Copertina

SAIL: Self-Amplified Iterative Learning for Diffusion Model Alignment with Minimal Human Feedback

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	He, Xiaoxuan, Fu, Siming, Li, Wanli, Li, Zhiyuan, Yin, Dacheng, Rong, Kang, Rao, Fengyun, Zhang, Bo
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

TempFlow-GRPO: When Timing Matters for GRPO in Flow Models
di: He, Xiaoxuan, et al.
Pubblicazione: (2025)

WeMMU: Enhanced Bridging of Vision-Language Models and Diffusion Models via Noisy Query Tokens
di: Yang, Jian, et al.
Pubblicazione: (2025)

Flash-GRPO: Efficient Alignment for Video Diffusion via One-Step Policy Optimization
di: He, Xiaoxuan, et al.
Pubblicazione: (2026)

WeThink: Toward General-purpose Vision-Language Reasoning via Reinforcement Learning
di: Yang, Jie, et al.
Pubblicazione: (2025)

REVERSE: Reinforcing Evidence Verification and Search for Agentic Image geo-localization
di: Li, Yong, et al.
Pubblicazione: (2026)

Instruction-Oriented Preference Alignment for Enhancing Multi-Modal Comprehension Capability of MLLMs
di: Wang, Zitian, et al.
Pubblicazione: (2025)

R1-Onevision: Advancing Generalized Multimodal Reasoning through Cross-Modal Formalization
di: Yang, Yi, et al.
Pubblicazione: (2025)

SAIL-VL2 Technical Report
di: Yin, Weijie, et al.
Pubblicazione: (2025)

Feedback-Driven Vision-Language Alignment with Minimal Human Supervision
di: Giannone, Giorgio, et al.
Pubblicazione: (2025)

SAIL: Self-supervised Albedo Estimation from Real Images with a Latent Diffusion Model
di: Djeghim, Hala, et al.
Pubblicazione: (2025)

MMAR: Towards Lossless Multi-Modal Auto-Regressive Probabilistic Modeling
di: Yang, Jian, et al.
Pubblicazione: (2024)

From Trial to Triumph: Advancing Long Video Understanding via Visual Context Sample Scaling and Self-reward Alignment
di: Suo, Yucheng, et al.
Pubblicazione: (2025)

Pixel-SAIL: Single Transformer For Pixel-Grounded Understanding
di: Zhang, Tao, et al.
Pubblicazione: (2025)

HarmonySet: A Comprehensive Dataset for Understanding Video-Music Semantic Alignment and Temporal Synchronization
di: Zhou, Zitang, et al.
Pubblicazione: (2025)

SAIL: Scene-aware Adaptive Iterative Learning for Long-Tail Trajectory Prediction in Autonomous Vehicles
di: Rao, Bin, et al.
Pubblicazione: (2026)

SAIL: Structure-Aware Interpretable Learning for Anatomy-Aligned Post-hoc Explanations in OCT
di: Chang, Tienyu, et al.
Pubblicazione: (2026)

SAIL-RL: Guiding MLLMs in When and How to Think via Dual-Reward RL Tuning
di: Shu, Fangxun, et al.
Pubblicazione: (2025)

SAIL-Embedding Technical Report: Omni-modal Embedding Foundation Model
di: Lin, Lin, et al.
Pubblicazione: (2025)

SAIL-Recon: Large SfM by Augmenting Scene Regression with Localization
di: Deng, Junyuan, et al.
Pubblicazione: (2025)

Maximizing Alignment with Minimal Feedback: Efficiently Learning Rewards for Visuomotor Robot Policy Alignment
di: Tian, Ran, et al.
Pubblicazione: (2024)

Divergence Minimization Preference Optimization for Diffusion Model Alignment
di: Li, Binxu, et al.
Pubblicazione: (2025)

Instant Preference Alignment for Text-to-Image Diffusion Models
di: Li, Yang, et al.
Pubblicazione: (2025)

MS-Diffusion: Multi-subject Zero-shot Image Personalization with Layout Guidance
di: Wang, Xierui, et al.
Pubblicazione: (2024)

LiFT: Leveraging Human Feedback for Text-to-Video Model Alignment
di: Wang, Yibin, et al.
Pubblicazione: (2024)

MagicMan: Generative Novel View Synthesis of Humans with 3D-Aware Diffusion and Iterative Refinement
di: He, Xu, et al.
Pubblicazione: (2024)

Harnessing Text-to-Image Diffusion Models for Point Cloud Self-Supervised Learning
di: Chen, Yiyang, et al.
Pubblicazione: (2025)

RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback
di: Yu, Tianyu, et al.
Pubblicazione: (2023)

Representation Learning for Point Cloud Understanding
di: Yan, Siming
Pubblicazione: (2025)

Online Iterative Self-Alignment for Radiology Report Generation
di: Xiao, Ting, et al.
Pubblicazione: (2025)

Instruction-augmented Multimodal Alignment for Image-Text and Element Matching
di: Yue, Xinli, et al.
Pubblicazione: (2025)

Disentangling Content from Style to Overcome Shortcut Learning: A Hybrid Generative-Discriminative Learning Framework
di: Fu, Siming, et al.
Pubblicazione: (2025)

ObjEmbed: Towards Universal Multimodal Object Embeddings
di: Fu, Shenghao, et al.
Pubblicazione: (2026)

WeDetect: Fast Open-Vocabulary Object Detection as Retrieval
di: Fu, Shenghao, et al.
Pubblicazione: (2025)

Enhancing Diffusion-based Unrestricted Adversarial Attacks via Adversary Preferences Alignment
di: Jiang, Kaixun, et al.
Pubblicazione: (2025)

Why Self-Rewarding Works: Theoretical Guarantees for Iterative Alignment of Language Models
di: Fu, Shi, et al.
Pubblicazione: (2026)

HDiffTG: A Lightweight Hybrid Diffusion-Transformer-GCN Architecture for 3D Human Pose Estimation
di: Fu, Yajie, et al.
Pubblicazione: (2025)

WAVE: Learning Unified & Versatile Audio-Visual Embeddings with Multimodal LLM
di: Tang, Changli, et al.
Pubblicazione: (2025)

Deeper Diffusion Models Amplify Bias
di: Hakemi, Shahin, et al.
Pubblicazione: (2025)

UniFL: Improve Latent Diffusion Model via Unified Feedback Learning
di: Zhang, Jiacheng, et al.
Pubblicazione: (2024)

SAIL: Self-Improving Efficient Online Alignment of Large Language Models
di: Ding, Mucong, et al.
Pubblicazione: (2024)