Image de couverture de livre

Thermodynamic Focusing for Inference-Time Search: Practical Methods for Target-Conditioned Sampling and Prompted Inference

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteur principal:	Zhang, Zhan
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Thermodynamic Diffusion Inference with Minimal Digital Conditioning
par: De, Aditi
Publié: (2026)

Sample, Scrutinize and Scale: Effective Inference-Time Search by Scaling Verification
par: Zhao, Eric, et autres
Publié: (2025)

Dynamic Search for Inference-Time Alignment in Diffusion Models
par: Li, Xiner, et autres
Publié: (2025)

Adaptive Inference-Time Scaling via Cyclic Diffusion Search
par: Lee, Gyubin, et autres
Publié: (2025)

Beyond Inference-Time Search: Reinforcement Learning Synthesizes Reusable Solvers
par: Massoudi, Soheyl, et autres
Publié: (2026)

RosettaSearch: Multi-Objective Inference-Time Search for Protein Sequence Design
par: Kshirsagar, Meghana, et autres
Publié: (2026)

Reprompting: Automated Chain-of-Thought Prompt Inference Through Gibbs Sampling
par: Xu, Weijia, et autres
Publié: (2023)

Semantically-Guided Inference for Conditional Diffusion Models: Enhancing Covariate Consistency in Time Series Forecasting
par: Ding, Rui, et autres
Publié: (2025)

STEER: Inference-Time Risk Control via Constrained Quality-Diversity Search
par: Yang, Eric, et autres
Publié: (2026)

Archon: An Architecture Search Framework for Inference-Time Techniques
par: Saad-Falcon, Jon, et autres
Publié: (2024)

TreeBoN: Enhancing Inference-Time Alignment with Speculative Tree-Search and Best-of-N Sampling
par: Qiu, Jiahao, et autres
Publié: (2024)

Demonstrating the Continual Learning Capabilities and Practical Application of Discrete-Time Active Inference
par: Prakki, Rithvik
Publié: (2024)

Progressive Inference-Time Annealing of Diffusion Models for Sampling from Boltzmann Densities
par: Akhound-Sadegh, Tara, et autres
Publié: (2025)

GuidedSampling: Steering LLMs Towards Diverse Candidate Solutions at Inference-Time
par: Handa, Divij, et autres
Publié: (2025)

Martingale Foresight Sampling: A Principled Approach to Inference-Time LLM Decoding
par: Li, Huayu, et autres
Publié: (2026)

ProRefine: Inference-Time Prompt Refinement with Textual Feedback
par: Pandita, Deepak, et autres
Publié: (2025)

A Practical Approach to Causal Inference over Time
par: Cinquini, Martina, et autres
Publié: (2024)

Rollout Roulette: A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods
par: Puri, Isha, et autres
Publié: (2025)

DEI: Diversity in Evolutionary Inference for Quality-Diversity Search
par: Donaghy, John, et autres
Publié: (2026)

From Prompts to Power: Measuring the Energy Footprint of LLM Inference
par: Caravaca, Francisco, et autres
Publié: (2025)

Hyperparameter Trajectory Inference with Conditional Lagrangian Optimal Transport
par: Amad, Harry, et autres
Publié: (2026)

Generalization and Membership Inference Attack a Practical Perspective
par: Rahmani, Fateme, et autres
Publié: (2026)

Diversified Scaling Inference in Time Series Foundation Models
par: Hua, Ruijin, et autres
Publié: (2026)

UnIT: Scalable Unstructured Inference-Time Pruning for MAC-efficient Neural Inference on MCUs
par: Neth, Ashe, et autres
Publié: (2025)

Flash Inference: Near Linear Time Inference for Long Convolution Sequence Models and Beyond
par: Oncescu, Costin-Andrei, et autres
Publié: (2024)

Learning to Condition: A Neural Heuristic for Scalable MPE Inference
par: Malhotra, Brij, et autres
Publié: (2025)

How does Bayesian Sampling help Membership Inference Attacks?
par: Liu, Zhenlong, et autres
Publié: (2025)

Large Language Monkeys: Scaling Inference Compute with Repeated Sampling
par: Brown, Bradley, et autres
Publié: (2024)

Assessing Per-Sample Membership Inference Vulnerability without Retraining
par: Dorseuil, Valentin, et autres
Publié: (2026)

Inference Time Context Sparsity: Illusion or Opportunity?
par: Joshi, Sahil, et autres
Publié: (2026)

Learnable Chernoff Baselines for Inference-Time Alignment
par: Madhow, Sunil, et autres
Publié: (2026)

Calibrated Test-Time Guidance for Bayesian Inference
par: Geyfman, Daniel, et autres
Publié: (2026)

Green Prompting: Characterizing Prompt-driven Energy Costs of LLM Inference
par: Adamska, Marta, et autres
Publié: (2025)

$ϕ$-Decoding: Adaptive Foresight Sampling for Balanced Inference-Time Exploration and Exploitation
par: Xu, Fangzhi, et autres
Publié: (2025)

Learning to Guide Local Search for MPE Inference in Probabilistic Graphical Models
par: Malhotra, Brij, et autres
Publié: (2026)

DistPred: A Distribution-Free Probabilistic Inference Method for Regression and Forecasting
par: Liang, Daojun, et autres
Publié: (2024)

ConDiSim: Conditional Diffusion Models for Simulation Based Inference
par: Nautiyal, Mayank, et autres
Publié: (2025)

ILRR: Inference-Time Steering Method for Masked Diffusion Language Models
par: Avrahami, Eden, et autres
Publié: (2026)

Role-Aware Conditional Inference for Spatiotemporal Ecosystem Carbon Flux Prediction
par: Sun, Yiming, et autres
Publié: (2026)

Decocted Experience Improves Test-Time Inference in LLM Agents
par: Shen, Maohao, et autres
Publié: (2026)