Image de couverture de livre

Parallel Tempering Initial Sampling in Inference-Time Reward Alignment

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Oh, Myeongjun, Kim, Gwangho, Lee, Sungyoon
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Psi-Sampler: Initial Particle Sampling for SMC-Based Inference-Time Reward Alignment in Score Models
par: Yoon, Taehoon, et autres
Publié: (2025)

Localizing Memorized Regions in Diffusion Models via Coordinate-Wise Curvature Differences
par: Kim, Gwangho, et autres
Publié: (2026)

Spectral Evolution Search: Efficient Inference-Time Scaling for Reward-Aligned Image Generation
par: Ye, Jinyan, et autres
Publié: (2026)

Gradient-Free Noise Optimization for Reward Alignment in Generative Models
par: Kim, Jeongsol, et autres
Publié: (2026)

Activation Reward Models for Few-Shot Model Alignment
par: Chai, Tianning, et autres
Publié: (2025)

STAG: Structural Test-time Alignment of Gradients for Online Adaptation
par: Shin, Juhyeon, et autres
Publié: (2024)

Beyond Pairwise Preferences: Listwise Reward-Aware Alignment for Diffusion Models
par: Wang, Austin, et autres
Publié: (2026)

False Positive Sampling-based Data Augmentation for Enhanced 3D Object Detection Accuracy
par: Oh, Jiyong, et autres
Publié: (2024)

Backpropagation-Free Test-Time Adaptation via Probabilistic Gaussian Alignment
par: Zhang, Youjia, et autres
Publié: (2025)

TWINGS: Thin Plate Splines Warp-aligned Initialization for Sparse-View Gaussian Splatting
par: Kim, Hyeseong, et autres
Publié: (2026)

Bi-MCQ: Reformulating Vision-Language Alignment for Negation Understanding
par: Kim, Tae Hun, et autres
Publié: (2026)

Performance Plateaus in Inference-Time Scaling for Text-to-Image Diffusion Without External Models
par: Choi, Changhyun, et autres
Publié: (2025)

Cycle Consistency as Reward: Learning Image-Text Alignment without Human Preferences
par: Bahng, Hyojin, et autres
Publié: (2025)

Video Parallel Scaling: Aggregating Diverse Frame Subsets for VideoLLMs
par: Chung, Hyungjin, et autres
Publié: (2025)

Improving Diagnostic Accuracy for Oral Cancer with inpainting Synthesis Lesions Generated Using Diffusion Models
par: Lee, Yong Oh, et autres
Publié: (2025)

Towards Better Alignment: Training Diffusion Models with Reinforcement Learning Against Sparse Rewards
par: Hu, Zijing, et autres
Publié: (2025)

Neural Image Compression with Text-guided Encoding for both Pixel-level and Perceptual Fidelity
par: Lee, Hagyeong, et autres
Publié: (2024)

DreamPropeller: Supercharge Text-to-3D Generation with Parallel Sampling
par: Zhou, Linqi, et autres
Publié: (2023)

STELLA: Continual Audio-Video Pre-training with Spatio-Temporal Localized Alignment
par: Lee, Jaewoo, et autres
Publié: (2023)

Equivariant Latent Alignment via Flow Matching under Group Symmetries
par: Kim, Sunghyun, et autres
Publié: (2026)

Reward Score Matching: Unifying Reward-based Fine-tuning for Flow and Diffusion Models
par: Lee, Jeongjae, et autres
Publié: (2026)

Inference-Time Scaling for Flow Models via Stochastic Generation and Rollover Budget Forcing
par: Kim, Jaihoon, et autres
Publié: (2025)

Test-time Alignment of Diffusion Models without Reward Over-optimization
par: Kim, Sunwoo, et autres
Publié: (2025)

Dual-Stage Value-Guided Inference with Margin-Based Reward Adjustment for Fast and Faithful VLM Captioning
par: Deria, Ankan, et autres
Publié: (2025)

Global Context-aware Representation Learning for Spatially Resolved Transcriptomics
par: Oh, Yunhak, et autres
Publié: (2025)

Tuning-Free Multi-Event Long Video Generation via Synchronized Coupled Sampling
par: Kim, Subin, et autres
Publié: (2025)

Adaptive Non-uniform Timestep Sampling for Accelerating Diffusion Model Training
par: Kim, Myunsoo, et autres
Publié: (2024)

SoliReward: Mitigating Susceptibility to Reward Hacking and Annotation Noise in Video Generation Reward Models
par: Lian, Jiesong, et autres
Publié: (2025)

Reward-Forcing: Autoregressive Video Generation with Reward Feedback
par: Zhang, Jingran, et autres
Publié: (2026)

Machine learning approach to brain tumor detection and classification
par: Oh, Alice, et autres
Publié: (2024)

Video Diffusion Alignment via Reward Gradients
par: Prabhudesai, Mihir, et autres
Publié: (2024)

HEART-PFL: Stable Personalized Federated Learning under Heterogeneity with Hierarchical Directional Alignment and Adversarial Knowledge Transfer
par: Kim, Minjun, et autres
Publié: (2026)

Benign, Tempered, or Catastrophic: A Taxonomy of Overfitting
par: Mallinar, Neil, et autres
Publié: (2022)

TimePoint: Accelerated Time Series Alignment via Self-Supervised Keypoint and Descriptor Learning
par: Weber, Ron Shapira, et autres
Publié: (2025)

ZigZag: Universal Sampling-free Uncertainty Estimation Through Two-Step Inference
par: Durasov, Nikita, et autres
Publié: (2022)

SelMatch: Effectively Scaling Up Dataset Distillation via Selection-Based Initialization and Partial Updates by Trajectory Matching
par: Lee, Yongmin, et autres
Publié: (2024)

GrndCtrl: Grounding World Models via Self-Supervised Reward Alignment
par: He, Haoyang, et autres
Publié: (2025)

A Theoretical Framework for Preventing Class Collapse in Supervised Contrastive Learning
par: Lee, Chungpa, et autres
Publié: (2025)

Test-Time Anchoring for Discrete Diffusion Posterior Sampling
par: Rout, Litu, et autres
Publié: (2025)

Unified Control for Inference-Time Guidance of Denoising Diffusion Models
par: Goyal, Maurya, et autres
Publié: (2025)