Shenzhi-Wang / Beyond-the-80-20-Rule-RLVRLinks
The open-source code for the NeurIPS 2025 paper, "Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning."
☆14Updated last week
Alternatives and similar repositories for Beyond-the-80-20-Rule-RLVR
Users that are interested in Beyond-the-80-20-Rule-RLVR are comparing it to the libraries listed below
Sorting:
- ☆13Updated 11 months ago
- [ECCV 2024] AdaNAT: Exploring Adaptive Policy for Token-Based Image Generation☆34Updated last year
- [Nature Machine Intelligence 2025] Emulating Human-like Adaptive Vision for Efficient and Flexible Machine Visual Perception☆106Updated 2 weeks ago
- [NeurIPS 2025] NoisyRollout: Reinforcing Visual Reasoning with Data Augmentation☆100Updated 2 months ago
- [NeurIPS 2024] ENAT: Rethinking Spatial-temporal Interactions in Token-based Image Synthesis☆24Updated last year
- The official code of "VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning" [NeurIPS25]☆168Updated 6 months ago
- A Self-Training Framework for Vision-Language Reasoning☆87Updated 10 months ago
- repo for paper https://arxiv.org/abs/2504.13837☆278Updated 5 months ago
- Official repo for "PAPO: Perception-Aware Policy Optimization for Multimodal Reasoning"☆104Updated last week
- Segment Policy Optimization: Effective Segment-Level Credit Assignment in RL for Large Language Models☆42Updated 2 months ago
- [NeurIPS 2025] The official repository for our paper, "Open Vision Reasoner: Transferring Linguistic Cognitive Behavior for Visual Reason…☆150Updated 3 months ago
- The official repository for the paper "ThinkMorph: Emergent Properties in Multimodal Interleaved Chain-of-Thought Reasoning"☆119Updated 2 weeks ago
- MM-PRM: Enhancing Multimodal Mathematical Reasoning with Scalable Step-Level Supervision☆25Updated 6 months ago
- [NeurIPS 2025] MINT-CoT: Enabling Interleaved Visual Tokens in Mathematical Chain-of-Thought Reasoning☆90Updated 2 months ago
- One-shot Entropy Minimization☆187Updated 6 months ago
- Github repository for "Bring Reason to Vision: Understanding Perception and Reasoning through Model Merging" (ICML 2025)☆86Updated 2 months ago
- Official PyTorch code for ICLR 2025 paper "Gnothi Seauton: Empowering Faithful Self-Interpretability in Black-Box Models"☆24Updated 9 months ago
- [NeurIPS 2025] Think Silently, Think Fast: Dynamic Latent Compression of LLM Reasoning Chains☆63Updated 4 months ago
- Co-Reinforcement Learning for Unified Multimodal Understanding and Generation☆31Updated 4 months ago
- ☆62Updated 7 months ago
- [NeurIPS 2025] VeriThinker: Learning to Verify Makes Reasoning Model Efficient☆63Updated 2 months ago
- ☆20Updated 5 months ago
- ☆297Updated 2 months ago
- Official code of *Virgo: A Preliminary Exploration on Reproducing o1-like MLLM*☆109Updated 6 months ago
- Code release for VTW (AAAI 2025 Oral)☆65Updated last month
- Machine Mental Imagery: Empower Multimodal Reasoning with Latent Visual Tokens (arXiv 2025)☆205Updated 4 months ago
- Code repo for "Harnessing Negative Signals: Reinforcement Distillation from Teacher Data for LLM Reasoning"☆30Updated 4 months ago
- [ICML 2025 Oral] The official repository for the paper "Can MLLMs Reason in Multimodality? EMMA: An Enhanced MultiModal ReAsoning Benchma…☆68Updated 4 months ago
- ☆104Updated 11 months ago
- Imagine While Reasoning in Space: Multimodal Visualization-of-Thought (ICML 2025)☆59Updated 8 months ago