Imagen de Portada

Oracle-RLAIF: An Improved Fine-Tuning Framework for Multi-modal Video Models through Reinforcement Learning from Ranking Feedback

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Shi, Derek, Glatt, Ruben, Klymko, Christine, Mohole, Shubham, Choi, Hongjun, Kushwaha, Shashank, Sakla, Sam, da Silva, Felipe Leno
Formato:	Preprint
Publicado:	2025
Materias:	Computer Vision and Pattern Recognition Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

VERIRAG: A Post-Retrieval Auditing of Scientific Study Summaries
por: Mohole, Shubham, et al.
Publicado: (2025)

SIFOTL: A Principled, Statistically-Informed Fidelity-Optimization Method for Tabular Learning
por: Mohole, Shubham, et al.
Publicado: (2025)

VeriMinder: Mitigating Analytical Vulnerabilities in NL2SQL
por: Mohole, Shubham, et al.
Publicado: (2025)

Enhancing Accuracy and Parameter-Efficiency of Neural Representations for Network Parameterization
por: Choi, Hongjun, et al.
Publicado: (2024)

Curriculum-RLAIF: Curriculum Alignment with Reinforcement Learning from AI Feedback
por: Lin, Jiaye, et al.
Publicado: (2025)

RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback
por: Lee, Harrison, et al.
Publicado: (2023)

Offline RLAIF: Piloting VLM Feedback for RL via SFO
por: Beck, Jacob
Publicado: (2025)

Tuning Large Multimodal Models for Videos using Reinforcement Learning from AI Feedback
por: Ahn, Daechul, et al.
Publicado: (2024)

RLAIF-SPA: Structured AI Feedback for Semantic-Prosodic Alignment in Speech Synthesis
por: Yang, Qing, et al.
Publicado: (2025)

Oracle modalities
por: Swan, Andrew W
Publicado: (2024)

Safe, Efficient, and Robust Reinforcement Learning for Ranking and Diffusion Models
por: Gupta, Shashank
Publicado: (2025)

RLAIF-V: Open-Source AI Feedback Leads to Super GPT-4V Trustworthiness
por: Yu, Tianyu, et al.
Publicado: (2024)

Why Does RLAIF Work At All?
por: Young, Robin
Publicado: (2026)

Intent-conditioned and Non-toxic Counterspeech Generation using Multi-Task Instruction Tuning with RLAIF
por: Hengle, Amey, et al.
Publicado: (2024)

Sparse Autoencoders as a Steering Basis for Phase Synchronization in Graph-Based CFD Surrogates
por: Hu, Yeping, et al.
Publicado: (2026)

Improving Robustness In Sparse Autoencoders via Masked Regularization
por: Narayanaswamy, Vivek, et al.
Publicado: (2026)

Learning nuclear cross sections across the chart of nuclides with graph neural networks
por: Choi, Hongjun, et al.
Publicado: (2024)

Zeroth-Order Optimization Meets Human Feedback: Provable Learning via Ranking Oracles
por: Tang, Zhiwei, et al.
Publicado: (2023)

Fine-Tuning Text-to-Speech Diffusion Models Using Reinforcement Learning with Human Feedback
por: Chen, Jingyi, et al.
Publicado: (2025)

Robust Reinforcement Learning from Human Feedback for Large Language Models Fine-Tuning
por: Ye, Kai, et al.
Publicado: (2025)

Voting with the Graph: Stable RLAIF via Topological Consistency Maximization
por: Liu, Boyin, et al.
Publicado: (2025)

Applying RLAIF for Code Generation with API-usage in Lightweight LLMs
por: Dutta, Sujan, et al.
Publicado: (2024)

Enhancing the Aesthetic Appeal of AI-Generated Physical Product Designs through LoRA Fine-Tuning with Human Feedback
por: Liao, Dinuo, et al.
Publicado: (2025)

VideoRFT: Incentivizing Video Reasoning Capability in MLLMs via Reinforced Fine-Tuning
por: Wang, Qi, et al.
Publicado: (2025)

Oracle Bone Inscriptions Multi-modal Dataset
por: Li, Bang, et al.
Publicado: (2024)

TeleOracle: Fine-Tuned Retrieval-Augmented Generation with Long-Context Support for Network
por: Alabbasi, Nouf, et al.
Publicado: (2024)

TerraFormer: Automated Infrastructure-as-Code with LLMs Fine-Tuned via Policy-Guided Verifier Feedback
por: Jana, Prithwish, et al.
Publicado: (2026)

GigaVideo-1: Advancing Video Generation via Automatic Feedback with 4 GPU-Hours Fine-Tuning
por: Bao, Xiaoyi, et al.
Publicado: (2025)

Reinforcement Learning without Human Feedback for Last Mile Fine-Tuning of Large Language Models
por: Solway, Alec
Publicado: (2024)

Attractor Patch Networks: Reducing Catastrophic Forgetting with Routed Low-Rank Patch Experts
por: Shashank
Publicado: (2026)

The Digital Sous Chef -- A Comparative Study on Fine-Tuning Language Models for Recipe Generation
por: Pundhir, Shubham, et al.
Publicado: (2025)

Fine-Tuning LLMs with Fine-Grained Human Feedback on Text Spans
por: CH-Wang, Sky, et al.
Publicado: (2025)

Improving Medical Visual Reinforcement Fine-Tuning via Perception and Reasoning Augmentation
por: Yang, Guangjing, et al.
Publicado: (2026)

IMPORTANCIA DE UN DIAGNÓSTICO PRECOZ Y CUIDADOS DE ENFERMERÍA EN DIABETES GESTACIONAL.
por: D. Leno González
Publicado: (2005)

América latina, o discurso filosófico-sociológico da modernidade, a ce-gueira histórico-sociológica das teorias da modernidade: notas programá-ticas para uma práxis decolonial latino-americana
por: Leno Francisco Danner
Publicado: (2018)

Um mundo sem mediações: descolonização africana como teoria política da modernização periférica
por: Leno Francisco Danner
Publicado: (2022)

Pacificando o branco: uma história da modernidade contada pelos indígenas
por: Leno Francisco Danner
Publicado: (2022)

Educação, resistência e politização: sobre o sentido da educação na literatura indígena brasileira contemporânea
por: Leno Francisco Danner
Publicado: (2020)

Um xamã yanomami frente ao discurso filosófico-sociológico da modernidade
por: Leno Francisco Danner
Publicado: (2018)

Estado, política e evolução social: uma tendência para este século XXI
por: Leno Francisco Danner
Publicado: (2017)