Copertina

Effective Test-Time Scaling of Discrete Diffusion through Iterative Refinement

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Lee, Sanghyun, Kim, Sunwoo, Kim, Seungryong, Park, Jongho, Park, Dongmin
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

Lookahead Unmasking Elicits Accurate Decoding in Diffusion Language Models
di: Lee, Sanghyun, et al.
Pubblicazione: (2025)

Test-time Alignment of Diffusion Models without Reward Over-optimization
di: Kim, Sunwoo, et al.
Pubblicazione: (2025)

When Model Meets New Normals: Test-time Adaptation for Unsupervised Time-series Anomaly Detection
di: Kim, Dongmin, et al.
Pubblicazione: (2023)

Can Large Language Models Develop Strategic Reasoning? Post-training Insights from Learning Chess
di: Hwang, Dongyoon, et al.
Pubblicazione: (2025)

Lookahead Sample Reward Guidance for Test-Time Scaling of Diffusion Models
di: Kim, Yeongmin, et al.
Pubblicazione: (2026)

Inference-Time Scaling in Diffusion Models through Iterative Partial Refinement
di: Kang, Taegu, et al.
Pubblicazione: (2026)

Are Self-Attentions Effective for Time Series Forecasting?
di: Kim, Dongbin, et al.
Pubblicazione: (2024)

VLM-SubtleBench: How Far Are VLMs from Human-Level Subtle Comparative Reasoning?
di: Kim, Minkyu, et al.
Pubblicazione: (2026)

Text-Aware Image Restoration with Diffusion Models
di: Min, Jaewon, et al.
Pubblicazione: (2025)

Active Learning for Continual Learning: Keeping the Past Alive in the Present
di: Park, Jaehyun, et al.
Pubblicazione: (2025)

Controllable 3D Molecular Generation for Structure-Based Drug Design Through Bayesian Flow Networks and Gradient Integration
di: Choi, Seungyeon, et al.
Pubblicazione: (2025)

Discrete Dictionary-based Decomposition Layer for Structured Representation Learning
di: Park, Taewon, et al.
Pubblicazione: (2024)

LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models
di: Park, Taekhyun, et al.
Pubblicazione: (2026)

SOLAR 10.7B: Scaling Large Language Models with Simple yet Effective Depth Up-Scaling
di: Kim, Dahyun, et al.
Pubblicazione: (2023)

Deep Learning and Matrix Completion-aided IoT Network Localization in the Outlier Scenarios
di: Kim, Sunwoo
Pubblicazione: (2025)

Understanding and Accelerating the Training of Masked Diffusion Language Models
di: Hong, Chunsan, et al.
Pubblicazione: (2026)

Where and How to Perturb: On the Design of Perturbation Guidance in Diffusion and Flow Models
di: Ahn, Donghoon, et al.
Pubblicazione: (2025)

Rare-to-Frequent: Unlocking Compositional Generation Power of Diffusion Models on Rare Concepts with LLM Guidance
di: Park, Dongmin, et al.
Pubblicazione: (2024)

Disentangling Hyperedges through the Lens of Category Theory
di: Lee, Yoonho, et al.
Pubblicazione: (2025)

ANT: Adaptive Noise Schedule for Time Series Diffusion Models
di: Lee, Seunghan, et al.
Pubblicazione: (2024)

DIAR: Diffusion-model-guided Implicit Q-learning with Adaptive Revaluation
di: Park, Jaehyun, et al.
Pubblicazione: (2024)

ReTAMamba: Reliability-Aware Temporal Aggregation with Mamba for Irregular Clinical Time Series Prediction
di: Kim, Jinwoong, et al.
Pubblicazione: (2026)

JustDense: Just using Dense instead of Sequence Mixer for Time Series analysis
di: Park, TaekHyun, et al.
Pubblicazione: (2025)

IConv: Focusing on Local Variation with Channel Independent Convolution for Multivariate Time Series Forecasting
di: Lee, Gawon, et al.
Pubblicazione: (2025)

Discrete Diffusion Schrödinger Bridge Matching for Graph Transformation
di: Kim, Jun Hyeong, et al.
Pubblicazione: (2024)

When Will It Fail?: Anomaly to Prompt for Forecasting Future Anomalies in Time Series
di: Park, Min-Yeong, et al.
Pubblicazione: (2025)

A Noise is Worth Diffusion Guidance
di: Ahn, Donghoon, et al.
Pubblicazione: (2024)

HiRef: Leveraging Hierarchical Ontology and Network Refinement for Robust Medication Recommendation
di: Chok, Yan Ting, et al.
Pubblicazione: (2025)

SPIN: SE(3)-Invariant Physics Informed Network for Binding Affinity Prediction
di: Choi, Seungyeon, et al.
Pubblicazione: (2024)

Towards Next-Level Post-Training Quantization of Hyper-Scale Transformers
di: Kim, Junhan, et al.
Pubblicazione: (2024)

Attention-based Iterative Decomposition for Tensor Product Representation
di: Park, Taewon, et al.
Pubblicazione: (2024)

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

FlowerFormer: Empowering Neural Architecture Encoding using a Flow-aware Graph Transformer
di: Hwang, Dongyeong, et al.
Pubblicazione: (2024)

A Scalable and Transferable Time Series Prediction Framework for Demand Forecasting
di: Park, Young-Jin, et al.
Pubblicazione: (2024)

CRePE: Curved Ray Expectation Positional Encoding for Unified-Camera-Controlled Video Generation
di: Jin, Seonghyun, et al.
Pubblicazione: (2026)

TimeBridge: Better Diffusion Prior Design with Bridge Models for Time Series Generation
di: Park, Jinseong, et al.
Pubblicazione: (2024)

Generative Representation Learning on Hyper-relational Knowledge Graphs via Masked Discrete Diffusion
di: Lee, Jaejun, et al.
Pubblicazione: (2026)

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

Fair Clustering via Alignment
di: Kim, Kunwoong, et al.
Pubblicazione: (2025)

Stop-RAG: Value-Based Retrieval Control for Iterative RAG
di: Park, Jaewan, et al.
Pubblicazione: (2025)