Image de couverture de livre

Decouple to Generalize: Context-First Self-Evolving Learning for Data-Scarce Vision-Language Reasoning

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Li, Tingyu, Sun, Zheng, Wei, Jingxuan, Li, Siyuan, He, Conghui, Wu, Lijun, Tan, Cheng
Format:	Preprint
Publié:	2025
Sujets:	Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

GGBench: A Geometric Generative Reasoning Benchmark for Unified Multimodal Models
par: Wei, Jingxuan, et autres
Publié: (2025)

Envision: Benchmarking Unified Understanding & Generation for Causal World Process Insights
par: Tian, Juanxi, et autres
Publié: (2025)

Programming with Data: Test-Driven Data Engineering for Self-Improving LLMs from Raw Corpora
par: Pan, Chenkai, et autres
Publié: (2026)

Geoint-R1: Formalizing Multimodal Geometric Reasoning with Dynamic Auxiliary Constructions
par: Wei, Jingxuan, et autres
Publié: (2025)

PaperFit: Vision-in-the-Loop Typesetting Optimization for Scientific Documents
par: Yu, Bihui, et autres
Publié: (2026)

Can One Domain Help Others? A Data-Centric Study on Multi-Domain Reasoning via Reinforcement Learning
par: Li, Yu, et autres
Publié: (2025)

Boosting the Power of Small Multimodal Reasoning Models to Match Larger Models with Self-Consistency Training
par: Tan, Cheng, et autres
Publié: (2023)

NanoResearch: Co-Evolving Skills, Memory, and Policy for Personalized Research Automation
par: Xu, Jinhang, et autres
Publié: (2026)

Diving into Self-Evolving Training for Multimodal Reasoning
par: Liu, Wei, et autres
Publié: (2024)

PAGER: Bridging the Semantic-Execution Gap in Point-Precise Geometric GUI Control
par: Wei, Jingxuan, et autres
Publié: (2026)

Retrieval Meets Reasoning: Even High-school Textbook Knowledge Benefits Multimodal Reasoning
par: Tan, Cheng, et autres
Publié: (2024)

How RL Unlocks the Aha Moment in Geometric Interleaved Reasoning
par: Zhang, Xiangxiang, et autres
Publié: (2026)

Self-Evolving Spatial Reasoning in Vision Language Models via Geometric Logic Consistency
par: Liu, Junming, et autres
Publié: (2026)

MobEvolve: An Agentic Self-Evolving Heuristic System for Interpretable Human Mobility Generation
par: He, Junlin, et autres
Publié: (2026)

On the Generalization Gap in Self-Evolving Language Model Reasoning
par: Qi, Zhenting, et autres
Publié: (2026)

MM-Zero: Self-Evolving Multi-Model Vision Language Models From Zero Data
par: Li, Zongxia, et autres
Publié: (2026)

MMFineReason: Closing the Multimodal Reasoning Gap via Open Data-Centric Methods
par: Lin, Honglin, et autres
Publié: (2026)

Self-Supervised Federated Learning under Data Heterogeneity for Label-Scarce Diatom Classification
par: Tan, Mingkun, et autres
Publié: (2026)

Masked Modeling for Self-supervised Representation Learning on Vision and Beyond
par: Li, Siyuan, et autres
Publié: (2023)

Learning by Correction: Efficient Tuning Task for Zero-Shot Generative Vision-Language Reasoning
par: Li, Rongjie, et autres
Publié: (2024)

Multi-View Subgraph Neural Networks: Self-Supervised Learning with Scarce Labeled Data
par: Wang, Zhenzhong, et autres
Publié: (2024)

Peer Review as A Multi-Turn and Long-Context Dialogue with Role-Based Interactions
par: Tan, Cheng, et autres
Publié: (2024)

VisPlay: Self-Evolving Vision-Language Models from Images
par: He, Yicheng, et autres
Publié: (2025)

Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models
par: Zhang, Qizheng, et autres
Publié: (2025)

Respecting Self-Uncertainty in On-Policy Self-Distillation for Efficient LLM Reasoning
par: Ke, Junlong, et autres
Publié: (2026)

From Words to Structured Visuals: A Benchmark and Framework for Text-to-Diagram Generation and Editing
par: Wei, Jingxuan, et autres
Publié: (2024)

Self-Consistent Latent Reasoning: Long Latent Sequence Reasoning for Vision-Language Model
par: Wang, Chenfeng, et autres
Publié: (2026)

CoTEvol: Self-Evolving Chain-of-Thoughts for Data Synthesis in Mathematical Reasoning
par: Wang, Zhuo, et autres
Publié: (2026)

Scaling Code-Assisted Chain-of-Thoughts and Instructions for Model Reasoning
par: Lin, Honglin, et autres
Publié: (2025)

SPELL: Self-Play Reinforcement Learning for Evolving Long-Context Language Models
par: Yang, Ziyi, et autres
Publié: (2025)

Value-Spectrum: Quantifying Preferences of Vision-Language Models via Value Decomposition in Social Media Contexts
par: Li, Jingxuan, et autres
Publié: (2024)

Synth-Empathy: Towards High-Quality Synthetic Empathy Data
par: Liang, Hao, et autres
Publié: (2024)

CipherBank: Exploring the Boundary of LLM Reasoning Capabilities through Cryptography Challenges
par: Li, Yu, et autres
Publié: (2025)

REST: Stress Testing Large Reasoning Models by Asking Multiple Problems at Once
par: Pan, Zhuoshi, et autres
Publié: (2025)

Evolving Prompt Adaptation for Vision-Language Models
par: Zhang, Enming, et autres
Publié: (2026)

Deep Self-Evolving Reasoning
par: Liu, Zihan, et autres
Publié: (2025)

SketchAgent: Generating Structured Diagrams from Hand-Drawn Sketches
par: Tan, Cheng, et autres
Publié: (2025)

IDEAL: Data Equilibrium Adaptation for Multi-Capability Language Model Alignment
par: Ming, Chenlin, et autres
Publié: (2025)

Closing the Data Loop: Using OpenDataArena to Engineer Superior Training Datasets
par: Gao, Xin, et autres
Publié: (2025)

Hierarchical Dual-Subspace Decoupling for Continual Learning in Vision-Language Models
par: Qin, Mengxin, et autres
Publié: (2026)