Image de couverture de livre

Meta-TTRL: A Metacognitive Framework for Self-Improving Test-Time Reinforcement Learning in Unified Multimodal Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Tan, Lit Sin, Chen, Junzhe, Fu, Xiaolong, Ma, Lichen, Huang, Junshi, Shi, Jianzhong, Li, Yan, Wen, Lijie
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

TTRL: Test-Time Reinforcement Learning
par: Zuo, Yuxin, et autres
Publié: (2025)

UM-Text: A Unified Multimodal Model for Image Understanding and Visual Text Editing
par: Ma, Lichen, et autres
Publié: (2026)

AQA-TTRL: Self-Adaptation in Audio Question Answering with Test-Time Reinforcement Learning
par: Zhang, Haoyu, et autres
Publié: (2025)

Dynamic-TreeRPO: Breaking the Independent Trajectory Bottleneck with Structured Sampling
par: Fu, Xiaolong, et autres
Publié: (2025)

CG-TTRL: Context-Guided Test-Time Reinforcement Learning for On-Device Large Language Models
par: Hosseini, Peyman, et autres
Publié: (2025)

FrequencyBooster: Full-Frequency Modeling for High-Fidelity Pixel Diffusion
par: Ma, Lichen, et autres
Publié: (2026)

Fashion130K: An E-commerce Fashion Dataset for Outfit Generation with Unified Multi-modal Condition
par: He, Yu, et autres
Publié: (2026)

CoT2-Meta: Budgeted Metacognitive Control for Test-Time Reasoning
par: Ma, Siyuan, et autres
Publié: (2026)

Beyond Meta-Reasoning: Metacognitive Consolidation for Self-Improving LLM Reasoning
par: Zhuang, Ziqing, et autres
Publié: (2026)

HyperDiT: Hyper-Connected Transformers for High-Fidelity Pixel-Space Diffusion
par: He, Yu, et autres
Publié: (2026)

RePainter: Empowering E-commerce Object Removal via Spatial-matting Reinforcement Learning
par: Guo, Zipeng, et autres
Publié: (2025)

SUDER: Self-Improving Unified Large Multimodal Models for Understanding and Generation with Dual Self-Rewards
par: Hong, Jixiang, et autres
Publié: (2025)

Irec: A Metacognitive Scaffolding for Self-Regulated Learning through Just-in-Time Insight Recall: A Conceptual Framework and System Prototype
par: Hou, Xuefei, et autres
Publié: (2025)

Do We Really Need External Tools to Mitigate Hallucinations? SIRA: Shared-Prefix Internal Reconstruction of Attribution
par: Qin, Tian, et autres
Publié: (2026)

UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning
par: Mao, Weijia, et autres
Publié: (2025)

Metacognitive Sensitivity for Test-Time Dynamic Model Selection
par: Trinh, Le Tuan Minh, et autres
Publié: (2025)

UniT: Unified Multimodal Chain-of-Thought Test-time Scaling
par: Chen, Leon Liangyu, et autres
Publié: (2026)

MetaCogAgent: A Metacognitive Multi-Agent LLM Framework with Self-Aware Task Delegation
par: Wang, Chenyu, et autres
Publié: (2026)

LiWi: Layering in the Wild
par: He, Yu, et autres
Publié: (2026)

MetaCLASS: Metacognitive Coaching for Learning with Adaptive Self-regulation Support
par: Liu, Naiming, et autres
Publié: (2026)

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning
par: Liu, Tennison, et autres
Publié: (2025)

MENTOR: A Metacognition-Driven Self-Evolution Framework for Uncovering and Mitigating Implicit Domain Risks in LLMs
par: Shan, Liang, et autres
Publié: (2025)

Exploring the Output of Software Testing Tools through a Visual Comparative Analysis
par: Lit, Brandon, et autres
Publié: (2026)

The Debate on the Dietary Guidelines for Americans (2025–2030) and Implications for China's Nutritional Policy
par: Junshi Chen
Publié: (2026)

Test-Time Meta-Adaptation with Self-Synthesis
par: Kaya, Zeyneb N., et autres
Publié: (2026)

Test-Time Regret Minimization in Meta Reinforcement Learning
par: Mutti, Mirco, et autres
Publié: (2024)

Curiosity and Metacognition: Towards a Unified Framework for Learning and Education in the Age of AI
par: Desvaux, Chloé, et autres
Publié: (2026)

MetaEmbed: Scaling Multimodal Retrieval at Test-Time with Flexible Late Interaction
par: Xiao, Zilin, et autres
Publié: (2025)

The PCP-like Theorem for Sub-linear Time Inapproximability
par: Ma, Hengzhao, et autres
Publié: (2021)

ImAgent: A Unified Multimodal Agent Framework for Test-Time Scalable Image Generation
par: Wang, Kaishen, et autres
Publié: (2025)

UniCorn: Towards Self-Improving Unified Multimodal Models through Self-Generated Supervision
par: Han, Ruiyan, et autres
Publié: (2026)

A Unified Information-Theoretic Framework for Meta-Learning Generalization
par: Wen, Wen, et autres
Publié: (2025)

Meta Fusion: A Unified Framework For Multimodality Fusion with Mutual Learning
par: Liang, Ziyi, et autres
Publié: (2025)

PER-DPP Sampling Framework and Its Application in Path Planning
par: Wang, Junzhe
Publié: (2025)

Constrained Meta Reinforcement Learning with Provable Test-Time Safety
par: Ni, Tingting, et autres
Publié: (2026)

Grouped Competition Test with Unified False Discovery Rate Control
par: Deng, Mingzhou, et autres
Publié: (2025)

MUSE: Manipulating Unified Framework for Synthesizing Emotions in Images via Test-Time Optimization
par: Xia, Yingjie, et autres
Publié: (2025)

Self-Improving LLM Agents at Test-Time
par: Acikgoz, Emre Can, et autres
Publié: (2025)

Co-Reinforcement Learning for Unified Multimodal Understanding and Generation
par: Jiang, Jingjing, et autres
Publié: (2025)

UR$^2$: Unify RAG and Reasoning through Reinforcement Learning
par: Li, Weitao, et autres
Publié: (2025)