XueruiSu / Trust-Region-Preference-ApproximationLinks
Trust Region Preference Approximation: A simple and stable reinforcement learning algorithm for LLM reasoning
☆13Updated 3 months ago
Alternatives and similar repositories for Trust-Region-Preference-Approximation
Users that are interested in Trust-Region-Preference-Approximation are comparing it to the libraries listed below
Sorting:
- LongLLaDA: Unlocking Long Context Capabilities in Diffusion LLMs☆40Updated 2 months ago
- ICML 2024 - Official Repository for EXO: Towards Efficient Exact Optimization of Language Model Alignment☆57Updated last year
- Reinforcing General Reasoning without Verifiers☆90Updated 3 months ago
- official implementation of ICLR'2025 paper: Rethinking Bradley-Terry Models in Preference-based Reward Modeling: Foundations, Theory, and…☆66Updated 6 months ago
- Code accompanying the paper "Noise Contrastive Alignment of Language Models with Explicit Rewards" (NeurIPS 2024)☆57Updated 11 months ago
- ☆98Updated last week
- [EMNLP 2025] WebAgent-R1: Training Web Agents via End-to-End Multi-Turn Reinforcement Learning☆47Updated last month
- ☆33Updated 11 months ago
- MathFusion: Enhancing Mathematical Problem-solving of LLM through Instruction Fusion (ACL 2025)☆30Updated 3 months ago
- Emergent Hierarchical Reasoning in LLMs/VLMs through Reinforcement Learning☆36Updated last month
- [ACL'24] Beyond One-Preference-Fits-All Alignment: Multi-Objective Direct Preference Optimization☆89Updated last year
- ☆22Updated 10 months ago
- A Sober Look at Language Model Reasoning☆84Updated last week
- implementation of dualformer☆21Updated 7 months ago
- Regressing the Relative Future: Efficient Policy Optimization for Multi-turn RLHF☆23Updated last year
- Code for "Reasoning to Learn from Latent Thoughts"☆121Updated 6 months ago
- ☆45Updated 2 weeks ago
- MetaLadder: Ascending Mathematical Solution Quality via Analogical-Problem Reasoning Transfer (EMNLP 2025)☆11Updated 6 months ago
- SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning☆156Updated last month
- Directional Preference Alignment☆57Updated last year
- [ICML 2025] Flow of Reasoning: Training LLMs for Divergent Reasoning with Minimal Examples☆107Updated 2 months ago
- exploring whether LLMs perform case-based or rule-based reasoning☆29Updated last year
- Reference implementation for Token-level Direct Preference Optimization(TDPO)☆148Updated 8 months ago
- Natural Language Reinforcement Learning☆98Updated 2 months ago
- Code for "Variational Reasoning for Language Models"☆47Updated 3 weeks ago
- [ICLR 2025] Code for the paper "Beyond Autoregression: Discrete Diffusion for Complex Reasoning and Planning"☆77Updated 8 months ago
- ☆76Updated last month
- This is an official implementation of the paper ``Building Math Agents with Multi-Turn Iterative Preference Learning'' with multi-turn DP…☆30Updated 10 months ago
- ☆116Updated 8 months ago
- [ICLR 2025] Official code of "Towards Robust Alignment of Language Models: Distributionally Robustifying Direct Preference Optimization"☆18Updated last year