[ICML 2026] Hybrid Policy Distillation (HPD) is a practical distillation framework for reasoning-oriented language models. This repository contains the code, configurations, and experiment assets for the project.
☆25Apr 24, 2026Updated 4 months ago
Alternatives and similar repositories for Hybrid-Policy-Distillation
Users that are interested in Hybrid-Policy-Distillation are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Official repository for the paper "Learning beyond Teacher: Generalized On-Policy Distillation with Reward Extrapolation"☆294May 28, 2026Updated 3 months ago
- On Policy Distillation Build on top of Verl☆99Sep 3, 2026Updated last week
- A Teacher–Student Cooperation Framework to Synthesize Student-Consistent SFT Data☆37May 1, 2026Updated 4 months ago
- ☆84May 12, 2026Updated 4 months ago
- The official implementation of the paper "A Dual-Space Framework for General Knowledge Distillation of Large Language Models".☆17Jan 4, 2026Updated 8 months 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.
- Beyond SFT-to-RL: Pre-alignment via Black-BoxOn-Policy Distillation for Multimodal RL☆100May 6, 2026Updated 4 months ago
- Codebase for the work “Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?”☆77Apr 14, 2026Updated 5 months ago
- ☆36Jun 29, 2026Updated 2 months ago
- [COLM 2026] Revisiting On-Policy Distillation: Empirical Failure Modes and Simple Fixes☆137May 19, 2026Updated 3 months ago
- A Paper List for Math Word Problem☆20Oct 25, 2023Updated 2 years ago
- PyTorch-based open-source code for paper "SOD: Step-wise On-policy Distillation for Small Language Model Agents"☆165May 22, 2026Updated 3 months ago
- VLA^2: Empowering Vision-Language-Action Models with an Agentic Framework for Unseen Concept Manipulation☆33Nov 3, 2025Updated 10 months ago
- [ACL 2025] Cautious Next Token Prediction☆16Jul 24, 2025Updated last year
- Source code to accompany research paper on training multi token prediction language models using self-distillation.☆42Feb 21, 2026Updated 6 months 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.
- ☆635Sep 5, 2026Updated last week
- [ICLR'26 Oral] LLM DNA: Tracing Model Evolution via Functional Representations☆32Apr 8, 2026Updated 5 months ago
- ☆32Updated this week
- [COLM 2024] SKVQ: Sliding-window Key and Value Cache Quantization for Large Language Models☆25Oct 5, 2024Updated last year
- Official code for "Breaking the Ceiling in On-Policy Distillation via Multi-Agent Debate" (arXiv:2605.01347).☆37Jul 31, 2026Updated last month
- Adapter-X: A Novel General Parameter-Efficient Fine-Tuning Framework for Vision☆11Jul 22, 2024Updated 2 years ago
- ☆23Oct 22, 2024Updated last year
- ☆25Aug 3, 2026Updated last month
- Awesome List for On-Policy Distillation☆858Aug 26, 2026Updated 2 weeks ago
- 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.
- CoT-Valve: Length-Compressible Chain-of-Thought Tuning☆92Feb 14, 2025Updated last year
- [ICML2026] Reproduce Kimi K1.5/K2 RL algorithm and rollout system☆21Apr 9, 2026Updated 5 months ago
- HSTGODE code☆11Nov 26, 2023Updated 2 years ago
- RENT (Reinforcement Learning via Entropy Minimization) is an unsupervised method for training reasoning LLMs.☆42Oct 31, 2025Updated 10 months ago
- A user-friendly & efficient knowledge distillation framework for LLMs, supporting off-policy, on-policy (OPD), cross-tokenizer, multimoda…☆250Updated this week
- Efficient and Effective Weight-Ensembling Mixture of Experts for Multi-Task Model Merging. Arxiv, 2024.☆16Oct 28, 2024Updated last year
- Source Code for our ICLR'26 paper☆18Feb 22, 2026Updated 6 months ago
- Repo for paper "Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability"☆109Aug 15, 2026Updated last month
- [ICML 2026] Spherical Steering: Geometry-Aware Activation Rotation for Language Models☆22May 19, 2026Updated 3 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Non-Autoregressive Math Word Problem Solver with Unified Tree Structure☆12Jan 13, 2024Updated 2 years ago
- This repository collects Visual Autoregressive (VAR) modeling papers from 2024 to 2026 published at top-tier conferences, as well as rele…☆22Mar 13, 2026Updated 6 months ago
- ☆14May 21, 2024Updated 2 years ago
- ☆31May 20, 2026Updated 3 months ago
- ☆15May 4, 2024Updated 2 years ago
- Code release and project site for "CCIL: Continuity-based Data Augmentation for Corrective Imitation Learning"☆23Feb 19, 2026Updated 6 months ago
- Official GitHub repo for Scaling Physical Reasoning with the PHYSICS Dataset (NeurIPS25).☆16Sep 20, 2025Updated 11 months ago