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."
☆57Jan 5, 2026Updated 6 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:
- [Nature Machine Intelligence 2025] Emulating Human-like Adaptive Vision for Efficient and Flexible Machine Visual Perception☆152May 27, 2026Updated last month
- ☆14Dec 19, 2024Updated last year
- ☆16Apr 12, 2024Updated 2 years ago
- [ICML 2024] SimPro: A Simple Probabilistic Framework Towards Realistic Long-Tailed Semi-Supervised Learning☆31Sep 30, 2024Updated last year
- [ECCV 2024] AdaNAT: Exploring Adaptive Policy for Token-Based Image Generation☆37Sep 12, 2024Updated last year
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- IMG: Calibrating Diffusion Models via Implicit Multimodal Guidance, ICCV 2025☆30Oct 1, 2025Updated 9 months ago
- [ICLR 2026] Code of "MemoryVLA: Perceptual-Cognitive Memory in Vision-Language-Action Models for Robotic Manipulation"☆293Jun 13, 2026Updated 3 weeks ago
- ☆55Jan 2, 2025Updated last year
- CODA: Repurposing Continuous VAEs for Discrete Tokenization☆37Jul 4, 2025Updated last year
- [IEEE TPAMI] Latency-aware Unified Dynamic Networks for Efficient Image Recognition☆53Mar 20, 2025Updated last year
- Official implementation of Dynamic Perceiver☆44Nov 16, 2023Updated 2 years ago
- Official code of paper Understanding, Predicting and Better Resolving Q-Value Divergence in Offline-RL☆24Oct 30, 2023Updated 2 years ago
- Official repository of Uni-AdaFocus (TPAMI 2024).☆60Dec 17, 2024Updated last year
- [NeurIPS 2024] ENAT: Rethinking Spatial-temporal Interactions in Token-based Image Synthesis☆25Nov 28, 2024Updated last year
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- repo for paper https://arxiv.org/abs/2504.13837☆345Dec 17, 2025Updated 6 months ago
- Jittor implementation of Vision Transformer with Deformable Attention☆32Mar 1, 2022Updated 4 years ago
- Official implementation of A Mixture of Surprises for Unsupervised Reinforcement Learning☆23Nov 16, 2022Updated 3 years ago
- 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
- [TPAMI 2024] Probabilistic Contrastive Learning for Long-Tailed Visual Recognition☆95Sep 30, 2024Updated last year
- [CVPR 2025] EchoWorld: Learning Motion-Aware World Models for Echocardiography Probe Guidance☆47Apr 18, 2025Updated last year
- [CVPR 2025] CheXWorld: Exploring Image World Modeling for Radiograph Representation Learning☆48Apr 21, 2025Updated last year
- [CVPR2024] GSVA: Generalized Segmentation via Multimodal Large Language Models☆166Sep 12, 2024Updated last year
- Repository of GridMix (ICLR 2025)☆36Mar 18, 2025Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- The official source code for "Boosting LLM Agents with Recursive Contemplation for Effective Deception Handling" (ACL 2024, Findings)☆15Aug 12, 2024Updated last year
- ☆14Dec 16, 2023Updated 2 years ago
- [ECCV 2022] Learning to Weight Samples for Dynamic Early-exiting Networks☆38Sep 28, 2023Updated 2 years ago
- Code release for Deep Incubation (https://arxiv.org/abs/2212.04129)☆92Mar 16, 2023Updated 3 years ago
- (CVPR 2026) Long-RVOS: A Comprehensive Benchmark for Long-term Referring Video Object Segmentation☆36Feb 28, 2026Updated 4 months ago
- ☆98Dec 29, 2024Updated last year
- LoPA: Scaling dLLM Inference via Lookahead Parallel Decoding☆39Apr 25, 2026Updated 2 months ago
- ☆26Nov 26, 2024Updated last year
- ☆225Dec 20, 2024Updated last year
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- 1.5−3.0× lossless training or pre-training speedup. An off-the-shelf, easy-to-implement algorithm for the efficient training of foundatio…☆230Aug 23, 2024Updated last year
- Checkpoint for Voyager, 160 iterations.☆23May 27, 2023Updated 3 years ago
- Build LLM Application with Local Documents☆20Jun 13, 2025Updated last year
- [NeurIPS 2023] Rank-DETR for High Quality Object Detection☆106Oct 19, 2023Updated 2 years ago
- Repository of Vision Transformer with Deformable Attention (CVPR2022) and DAT++: Spatially Dynamic Vision Transformerwith Deformable Atte…☆21Apr 17, 2024Updated 2 years ago
- ☆37Dec 2, 2025Updated 7 months ago
- Implementation of Bitune: Bidirectional Instruction-Tuning☆27Jun 19, 2025Updated last year