AdaC-GRPO: Towards Mastering Long-Horizon Visual Sudoku Puzzles via Adaptive Curriculum Learning
cs.AI
Submitted: 2026-10-09
Updated: 2026-10-09
Code: https://github.com/DuHeng0128/AdaC-GRPO
Terminology
Sources
- Qwen3-VL Technical Report
- Qwen2.5-VL Technical Report
- Video-Holmes: Can MLLM Think Like Holmes for Complex Video Reasoning?
- Training Verifiers to Solve Math Word Problems
- DeepSeek-V3 Technical Report
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Video-R1: Reinforcing Video Reasoning in MLLMs
- Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
- Measuring Mathematical Problem Solving With the MATH Dataset
- Video-MMMU: Evaluating Knowledge Acquisition from Multi-Discipline Professional Videos
- CrossWordBench: Evaluating the Reasoning Capabilities of LLMs and LVLMs with Controllable Puzzle Generation
- Zebra-CoT: A Dataset for Interleaved Vision Language Reasoning
- CMM-Math: A Chinese Multimodal Math Dataset To Evaluate and Enhance the Mathematics Reasoning of Large Multimodal Models
- VideoReasonBench: Can MLLMs Perform Vision-Centric Complex Video Reasoning?
- GPT-4o System Card
- ReasonBENCH: Benchmarking the (In)Stability of LLM Reasoning
- VCR-Bench: A Comprehensive Evaluation Framework for Video Chain-of-Thought Reasoning
- Sudoku-Bench: Evaluating creative reasoning with Sudoku variants
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Efficient Reinforcement Finetuning via Adaptive Curriculum Learning
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