Source Code for our ICLR'26 paper
☆17Feb 22, 2026Updated 6 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:
- Official Repo for DAC-RL: Training LLMs for Divide-and-Conquer Reasoning Elevates Test-Time Scalability☆16Feb 26, 2026Updated 6 months ago
- [ICML 2026] Spherical Steering: Geometry-Aware Activation Rotation for Language Models☆21May 19, 2026Updated 3 months ago
- Code for Research Project TLDR☆26Jul 28, 2025Updated last year
- ☆15Jan 20, 2026Updated 7 months ago
- [ICLR 2026] Official Implementation of ProxyThinker: Test-Time Guidance through Small Visual Reasoners.☆22Sep 24, 2025Updated 11 months ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- ☆36Jan 20, 2026Updated 7 months ago
- Official repository for Activation-Informed Merging (AIM) of Large Language Models☆25Feb 10, 2025Updated last year
- REAM: Merging Improves Pruning of Experts in LLMs☆25Apr 16, 2026Updated 4 months ago
- Agent-RRM: Exploring Reasoning Reward Model for Agents☆70Mar 17, 2026Updated 5 months ago
- ☆65Mar 30, 2026Updated 5 months ago
- ☆16Mar 24, 2026Updated 5 months ago
- Implementation for "EpiCoder: Encompassing Diversity and Complexity in Code Generation" (ICML 2025)☆28May 16, 2025Updated last year
- [arxiv: 2604.14142] From P(y|x) to P(y): Investigating Reinforcement Learning in Pre-train Space☆17Apr 16, 2026Updated 4 months ago
- [NeurIPS'25] The official code of "PeRL: Permutation-Enhanced Reinforcement Learning for Interleaved Vision-Language Reasoning"☆30Mar 30, 2026Updated 5 months ago
- 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.
- [ICML'26] Beyond Test-Time Memory: State-Space Optimal Control for LLM Reasoning☆17Jun 1, 2026Updated 2 months ago
- Official implementation of BandPO: Bridging Trust Regions and Ratio Clipping via Probability-Aware Bounds for LLM Reinforcement Learning.…☆50Apr 8, 2026Updated 4 months ago
- Code for the "Long Context Needs Some R&R" paper.☆12Mar 11, 2024Updated 2 years ago
- ☆23May 14, 2026Updated 3 months ago
- ☆14May 4, 2024Updated 2 years ago
- ☆65Dec 4, 2025Updated 8 months ago
- EANN(Pytorch)☆10Mar 12, 2022Updated 4 years ago
- ☆35Jul 30, 2026Updated last month
- Official GitHub repo for Scaling Physical Reasoning with the PHYSICS Dataset (NeurIPS25).☆16Sep 20, 2025Updated 11 months ago
- 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 implementation for FREE-Merging: Fourier Transform for Model Merging with Lightweight Experts (ICCV25)☆16Jun 26, 2025Updated last year
- ☆24Nov 4, 2025Updated 9 months ago
- [ICLR 2026] Block-wise Adaptive Caching for Accelerating Diffusion Policy☆18Jan 27, 2026Updated 7 months ago
- [EMNLP 2026' Main] HoliTok:A Continuous Holistic Tokenization with Robust Dual Capabilities of Speech Generation and Understanding☆49Jun 8, 2026Updated 2 months ago
- Low-Rank Rescaled Vision Transformer Fine-Tuning: A Residual Design Approach, CVPR 2024☆27Jul 25, 2024Updated 2 years ago
- [EMNLP'22] Weakly-Supervised Temporal Article Grounding☆14Nov 25, 2023Updated 2 years ago
- An arbitrage bot is a smart contract connected to an external automation script that controls its operation.☆2,690Updated this week
- pytorch版损失函数，改写自科学空间文章，【通过互信息思想来缓解类别不平衡问题】、【将“softmax+交叉熵”推广到多标签分类问题】☆12Aug 22, 2021Updated 5 years ago
- [ACL'26 Findings] Steering LLM Thinking with Budget Guidance☆34Feb 19, 2026Updated 6 months ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- LONGAGENT: Scaling Language Models to 128k Context through Multi-Agent Collaboration☆11Mar 11, 2024Updated 2 years ago
- A dataset and CLIP baseline for unrepresentative news thumbnail detection (ACL 2022 workshop)☆12May 26, 2022Updated 4 years ago
- ☆10Jun 21, 2021Updated 5 years ago
- xKV: Cross-Layer SVD for KV-Cache Compression [ICML 2026]☆57Jul 7, 2026Updated last month
- Pytorch code for NeurIPS 2025 paper "Accurate and Efficient Low-Rank Model Merging in Core Space"☆41Feb 2, 2026Updated 6 months ago
- MathFusion: Enhancing Mathematical Problem-solving of LLM through Instruction Fusion (ACL 2025)☆37Jul 16, 2025Updated last year
- Everything for the Paper: 'Evoke: Evoking Critical Thinking Abilities in LLMs via Reviewer-Author Prompt Editing'☆19Dec 2, 2023Updated 2 years ago