Copertina

Discrete Meanflow Training Curriculum

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Hsu, Chia-Hong, Wood, Frank
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

OT-MeanFlow3D: Bridging Optimal Transport and Meanflow for Efficient 3D Point Cloud Generation
di: Akbari, Elaheh, et al.
Pubblicazione: (2025)

Post-Hoc Guidance for Consistency Models by Joint Flow Distribution Learning
di: Hsu, Chia-Hong, et al.
Pubblicazione: (2026)

Self-Correcting Self-Consuming Loops for Generative Model Training
di: Gillman, Nate, et al.
Pubblicazione: (2024)

Provable Benefit of Curriculum in Transformer Tree-Reasoning Post-Training
di: Bu, Dake, et al.
Pubblicazione: (2025)

On the Hardness of Training Deep Neural Networks Discretely
di: Doron-Arad, Ilan
Pubblicazione: (2024)

Enhancing Signed Graph Neural Networks through Curriculum-Based Training
di: Zhang, Zeyu, et al.
Pubblicazione: (2023)

Localized Physics-informed Gaussian Processes with Curriculum Training for Topology Optimization
di: Yousefpour, Amin, et al.
Pubblicazione: (2025)

On the Impact of Weight Discretization in QUBO-Based SVM Training
di: Mücke, Sascha
Pubblicazione: (2025)

Harmless Yet Harmful: Neutral Prompting Attacks for Stealthy Hallucination Steering in Agent Skills
di: Hsu, Chia-Yi, et al.
Pubblicazione: (2026)

Prompt Curriculum Learning for Efficient LLM Post-Training
di: Gao, Zhaolin, et al.
Pubblicazione: (2025)

DOGE-Train: Discrete Optimization on GPU with End-to-end Training
di: Abbas, Ahmed, et al.
Pubblicazione: (2022)

SPEED-RL: Faster Training of Reasoning Models via Online Curriculum Learning
di: Zhang, Ruiqi, et al.
Pubblicazione: (2025)

Learning to Predict Chaos: Curriculum-Driven Training for Robust Forecasting of Chaotic Dynamics
di: Vejendla, Harshil
Pubblicazione: (2025)

Curriculum Sampling: A Two-Phase Curriculum for Efficient Training of Flow Matching
di: Sun, Pengwei
Pubblicazione: (2026)

Entropy-Driven Curriculum for Multi-Task Training in Human Mobility Prediction
di: Fang, Tianye, et al.
Pubblicazione: (2025)

Dataset Decomposition: Faster LLM Training with Variable Sequence Length Curriculum
di: Pouransari, Hadi, et al.
Pubblicazione: (2024)

Sparse Training of Discrete Diffusion Models for Graph Generation
di: Qin, Yiming, et al.
Pubblicazione: (2023)

Multi-scale Autoregressive Models are Laplacian, Discrete, and Latent Diffusion Models in Disguise
di: Hong, Steve, et al.
Pubblicazione: (2025)

Veli: Unsupervised Method and Unified Benchmark for Low-Cost Air Quality Sensor Correction
di: Dalbah, Yahia, et al.
Pubblicazione: (2025)

Training-free retrieval-augmented generation with reinforced reasoning for flood damage nowcasting
di: Huang, Lipai, et al.
Pubblicazione: (2026)

Layerwise Proximal Replay: A Proximal Point Method for Online Continual Learning
di: Yoo, Jason, et al.
Pubblicazione: (2024)

Constrained Generative Modeling with Manually Bridged Diffusion Models
di: Naderiparizi, Saeid, et al.
Pubblicazione: (2025)

Safe LoRA: the Silver Lining of Reducing Safety Risks when Fine-tuning Large Language Models
di: Hsu, Chia-Yi, et al.
Pubblicazione: (2024)

Consistency Training with Physical Constraints
di: Chang, Che-Chia, et al.
Pubblicazione: (2025)

A Unified Training Process for Fake News Detection based on Fine-Tuned BERT Model
di: Tida, Vijay Srinivas, et al.
Pubblicazione: (2022)

Unsupervised Physics-Informed Operator Learning through Multi-Stage Curriculum Training
di: Marcandelli, Paolo, et al.
Pubblicazione: (2026)

From Reward-Free Representations to Preferences: Rethinking Offline Preference-Based Reinforcement Learning
di: Yang, Jun-Jie, et al.
Pubblicazione: (2026)

Training Large Language Models for Reasoning through Reverse Curriculum Reinforcement Learning
di: Xi, Zhiheng, et al.
Pubblicazione: (2024)

M$^3$: Reframing Training Measures for Discretized Physical Simulations
di: Mei, Yuan, et al.
Pubblicazione: (2026)

ReDi: Rectified Discrete Flow
di: Yoo, Jaehoon, et al.
Pubblicazione: (2025)

Training Neural ODEs Using Fully Discretized Simultaneous Optimization
di: Shapovalova, Mariia, et al.
Pubblicazione: (2025)

Train Long, Think Short: Curriculum Learning for Efficient Reasoning
di: Hammoud, Hasan Abed Al Kader, et al.
Pubblicazione: (2025)

Denoising Task Difficulty-based Curriculum for Training Diffusion Models
di: Kim, Jin-Young, et al.
Pubblicazione: (2024)

EfficientTrain++: Generalized Curriculum Learning for Efficient Visual Backbone Training
di: Wang, Yulin, et al.
Pubblicazione: (2024)

Robust Server Defense Against Unreliable Clients in One-Shot Fair Collaborative Machine Learning
di: Wu, Chia-Yuan, et al.
Pubblicazione: (2026)

Prospective Messaging: Learning in Networks with Communication Delays
di: Fayyazi, Ryan, et al.
Pubblicazione: (2024)

Assessing the Potential for Catastrophic Failure in Dynamic Post-Training Quantization
di: Frank, Logan, et al.
Pubblicazione: (2025)

Training-Free Guidance for Discrete Diffusion Models for Molecular Generation
di: Kerby, Thomas J., et al.
Pubblicazione: (2024)

Don't be so negative! Score-based Generative Modeling with Oracle-assisted Guidance
di: Naderiparizi, Saeid, et al.
Pubblicazione: (2023)

Frankenstein Optimizer: Harnessing the Potential by Revisiting Optimization Tricks
di: Hsu, Chia-Wei, et al.
Pubblicazione: (2025)