Source Code for our ICLR'26 paper
β18Feb 22, 2026Updated 8 months ago
Alternatives and similar repositories for RLVR-Directions
Users that are interested in RLVR-Directions are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- π First survey bridging LLM, RL, and Agentic Eras β 100+ papers on efficient inference from static generation to systematic reasoning anβ¦β15May 13, 2026Updated 5 months ago
- Zipage is a high-concurrency LLM inference engine built on PagedAttention and KV cache eviction.β15Mar 13, 2026Updated 7 months ago
- [ICML 2026] Spherical Steering: Geometry-Aware Activation Rotation for Language Modelsβ23May 19, 2026Updated 5 months ago
- Official Repo for DAC-RL: Training LLMs for Divide-and-Conquer Reasoning Elevates Test-Time Scalabilityβ39Sep 20, 2026Updated last month
- β15Jan 20, 2026Updated 9 months ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits β’ AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- Procedural Knowledge at Scale Improves ReasoningThis repository contains the minimal, end-to-end pipeline for reproducing the paper resulβ¦β21Apr 1, 2026Updated 6 months ago
- [ICLR 2026] Official Implementation of ProxyThinker: Test-Time Guidance through Small Visual Reasoners.β22Sep 24, 2025Updated last year
- β15Sep 29, 2026Updated last month
- Weak-to-Strong On-Policy Distillationβ34Aug 9, 2026Updated 2 months ago
- Official GitHub repo for SCI-Verifier: Scientific Verifier with Thinking (ICLR2026).β11Jan 26, 2026Updated 9 months ago
- β36Jan 20, 2026Updated 9 months ago
- Latent On-Policy Self-Distillationβ62Sep 22, 2026Updated last month
- Agent-RRM: Exploring Reasoning Reward Model for Agentsβ73Mar 17, 2026Updated 7 months ago
- Official repository for Activation-Informed Merging (AIM) of Large Language Modelsβ25Feb 10, 2025Updated last year
- Deploy to Railway using AI coding agents - Free Credits Offer β’ AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- β65Mar 30, 2026Updated 6 months ago
- β21Aug 18, 2026Updated 2 months ago
- Adapter-X: A Novel General Parameter-Efficient Fine-Tuning Framework for Visionβ11Jul 22, 2024Updated 2 years ago
- REAM: Merging Improves Pruning of Experts in LLMsβ28Apr 16, 2026Updated 6 months ago
- A minimal open-source on-policy-distillation implementationβ11May 21, 2026Updated 5 months ago
- β17Mar 24, 2026Updated 7 months ago
- [NeurIPS'25] The official code of "PeRL: Permutation-Enhanced Reinforcement Learning for Interleaved Vision-Language Reasoning"β30Mar 30, 2026Updated 6 months ago
- Official repository for paper Routing-Free Mixture-of-Experts.β19Aug 23, 2026Updated 2 months ago
- The official implementation of ICLR26 poster, Pragma-VL: Towards a Pragmatic Arbitration of Safety and Helpfulness in MLLMs.β18Mar 31, 2026Updated 6 months ago
- Deploy on Railway without the complexity - Free Credits Offer β’ AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- [ICLR 2026] LookaheadKV: Fast and Accurate KV Cache Eviction by Glimpsing into the Future without Generationβ14Mar 16, 2026Updated 7 months ago
- On Policy Distillation Build on top of Verlβ103Sep 3, 2026Updated last month
- [ICML'26] Beyond Test-Time Memory: State-Space Optimal Control for LLM Reasoningβ17Jun 1, 2026Updated 4 months ago
- High-Throughput Batch Inferenceβ18Updated this week
- Scaling Test-time Training for LLM Reasoningβ37Apr 14, 2026Updated 6 months ago
- Code for [SeFA-Policy: Fast and Accurate Visuomotor Policy Learning with Selective Flow Alignment]β14Nov 12, 2025Updated 11 months ago
- [NeurIPS 2026 Pre-to-Post] From P(y|x) to P(y): Investigating Reinforcement Learning in Pre-train Spaceβ20Apr 16, 2026Updated 6 months ago
- Band-constrained Policy Optimization with probability-aware clipping for LLM reinforcement learningβ50Apr 8, 2026Updated 6 months ago
- δ»Ώι«εΎ·ε°ιηΊΏθ·―εΎSDKβ12Jun 15, 2021Updated 5 years ago
- GPU virtual machines on DigitalOcean Gradient AI β’ AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- Efficient and Effective Weight-Ensembling Mixture of Experts for Multi-Task Model Merging. Arxiv, 2024.β16Oct 28, 2024Updated 2 years ago
- β21Jul 26, 2026Updated 3 months ago
- Code for the "Long Context Needs Some R&R" paper.β12Mar 11, 2024Updated 2 years ago
- On-policy self-distillation using worked solutions from other problems.β18Aug 28, 2026Updated 2 months ago
- EANN(Pytorch)β10Mar 12, 2022Updated 4 years ago
- β15Aug 17, 2026Updated 2 months ago
- β11Mar 13, 2023Updated 3 years ago