (2025)

Representation Learning of Lab Values via Masked AutoEncoders
por: Restrepo, David, et al.
Publicado: (2025)

Towards Safe Reinforcement Learning via Constraining Conditional Value-at-Risk
por: Ying, Chengyang, et al.
Publicado: (2022)

GCoDE: Efficient Device-Edge Co-Inference for GNNs via Architecture-Mapping Co-Search
por: Zhou, Ao, et al.
Publicado: (2025)

Monitoring Risks in Test-Time Adaptation
por: Schirmer, Mona, et al.
Publicado: (2025)

Best-of-Tails: Bridging Optimism and Pessimism in Inference-Time Alignment
por: Hsu, Hsiang, et al.
Publicado: (2026)

Diverse Text-to-Image Generation via Contrastive Noise Optimization
por: Kim, Byungjun, et al.
Publicado: (2025)

SPARQ: Synthetic Problem Generation for Reasoning via Quality-Diversity Algorithms
por: Havrilla, Alex, et al.
Publicado: (2025)

ControlTraj: Controllable Trajectory Generation with Topology-Constrained Diffusion Model
por: Zhu, Yuanshao, et al.
Publicado: (2024)

Memory- and Latency-Constrained Inference of Large Language Models via Adaptive Split Computing
por: Sung, Mingyu, et al.
Publicado: (2025)

Aligning Few-Step Generative Models by Amortizing Sample-based Variational Inference
por: Lee, Jaewoo, et al.
Publicado: (2026)

Quality-Diversity Actor-Critic: Learning High-Performing and Diverse Behaviors via Value and Successor Features Critics
por: Grillotti, Luca, et al.
Publicado: (2024)

Archon: An Architecture Search Framework for Inference-Time Techniques
por: Saad-Falcon, Jon, et al.
Publicado: (2024)

PromptLoop: Plug-and-Play Prompt Refinement via Latent Feedback for Diffusion Model Alignment
por: Lee, Suhyeon, et al.
Publicado: (2025)

Rethinking Multimodal Fusion for Time Series: Auxiliary Modalities Need Constrained Fusion
por: Lee, Seunghan, et al.
Publicado: (2026)

QLASS: Boosting Language Agent Inference via Q-Guided Stepwise Search
por: Lin, Zongyu, et al.
Publicado: (2025)

Search-Augmented Masked Diffusion Models for Constrained Generation
por: Ta, Huu Binh, et al.
Publicado: (2026)

TS-Reasoner: Domain-Oriented Time Series Inference Agents for Reasoning and Automated Analysis
por: Ye, Wen, et al.
Publicado: (2024)

Finding the Sweet Spot: Trading Quality, Cost, and Speed During Inference-Time LLM Reflection
por: Butler, Jack, et al.
Publicado: (2025)

Calibrated Test-Time Guidance for Bayesian Inference
por: Geyfman, Daniel, et al.
Publicado: (2026)