Dynamic Search for Inference-Time Alignment in Diffusion Models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Li, Xiner, Uehara, Masatoshi, Su, Xingyu, Scalia, Gabriele, Biancalani, Tommaso, Regev, Aviv, Levine, Sergey, Ji, Shuiwang
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Reward-Guided Iterative Refinement in Diffusion Models at Test-Time with Applications to Protein and DNA Design
di: Uehara, Masatoshi, et al.
Pubblicazione: (2025)

Inference-Time Alignment in Diffusion Models with Reward-Guided Generation: Tutorial and Review
di: Uehara, Masatoshi, et al.
Pubblicazione: (2025)

Derivative-Free Guidance in Continuous and Discrete Diffusion Models with Soft Value-Based Decoding
di: Li, Xiner, et al.
Pubblicazione: (2024)

Iterative Distillation for Reward-Guided Fine-Tuning of Diffusion Models in Biomolecular Design
di: Su, Xingyu, et al.
Pubblicazione: (2025)

Adding Conditional Control to Diffusion Models with Reinforcement Learning
di: Zhao, Yulai, et al.
Pubblicazione: (2024)

Bridging Model-Based Optimization and Generative Modeling via Conservative Fine-Tuning of Diffusion Models
di: Uehara, Masatoshi, et al.
Pubblicazione: (2024)

Understanding Reinforcement Learning-Based Fine-Tuning of Diffusion Models: A Tutorial and Review
di: Uehara, Masatoshi, et al.
Pubblicazione: (2024)

Fine-Tuning of Continuous-Time Diffusion Models as Entropy-Regularized Control
di: Uehara, Masatoshi, et al.
Pubblicazione: (2024)

Fine-Tuning Discrete Diffusion Models via Reward Optimization with Applications to DNA and Protein Design
di: Wang, Chenyu, et al.
Pubblicazione: (2024)

Feedback Efficient Online Fine-Tuning of Diffusion Models
di: Uehara, Masatoshi, et al.
Pubblicazione: (2024)

Hierarchically branched diffusion models leverage dataset structure for class-conditional generation
di: Tseng, Alex M., et al.
Pubblicazione: (2022)

Active Test-Time Adaptation: Theoretical Analyses and An Algorithm
di: Gui, Shurui, et al.
Pubblicazione: (2024)

Language Models for Controllable DNA Sequence Design
di: Su, Xingyu, et al.
Pubblicazione: (2025)

Joint Embedding vs Reconstruction: Provable Benefits of Latent Space Prediction for Self Supervised Learning
di: Van Assel, Hugues, et al.
Pubblicazione: (2025)

Functional Graphical Models: Structure Enables Offline Data-Driven Optimization
di: Kuba, Jakub Grudzien, et al.
Pubblicazione: (2024)

A Hierarchical Language Model For Interpretable Graph Reasoning
di: Khurana, Sambhav, et al.
Pubblicazione: (2024)

RAG-Enhanced Collaborative LLM Agents for Drug Discovery
di: Lee, Namkyeong, et al.
Pubblicazione: (2025)

E-valuator: Reliable Agent Verifiers with Sequential Hypothesis Testing
di: Sadhuka, Shuvom, et al.
Pubblicazione: (2025)

MolCap-Arena: A Comprehensive Captioning Benchmark on Language-Enhanced Molecular Property Prediction
di: Edwards, Carl, et al.
Pubblicazione: (2024)

Inference-Time Alignment of Diffusion Models with Direct Noise Optimization
di: Tang, Zhiwei, et al.
Pubblicazione: (2024)

Inference-Time Computations for LLM Reasoning and Planning: A Benchmark and Insights
di: Parashar, Shubham, et al.
Pubblicazione: (2025)

Inference-Time Alignment Control for Diffusion Models with Reinforcement Learning Guidance
di: Jin, Luozhijie, et al.
Pubblicazione: (2025)

A mechanistically interpretable neural network for regulatory genomics
di: Tseng, Alex M., et al.
Pubblicazione: (2024)

DC-W2S: Dual-Consensus Weak-to-Strong Training for Reliable Process Reward Modeling in Biological Reasoning
di: Chan, Chi-Min, et al.
Pubblicazione: (2026)

Contextualizing biological perturbation experiments through language
di: Wu, Menghua, et al.
Pubblicazione: (2025)

Knowledgeable Language Models as Black-Box Optimizers for Personalized Medicine
di: Yao, Michael S., et al.
Pubblicazione: (2025)

Learning to Discover Regulatory Elements for Gene Expression Prediction
di: Su, Xingyu, et al.
Pubblicazione: (2025)

Discovering Physics Laws of Dynamical Systems via Invariant Function Learning
di: Gui, Shurui, et al.
Pubblicazione: (2025)

Empowering GNNs via Edge-Aware Weisfeiler-Leman Algorithm
di: Liu, Meng, et al.
Pubblicazione: (2022)

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

Geometry Informed Tokenization of Molecules for Language Model Generation
di: Li, Xiner, et al.
Pubblicazione: (2024)

Provable Reward-Agnostic Preference-Based Reinforcement Learning
di: Zhan, Wenhao, et al.
Pubblicazione: (2023)

Model Alignment Search
di: Grant, Satchel
Pubblicazione: (2025)

Real-Time Execution of Action Chunking Flow Policies
di: Black, Kevin, et al.
Pubblicazione: (2025)

Equivariant Graph Network Approximations of High-Degree Polynomials for Force Field Prediction
di: Xu, Zhao, et al.
Pubblicazione: (2024)

Navigating the Exploration-Exploitation Tradeoff in Inference-Time Scaling of Diffusion Models
di: Su, Xun, et al.
Pubblicazione: (2025)

Learnable Chernoff Baselines for Inference-Time Alignment
di: Madhow, Sunil, et al.
Pubblicazione: (2026)

Generate in Reconstruction Space, Match in Semantic Space: Transport Geometry for One-Step Generation
di: Van Assel, Hugues, et al.
Pubblicazione: (2026)

Cliqueformer: Model-Based Optimization with Structured Transformers
di: Kuba, Jakub Grudzien, et al.
Pubblicazione: (2024)

Inference Time Debiasing Concepts in Diffusion Models
di: Kupssinskü, Lucas S., et al.
Pubblicazione: (2025)