[ICLR 2026] Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs
☆46May 20, 2025Updated last year
Alternatives and similar repositories for AR-Lopti
Users that are interested in AR-Lopti are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [ICLR 2024] DMBP: Diffusion Model-Based Predictor for Robust Offline Reinforcement Learning against State Observations Perturbations.☆17May 24, 2024Updated 2 years ago
- [CVPR 2025 (Oral)] Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key☆111Jan 9, 2026Updated 6 months ago
- UFT: Unifying Supervised and Reinforcement Fine-Tuning☆31Jun 30, 2025Updated last year
- ArcherCodeR is an open-source initiative enhancing code reasoning in large language models through scalable, rule-governed reinforcement …☆44Aug 6, 2025Updated 11 months ago
- [ICLR 2025 Spotlight] Official PyTorch Implementation of "What Makes a Good Diffusion Planner for Decision Making?"☆84Apr 20, 2025Updated last year
- End-to-end encrypted cloud storage - Proton Drive • AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- Official Repository of "Learning what reinforcement learning can't"☆84Dec 30, 2025Updated 6 months ago
- ☆81Jun 8, 2026Updated last month
- [ICLR 2024 Spotlight] Code for ICLR 2024 paper "Towards Robust Offline Reinforcement Learning under Diverse Data Corruption"☆22Nov 25, 2024Updated last year
- Klear-Reasoner: Advancing Reasoning Capability via Gradient-Preserving Clipping Policy Optimization☆82Dec 25, 2025Updated 6 months ago
- [NeurIPS 2025] RL Tango: Reinforcing Generator and Verifier Together for Language Reasoning☆57Oct 23, 2025Updated 8 months ago
- Easy-to-Hard Learning for Information Extraction (ACL 2023 Findings)☆14Jul 11, 2023Updated 3 years ago
- [NeurIPS 2024 poster] Cross-model Control: Improving Multiple Large Language Models in One-time Training☆14Oct 25, 2024Updated last year
- Official Repository of "Learning to Reason under Off-Policy Guidance"☆459Mar 20, 2026Updated 4 months ago
- ☆20Dec 14, 2024Updated last year
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- [NeurIPS 2025] Implementation for the paper "The Surprising Effectiveness of Negative Reinforcement in LLM Reasoning"☆165Mar 2, 2026Updated 4 months ago
- The Entropy Mechanism of Reinforcement Learning for Large Language Model Reasoning.☆443Jul 11, 2025Updated last year
- Behavior Injection: Preparing Language Models for Reinforcement Learning (NeurIPS 2025)☆17Jul 1, 2025Updated last year
- Official github repo for "Fractional Reasoning via Latent Steering Vectors Improves Inference Time Compute"☆17Jun 30, 2025Updated last year
- ☆16Feb 4, 2026Updated 5 months ago
- Official repository for paper "DeepCritic: Deliberate Critique with Large Language Models"☆41Jun 24, 2025Updated last year
- Extrapolating RLVR to General Domains without Verifiers☆205Aug 12, 2025Updated 11 months ago
- A repo for open research on building large reasoning models☆151Jul 3, 2026Updated 2 weeks ago
- generate pacenote from AMAP WebAPI☆14Jun 20, 2021Updated 5 years ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- TreeRL: LLM Reinforcement Learning with On-Policy Tree Search in ACL'25☆97Jun 16, 2025Updated last year
- Emergent Hierarchical Reasoning in LLMs/VLMs through Reinforcement Learning [ICLR26]☆64Apr 11, 2026Updated 3 months ago
- ☆20Mar 18, 2026Updated 4 months ago
- Socratic-Zero is a fully autonomous framework that generates high-quality training data for mathematical reasoning☆37Oct 26, 2025Updated 8 months ago
- NeurIPS 2025: Discriminative Constrained Optimization for Reinforcing Large Reasoning Models☆53Mar 14, 2026Updated 4 months ago
- Self-Hinting Language Models Enhance Reinforcement Learning☆26Mar 28, 2026Updated 3 months ago
- ☆68Jul 14, 2025Updated last year
- Nonebot 2 and Chiyuki(Mai-bot) based on the second creation of the multifunctional Bot. 基于Nonebot 2和Chiyuki(Mai-Bot)二创的多功能音游Bot，主服务项为舞萌DX…☆10Jan 10, 2023Updated 3 years ago
- LCA-on-the-line (ICML 2024 Oral)☆14Feb 13, 2025Updated last year
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- [ICML 2026] Heima☆75May 20, 2026Updated 2 months ago
- [ICLR 2025] Unintentional Unalignment: Likelihood Displacement in Direct Preference Optimization☆32Jan 7, 2026Updated 6 months ago
- PyTorch codes for the paper "An Empirical Study of Multimodal Model Merging"☆37Oct 11, 2023Updated 2 years ago
- [ICLR 2026] Geometric-Mean Policy Optimization☆104Jan 26, 2026Updated 5 months ago
- The official implementation of "Helen: Optimizing CTR Prediction Models with Frequency-wise Hessian Eigenvalue Regularization"☆16Mar 14, 2024Updated 2 years ago
- The Newton-Muon optimizer☆30Jun 5, 2026Updated last month
- An Ultra-Long Output Reinforcement Learning Approach☆23Jul 31, 2025Updated 11 months ago