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."
☆70Jan 5, 2026Updated 9 months ago
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. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆21Mar 5, 2025Updated last year
- IMG: Calibrating Diffusion Models via Implicit Multimodal Guidance, ICCV 2025☆30Oct 1, 2025Updated last year
- InsightTok: Improving Text and Face Fidelity in Discrete Tokenization for Autoregressive Image Generation☆42Oct 9, 2026Updated last week
- 🔥 Regeneration over editing: unlocking more effective image refinement!☆54May 26, 2026Updated 4 months ago
- ☆23Oct 1, 2026Updated 2 weeks ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- ☆14Dec 19, 2024Updated last year
- ☆16Apr 12, 2024Updated 2 years ago
- ☆38Dec 2, 2025Updated 10 months ago
- Official code of paper Understanding, Predicting and Better Resolving Q-Value Divergence in Offline-RL☆24Oct 30, 2023Updated 2 years ago
- ☆56Jan 2, 2025Updated last year
- [ICML 2024] SimPro: A Simple Probabilistic Framework Towards Realistic Long-Tailed Semi-Supervised Learning☆31Sep 30, 2024Updated 2 years ago
- Official implementation of Dynamic Perceiver☆43Nov 16, 2023Updated 2 years ago
- ☆34May 27, 2026Updated 4 months ago
- CODA: Repurposing Continuous VAEs for Discrete Tokenization☆37Jul 4, 2025Updated last year
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- [NeurIPS 2024] ENAT: Rethinking Spatial-temporal Interactions in Token-based Image Synthesis☆25Nov 28, 2024Updated last year
- Jittor implementation of Vision Transformer with Deformable Attention☆32Mar 1, 2022Updated 4 years ago
- [IEEE TPAMI] Latency-aware Unified Dynamic Networks for Efficient Image Recognition☆53Mar 20, 2025Updated last year
- repo for paper https://arxiv.org/abs/2504.13837☆354Jul 27, 2026Updated 2 months ago
- ArcherCodeR is an open-source initiative enhancing code reasoning in large language models through scalable, rule-governed reinforcement …☆44Aug 6, 2025Updated last year
- Repository of "Train Once, Get a Family: State-Adaptive Balances for Offline-to-Online Reinforcement Learning" (NeurIPS 2023 Spotlight)☆41Oct 30, 2023Updated 2 years ago
- [Nature Machine Intelligence 2025] Emulating Human-like Adaptive Vision for Efficient and Flexible Machine Visual Perception☆160May 27, 2026Updated 4 months ago
- [ICML 2026 Outstanding Paper] Minimalist RL for Diffusion LLMs. 89.1% on GSM8K.☆287Jul 6, 2026Updated 3 months ago
- [AAAI 2026 Oral] SpatialActor: Exploring Disentangled Spatial Representations for Robust Robotic Manipulation☆65Jun 13, 2026Updated 4 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Official repository of Uni-AdaFocus (TPAMI 2024).☆59Dec 17, 2024Updated last year
- [TPAMI 2024] Probabilistic Contrastive Learning for Long-Tailed Visual Recognition☆96Sep 30, 2024Updated 2 years ago
- ☆33Nov 14, 2025Updated 11 months ago
- ☆14Dec 16, 2023Updated 2 years ago
- Official implementation of A Mixture of Surprises for Unsupervised Reinforcement Learning☆23Nov 16, 2022Updated 3 years ago
- [CVPR 2022] Official repository of AdaFocusV2.☆92Dec 15, 2024Updated last year
- Archer2.0 evolves from its predecessor by introducing ASPO, which overcomes fundamental PPO-Clip limitations to prevent premature converg…☆31Oct 10, 2025Updated last year
- ☆68Updated this week
- An extension of veRL for post-training LLM reasoners with on-policy self-distillation and self-distilled RLVR.☆77Updated this week
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- [ECCV 2024] Efficient Diffusion Transformer with Step-wise Dynamic Attention Mediators☆48Sep 11, 2024Updated 2 years ago
- Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity☆22Aug 28, 2025Updated last year
- TreeRL: LLM Reinforcement Learning with On-Policy Tree Search in ACL'25☆106Jun 16, 2025Updated last year
- The Entropy Mechanism of Reinforcement Learning for Large Language Model Reasoning.☆454Jul 11, 2025Updated last year
- Code release for Deep Incubation (https://arxiv.org/abs/2212.04129)☆92Mar 16, 2023Updated 3 years ago
- ☆17Sep 26, 2026Updated 3 weeks ago
- [CVPR2024] GSVA: Generalized Segmentation via Multimodal Large Language Models☆169Sep 12, 2024Updated 2 years ago