SPLIT-RL: Staged Perception-Language Reasoning Training with Claim-Level Advantages

arXiv:2610.10889 · cs.CV · Submitted 2026-10-07 · Read on arXiv

cs.CV

Submitted: 2026-10-07

Updated: 2026-10-07

Code: https://github.com/hiyouga/EasyR1

Terminology

• GRPO — 97× in this paper · explained in 6 episodes
• Benchmark — 23× in this paper · explained in 2 episodes
• Accuracy — 17× in this paper · explained in 1 episode
• Language Reasoning — 12× in this paper
• Reinforcement Learning — 12× in this paper · explained in 4 episodes
• Multimodal Reasoning — 7× in this paper · explained in 5 episodes
• Verification — 6× in this paper · explained in 2 episodes
• Ablation — 5× in this paper · explained in 1 episode
• Visual Reasoning — 5× in this paper
• In International Conference on Learning Representations — 4× in this paper
• Credit assignment — 3× in this paper · explained in 3 episodes
• LLM judge — 3× in this paper · explained in 2 episodes
• Verifier — 3× in this paper · explained in 2 episodes
• Commentary — 2× in this paper · explained in 2 episodes
• Grounding — 2× in this paper · explained in 3 episodes
• Verifiable Rewards — 2× in this paper · explained in 2 episodes
• Ablation Studies — 1× in this paper · explained in 1 episode
• Adam — 1× in this paper · explained in 2 episodes
• Alignment — 1× in this paper · explained in 1 episode
• Calibration — 1× in this paper · explained in 7 episodes
• Chain-of-Thought (CoT) — 1× in this paper · explained in 4 episodes
• Chain-of-Thought Prompting — 1× in this paper · explained in 2 episodes
• Core — 1× in this paper · explained in 2 episodes
• Decoupling — 1× in this paper · explained in 2 episodes
• Entanglement — 1× in this paper · explained in 3 episodes
• Findings of the Association for Computational Linguistics — 1× in this paper
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• GRPO Objective — 1× in this paper · explained in 2 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Generative AI — 1× in this paper · explained in 2 episodes
• In International Conference on Machine Learning — 1× in this paper
• Objective Function — 1× in this paper · explained in 2 episodes
• Robustness — 1× in this paper · explained in 5 episodes

Sources

• Qwen3-VL Technical Report
• RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control
• VRPRM: Process Reward Modeling via Visual Reasoning
• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
• Boosting the Generalization and Reasoning of Vision Language Models with Curriculum Reinforcement Learning
• OpenVLThinker: Complex Vision-Language Reasoning via Iterative SFT-RL Cycles
• MM-PRM: Enhancing Multimodal Mathematical Reasoning with Scalable Step-Level Supervision
• Video-R1: Reinforcing Video Reasoning in MLLMs
• Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models
• Med-R1: Reinforcement Learning for Generalizable Medical Reasoning in Vision-Language Models
• Tulu 3: Pushing Frontiers in Open Language Model Post-Training
• Let's Verify Step by Step
• CLEVR-Math: A Dataset for Compositional Language, Visual and Mathematical Reasoning
• Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcement
• UI-R1: Enhancing Efficient Action Prediction of GUI Agents by Reinforcement Learning
• GUI-R1 : A Generalist R1-Style Vision-Language Action Model For GUI Agents
• MM-Eureka: Exploring the Frontiers of Multimodal Reasoning with Rule-based Reinforcement Learning
• DOCCI: Descriptions of Connected and Contrasting Images
• LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RL
• We-Math: Does Your Large Multimodal Model Achieve Human-like Mathematical Reasoning?

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models