On-Policy Distillation 调研资料：包含 ICLR 2024 论文、Hugging Face TRL 和 Thinking Machines Lab 的代码实现
☆25Dec 7, 2025Updated 7 months ago
Alternatives and similar repositories for on-policy-distillation-research
Users that are interested in on-policy-distillation-research are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Implementation of On-Policy Distillation (GKD) for Language Models - ICLR 2024☆23Nov 24, 2025Updated 7 months ago
- ☆15Nov 17, 2020Updated 5 years ago
- ☆10Jul 14, 2024Updated 2 years ago
- Repository for the paper "Advancing General-Purpose Reasoning Models with Modular Gradient Surgery"☆21Mar 15, 2026Updated 4 months ago
- [EMNLP 2025] Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment☆15Jul 22, 2025Updated 11 months ago
- Open source password manager - Proton Pass • AdSecurely store, share, and autofill your credentials with Proton Pass, the end-to-end encrypted password manager trusted by millions.
- ☆22May 23, 2025Updated last year
- This is the code repo for the paper <UTC-IE: A Unified Token-pair Classification Architecture for Information Extraction>☆15Aug 10, 2023Updated 2 years ago
- A naive implementation of the TableRag Paper☆38Oct 22, 2024Updated last year
- [ICLR' 26] Implementation of "Curriculum Reinforcement Learning from Easy to Hard Tasks Improves LLM Reasoning"☆24May 28, 2026Updated last month
- This repository includes the introduction to uncertain label in Chest X-Ray diagnosis.☆10Oct 20, 2024Updated last year
- PyTorch pipeline for Kaggle Jigsaw Toxic Comment Classification Challenge☆11Mar 23, 2018Updated 8 years ago
- ☆15Mar 22, 2026Updated 3 months ago
- The objective of this project is to demonstrate how to fine-tune deepseek-r1-distill-llama-8b.☆17Feb 19, 2025Updated last year
- [CVPR2021] VaB-AL: Incorporating Class Imbalance and Difficulty with Variational Bayes for Active Learning☆14Oct 3, 2021Updated 4 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Created a classifier that can identify and classify 41 types of facial attributes, using an ImageNet pre-trained ResNext50 model provided…☆11May 12, 2021Updated 5 years ago
- [TMI2023] Context Label Learning: Improving Background Class Representations in Semantic Segmentation.☆19Jan 23, 2024Updated 2 years ago
- Official repository of MICCAI 2022 Challenge: KiPA22☆16Oct 4, 2022Updated 3 years ago
- DCPO: Dynamic Adaptive Clipping for RL☆49Apr 1, 2026Updated 3 months ago
- ☆17Nov 26, 2024Updated last year
- RedSearcher's framework for deep search agent trajectory synthesis, QA filtering, and model evaluation, supporting ReACT and DeepSeek-sty…☆23Feb 26, 2026Updated 4 months ago
- The official repository of the paper "Laplacian Gradient Consistency Prior for Flash Guided Non-Flash Image Denoising"☆13Nov 9, 2024Updated last year
- ☆13Oct 25, 2023Updated 2 years ago
- ☆50Apr 11, 2025Updated last year
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- 大模型技术栈一览☆127Sep 22, 2024Updated last year
- 7th Place Solution for Jigsaw Unintended Bias in Toxicity Classification on Kaggle☆16Jul 25, 2024Updated last year
- ☆20May 14, 2025Updated last year
- [ICLR 2025 Oral] Knowledge Entropy Decay during Language Model Pretraining Hinders New Knowledge Acquisition☆17Nov 25, 2024Updated last year
- ☆18Jun 12, 2026Updated last month
- This is a repository for "PMET: Precise Model Editing in a Transformer"☆58Sep 28, 2023Updated 2 years ago
- A SQL Query Similarity Metric Benchmark☆16Apr 22, 2018Updated 8 years ago
- MICCAI2023: Accurate multi-contrast MRI super-resolution via a dual cross-attention transformer network (DCAMSR)☆22Jul 31, 2023Updated 2 years ago
- Autonomous Driving Research and Educational Platform☆15Dec 22, 2021Updated 4 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- The repo of ASGMVLP☆19Jan 16, 2026Updated 6 months ago
- [npj Digital Medicine] From pretraining to privacy: federated ultrasound foundation model with self-supervised learning☆17Jul 11, 2026Updated last week
- ☆25Dec 9, 2024Updated last year
- 博客转载项目(将在线的博客转化为markdown格式文件)，支持CSDN、博客园、简书以及印象笔记的导出文件☆23Aug 21, 2024Updated last year
- ☆24Nov 11, 2024Updated last year
- ☆21Mar 30, 2022Updated 4 years ago
- The collection of medical VLP papars☆20Jul 24, 2024Updated last year