NVlabs / NFTLinks
Implementation of Negative-aware Finetuning (NFT) algorithm for "Bridging Supervised Learning and Reinforcement Learning in Math Reasoning"
☆39Updated 2 weeks ago
Alternatives and similar repositories for NFT
Users that are interested in NFT are comparing it to the libraries listed below
Sorting:
- Optimizing Anytime Reasoning via Budget Relative Policy Optimization☆46Updated 2 months ago
- ☆92Updated last week
- SIFT: Grounding LLM Reasoning in Contexts via Stickers☆58Updated 6 months ago
- ☆55Updated 3 months ago
- TraceRL - Revolutionizing Reinforcement Learning Framework for Diffusion Large Language Models☆187Updated last week
- Code for "Reasoning to Learn from Latent Thoughts"☆118Updated 5 months ago
- MiroTrain is an efficient and algorithm-first framework for post-training large agentic models.☆85Updated 3 weeks ago
- ☆52Updated 2 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
- A repo for open research on building large reasoning models☆102Updated this week
- Revisiting Mid-training in the Era of Reinforcement Learning Scaling☆173Updated last month
- ☆100Updated this week
- The official repo of SynLogic: Synthesizing Verifiable Reasoning Data at Scale for Learning Logical Reasoning and Beyond☆166Updated 2 months ago
- official code for "BoostStep: Boosting mathematical capability of Large Language Models via improved single-step reasoning"☆36Updated 8 months ago
- ☆57Updated 2 months ago
- Code accompanying the paper "Noise Contrastive Alignment of Language Models with Explicit Rewards" (NeurIPS 2024)☆57Updated 10 months ago
- ☆44Updated 3 months ago
- Official repository for paper "DeepCritic: Deliberate Critique with Large Language Models"☆35Updated 2 months ago
- ☆34Updated 3 weeks ago
- ☆43Updated 5 months ago
- SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning☆147Updated this week
- [COLM 2025] Code for Paper: Learning Adaptive Parallel Reasoning with Language Models☆128Updated last month
- [EMNLP 2025] LightThinker: Thinking Step-by-Step Compression☆98Updated 5 months ago
- Official Repository of LatentSeek☆60Updated 3 months ago
- ReasonFlux-Coder: Open-Source LLM Coders with Co-Evolving Reinforcement Learning☆115Updated 3 weeks ago
- [NeurIPS 2024] Can LLMs Learn by Teaching for Better Reasoning? A Preliminary Study☆54Updated 9 months ago
- Repo for "Z1: Efficient Test-time Scaling with Code"☆64Updated 5 months ago
- A Sober Look at Language Model Reasoning☆83Updated last week
- [NeurIPS-2024] 📈 Scaling Laws with Vocabulary: Larger Models Deserve Larger Vocabularies https://arxiv.org/abs/2407.13623☆86Updated 11 months ago
- AnchorAttention: Improved attention for LLMs long-context training☆212Updated 8 months ago