Reinforcing Multimodal Reasoning via Token-Level Perception-Grounded Advantage Estimation
cs.AI
Submitted: 2026-09-30
Updated: 2026-09-30
Code: https://github.com/Zhihan72/TPAE
Terminology
Sources
- Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- SophiaVL-R1: Reinforcing MLLMs Reasoning with Thinking Reward
- Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models
- MMR1: Enhancing Multimodal Reasoning with Variance-Aware Sampling and Open Resources
- SPHINX: The Joint Mixing of Weights, Tasks, and Visual Embeddings for Multi-modal Large Language Models
- MM-Eureka: Exploring the Frontiers of Multimodal Reasoning with Rule-based Reinforcement Learning
- Proximal Policy Optimization Algorithms
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Qwen3 Technical Report
- Visionary-R1: Mitigating Shortcuts in Visual Reasoning with Reinforcement Learning
- Perception-R1: Advancing Multimodal Reasoning Capabilities of MLLMs via Visual Perception Reward
- LogicVista: Multimodal LLM Logical Reasoning Benchmark in Visual Contexts
- Shuffle-R1: Efficient RL framework for Multimodal Large Language Models via Data-centric Dynamic Shuffle
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems