SFT-then-RL Outperforms Mixed-Policy Methods for LLM Reasoning paper code.
☆12Aug 9, 2026Updated 2 months ago
Alternatives and similar repositories for sft_then_rl
Users that are interested in sft_then_rl are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [ICML 2026] Official implementation for paper: Learning Self-Correction in Vision–Language Models via Rollout Augmentation☆16Jun 4, 2026Updated 5 months ago
- ☆16Sep 8, 2025Updated last year
- [ECCV'26] Coevolving Representations in Joint Image-Feature Diffusion☆15Sep 14, 2026Updated last month
- [ECCV 2026] REGLUE Your Latents with Global and Local Semantics for Entangled Diffusion☆14Jul 19, 2026Updated 3 months ago
- ☆17Oct 28, 2026Updated last week
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- Afterburner: Reinforcement Learning Facilitates Self-Improving Code Efficiency Optimization☆15Apr 5, 2026Updated 7 months ago
- pretrain experiments☆14Updated this week
- [BabyLM@EMNLP 2025 - Challenge Award] Official Implementation: Masked Diffusion Language Models with Frequency-Informed Training☆16Dec 17, 2025Updated 10 months ago
- ☆27Jan 23, 2024Updated 2 years ago
- ☆15Sep 28, 2026Updated last month
- Developing a Korean LLM model : Hate Speech Filtering, Improving conversational skills, Finetuning with the RLHF method☆20May 27, 2025Updated last year
- ☆17Nov 23, 2021Updated 4 years ago
- ☆69Oct 16, 2026Updated 3 weeks ago
- Official repo for "Persistent Visual Memory: Sustaining Perception for Deep Generation in LVLMs"☆13May 5, 2026Updated 6 months ago
- 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.
- Implementation of Bitune: Bidirectional Instruction-Tuning☆27Jun 19, 2025Updated last year
- ☆13Jul 15, 2026Updated 3 months ago
- ☆23Jun 3, 2026Updated 5 months ago
- Official Implementation of Latent-Foresight: End-to-End Learning Predictable Representations for Latent World Models☆24Oct 5, 2026Updated last month
- [ECCV 2026] Official Implementation of Representations Before Pixels: Semantics-Guided Hierarchical Video Prediction☆19Sep 6, 2026Updated 2 months ago
- compare the theory attention gradient with PyTorch attention gradient☆16Apr 1, 2024Updated 2 years ago
- A python package for loading robotics datasets which were recorded on the TriFinger platform. Also contains simulated gym environments th…☆18Jan 17, 2024Updated 2 years ago
- [AAAI 2025] The official implementation for the "Motion Decoupled 3D Gaussian Splatting for Dynamic Object Representation"☆18Jul 18, 2025Updated last year
- ☆11Jul 1, 2025Updated 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.
- ☆12Jan 13, 2026Updated 9 months ago
- A unified framework for vision-language environments with Gymnasium-compatible interface☆38Mar 17, 2026Updated 7 months ago
- LatentLoop: Scaling Looped MoE Models with Asymmetric Compute Allocation☆16Oct 15, 2026Updated 3 weeks ago
- repo of paper implementations☆20Feb 25, 2025Updated last year
- A critical analysis of the Cambrian-S model and VSI-Super benchmarks☆16Nov 20, 2025Updated 11 months ago
- The interface between probabilistic model checking and data-driven policy learning.☆21Updated this week
- The official implemention of "Depth-Breadth Synergy in RLVR: Unlocking LLM Reasoning Gains with Adaptive Exploration" (ICML 2026)☆28Feb 4, 2026Updated 9 months ago
- Nanochat in MLX☆12Mar 6, 2026Updated 8 months ago
- [ICLR 2024 Spotlight] Code for ICLR 2024 paper "Towards Robust Offline Reinforcement Learning under Diverse Data Corruption"☆22Nov 25, 2024Updated 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.
- P1-VL: Bridging Visual Perception and Scientific Reasoning in Physics Olympiads☆15Feb 11, 2026Updated 8 months ago
- ☆26Oct 9, 2025Updated last year
- [preprint] Think Longer to Explore Deeper: Learn to Explore In-Context via Length-Incentivized Reinforcement Learning☆19Feb 18, 2026Updated 8 months ago
- ☆13Jul 25, 2023Updated 3 years ago
- ☆24Jul 20, 2026Updated 3 months ago
- Official code of Geometric Autoencoder for Diffusion Models.☆23Mar 12, 2026Updated 7 months ago
- 📄 Forgetting in Language Models: Capacity, Optimization, and Self-Generated Replay☆26Jul 17, 2026Updated 3 months ago