Copertina

How RL Unlocks the Aha Moment in Geometric Interleaved Reasoning

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Zhang, Xiangxiang, Jia, Caijun, Li, Siyuan, He, Dingyu, Xiong, Xiya, Sun, Zheng, He, Honghao, Wu, Yuchen, Yu, Bihui, Sun, Linzhuang, Tan, Cheng, Wei, Jingxuan
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Geoint-R1: Formalizing Multimodal Geometric Reasoning with Dynamic Auxiliary Constructions
di: Wei, Jingxuan, et al.
Pubblicazione: (2025)

Thinking with Drafting: Optical Decompression via Logical Reconstruction
di: Wei, Jingxuan, et al.
Pubblicazione: (2026)

GGBench: A Geometric Generative Reasoning Benchmark for Unified Multimodal Models
di: Wei, Jingxuan, et al.
Pubblicazione: (2025)

PAGER: Bridging the Semantic-Execution Gap in Point-Precise Geometric GUI Control
di: Wei, Jingxuan, et al.
Pubblicazione: (2026)

Canvas-of-Thought: Grounding Reasoning via Mutable Structured States
di: Sun, Lingzhuang, et al.
Pubblicazione: (2026)

LLaVA-NeuMT: Selective Layer-Neuron Modulation for Efficient Multilingual Multimodal Translation
di: Wei, Jingxuan, et al.
Pubblicazione: (2025)

Retrieval Meets Reasoning: Even High-school Textbook Knowledge Benefits Multimodal Reasoning
di: Tan, Cheng, et al.
Pubblicazione: (2024)

Boosting the Power of Small Multimodal Reasoning Models to Match Larger Models with Self-Consistency Training
di: Tan, Cheng, et al.
Pubblicazione: (2023)

PaperFit: Vision-in-the-Loop Typesetting Optimization for Scientific Documents
di: Yu, Bihui, et al.
Pubblicazione: (2026)

Sentence-Level or Token-Level? A Comprehensive Study on Knowledge Distillation
di: Wei, Jingxuan, et al.
Pubblicazione: (2024)

BEATS: Optimizing LLM Mathematical Capabilities with BackVerify and Adaptive Disambiguate based Efficient Tree Search
di: Sun, Linzhuang, et al.
Pubblicazione: (2024)

From Words to Structured Visuals: A Benchmark and Framework for Text-to-Diagram Generation and Editing
di: Wei, Jingxuan, et al.
Pubblicazione: (2024)

Synth-Empathy: Towards High-Quality Synthetic Empathy Data
di: Liang, Hao, et al.
Pubblicazione: (2024)

ChartReasoner: Code-Driven Modality Bridging for Long-Chain Reasoning in Chart Question Answering
di: Jia, Caijun, et al.
Pubblicazione: (2025)

Rational Sensibility: LLM Enhanced Empathetic Response Generation Guided by Self-presentation Theory
di: Sun, Linzhuang, et al.
Pubblicazione: (2023)

Brain-inspired Computing Based on Deep Learning for Human-computer Interaction: A Review
di: Yu, Bihui, et al.
Pubblicazione: (2023)

MM-Verify: Enhancing Multimodal Reasoning with Chain-of-Thought Verification
di: Sun, Linzhuang, et al.
Pubblicazione: (2025)

Efficient-Empathy: Towards Efficient and Effective Selection of Empathy Data
di: Sun, Linzhuang, et al.
Pubblicazione: (2024)

TRACER: Verifiable Generative Provenance for Multimodal Tool-Using Agents
di: Yu, Bihui, et al.
Pubblicazione: (2026)

SafeKey: Amplifying Aha-Moment Insights for Safety Reasoning
di: Zhou, Kaiwen, et al.
Pubblicazione: (2025)

GenProve: Learning to Generate Text with Fine-Grained Provenance
di: Wei, Jingxuan, et al.
Pubblicazione: (2026)

Decouple to Generalize: Context-First Self-Evolving Learning for Data-Scarce Vision-Language Reasoning
di: Li, Tingyu, et al.
Pubblicazione: (2025)

ReasoningGuard: Safeguarding Large Reasoning Models with Inference-time Safety Aha Moments
di: Wang, Yuquan, et al.
Pubblicazione: (2025)

Guided Verifier: Collaborative Multimodal Reasoning via Dynamic Process Supervision
di: Sun, Lingzhuang, et al.
Pubblicazione: (2026)

Can Aha Moments Be Fake? Towards Quantifying Decorative and True Thinking in Chain-of-Thought
di: Zhao, Jiachen, et al.
Pubblicazione: (2025)

R1-Zero's "Aha Moment" in Visual Reasoning on a 2B Non-SFT Model
di: Zhou, Hengguang, et al.
Pubblicazione: (2025)

Divide-Fuse-Conquer: Eliciting "Aha Moments" in Multi-Scenario Games
di: Zhang, Xiaoqing, et al.
Pubblicazione: (2025)

Understanding Aha Moments: from External Observations to Internal Mechanisms
di: Yang, Shu, et al.
Pubblicazione: (2025)

Rethinking Text-to-SQL: Dynamic Multi-turn SQL Interaction for Real-world Database Exploration
di: Sun, Linzhuang, et al.
Pubblicazione: (2025)

From "Aha Moments" to Controllable Thinking: Toward Meta-Cognitive Reasoning in Large Reasoning Models via Decoupled Reasoning and Control
di: Ha, Rui, et al.
Pubblicazione: (2025)

The Trinity of Consistency as a Defining Principle for General World Models
di: Wei, Jingxuan, et al.
Pubblicazione: (2026)

A Survey on Image-text Multimodal Models
di: Guo, Ruifeng, et al.
Pubblicazione: (2023)

Beyond 'Aha!': Toward Systematic Meta-Abilities Alignment in Large Reasoning Models
di: Hu, Zhiyuan, et al.
Pubblicazione: (2025)

Unlocking the Potential of Difficulty Prior in RL-based Multimodal Reasoning
di: Chen, Mingrui, et al.
Pubblicazione: (2025)

Aha Moment Revisited: Are VLMs Truly Capable of Self Verification in Inference-time Scaling?
di: Wu, Mingyuan, et al.
Pubblicazione: (2025)

ResearchPulse: Building Method-Experiment Chains through Multi-Document Scientific Inference
di: Chen, Qi, et al.
Pubblicazione: (2025)

RL Grokking Recipe: How Does RL Unlock and Transfer New Algorithms in LLMs?
di: Sun, Yiyou, et al.
Pubblicazione: (2025)

Aha Moments and Continued Confusion: An Analysis of Threshold Concepts through Student Reflections in the ACRL Framework
di: Eva, Nicole C., et al.
Pubblicazione: (2021)

DeepTool: Scaling Interleaved Deliberation in Tool-Integrated Reasoning via Process-Supervised Reinforcement Learning
di: He, Yang, et al.
Pubblicazione: (2026)

SketchAgent: Generating Structured Diagrams from Hand-Drawn Sketches
di: Tan, Cheng, et al.
Pubblicazione: (2025)