zhyang2226 / AR-LoptiLinks
[AI4MATH@ICML2025] Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs
☆40Updated 4 months ago
Alternatives and similar repositories for AR-Lopti
Users that are interested in AR-Lopti are comparing it to the libraries listed below
Sorting:
- CoT-Valve: Length-Compressible Chain-of-Thought Tuning☆86Updated 7 months ago
- ☆167Updated 4 months ago
- Laser: Learn to Reason Efficiently with Adaptive Length-based Reward Shaping☆54Updated 4 months ago
- [arXiv2505] Think Silently, Think Fast: Dynamic Latent Compression of LLM Reasoning Chains☆50Updated last month
- [ICML 2025] M-STAR (Multimodal Self-Evolving TrAining for Reasoning) Project. Diving into Self-Evolving Training for Multimodal Reasoning☆69Updated 2 months ago
- ☆50Updated 2 months ago
- The Entropy Mechanism of Reinforcement Learning for Large Language Model Reasoning.☆331Updated 2 months ago
- [NeurIPS 2025🔥]Main source code of SRPO framework.☆83Updated this week
- ACL'2025: SoftCoT: Soft Chain-of-Thought for Efficient Reasoning with LLMs. and preprint: SoftCoT++: Test-Time Scaling with Soft Chain-of…☆46Updated 3 months ago
- ☆43Updated 5 months ago
- AdaRFT: Efficient Reinforcement Finetuning via Adaptive Curriculum Learning☆45Updated 3 months ago
- This is the official implementation of the paper "S²R: Teaching LLMs to Self-verify and Self-correct via Reinforcement Learning"☆69Updated 5 months ago
- Official codebase for "GenPRM: Scaling Test-Time Compute of Process Reward Models via Generative Reasoning".☆81Updated 3 months ago
- ☆332Updated last month
- This repository contains a regularly updated paper list for LLMs-reasoning-in-latent-space.☆157Updated last week
- AdaptiveStep: Automatically Dividing Reasoning Step through Model Confidence☆10Updated 6 months ago
- ☆46Updated 5 months ago
- [ICML 2024] Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibrati…☆42Updated last year
- Optimizing Anytime Reasoning via Budget Relative Policy Optimization☆47Updated 2 months ago
- Official Repository of LatentSeek☆60Updated 3 months ago
- ☆67Updated 5 months ago
- End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning☆284Updated last week
- ☆209Updated 7 months ago
- [ICML'25] Our study systematically investigates massive values in LLMs' attention mechanisms. First, we observe massive values are concen…☆80Updated 3 months ago
- Chain of Thoughts (CoT) is so hot! so long! We need short reasoning process!☆69Updated 5 months ago
- [ACL'24] Beyond One-Preference-Fits-All Alignment: Multi-Objective Direct Preference Optimization☆87Updated last year
- Implementation for the research paper "Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision".☆56Updated 9 months ago
- Official repository for paper: O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning☆88Updated 7 months ago
- repo for paper https://arxiv.org/abs/2504.13837☆193Updated 2 months ago
- Model merging is a highly efficient approach for long-to-short reasoning.☆82Updated 3 months ago