[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.
☆24Apr 24, 2026Updated 6 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:
- Efficient and Effective Weight-Ensembling Mixture of Experts for Multi-Task Model Merging. Arxiv, 2024.☆16Oct 28, 2024Updated 2 years ago
- ☆30Sep 16, 2026Updated last month
- The implementation of Teachability-Aware On-Policy Distillation (TA-OPD), the method introduced in Not All Disagreement Is Learnable: Tok…☆20May 25, 2026Updated 5 months ago
- Non-Autoregressive Math Word Problem Solver with Unified Tree Structure☆12Jan 13, 2024Updated 2 years ago
- ☆21Jul 31, 2026Updated 2 months ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- A Teacher–Student Cooperation Framework to Synthesize Student-Consistent SFT Data☆38May 1, 2026Updated 5 months ago
- BEAVER: A Training-Free Hierarchical Prompt Compression Method via Structure-Aware Page Selection☆17Mar 30, 2026Updated 6 months ago
- ☆87May 12, 2026Updated 5 months ago
- Official repository for Activation-Informed Merging (AIM) of Large Language Models☆25Feb 10, 2025Updated last year
- [NeurIPS 2026] Beyond SFT-to-RL: Pre-alignment via Black-BoxOn-Policy Distillation for Multimodal RL☆101May 6, 2026Updated 5 months ago
- official code repo for paper "Merging Models on the Fly Without Retraining: A Sequential Approach to Scalable Continual Model Merging"☆25Oct 11, 2025Updated last year
- Repo for "STAR: Spectral Truncation and Rescale for Model Merging" [NAACL 2025]☆11Oct 22, 2026Updated last week
- [NeurIPS 2026] Training with Harnesses: On-Policy Harness Self-Distillation for Complex Reasoning☆27Oct 19, 2026Updated last week
- The official implementation of the paper "A Dual-Space Framework for General Knowledge Distillation of Large Language Models".☆17Jan 4, 2026Updated 9 months ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- An extension of veRL for post-training LLM reasoners with on-policy self-distillation and self-distilled RLVR + the official codebase for…☆80Oct 13, 2026Updated 2 weeks ago
- The official repository of "Whoever Started the Interference Should End It: Guiding Data-Free Model Merging via Task Vectors""☆51Oct 1, 2025Updated last year
- Code for "On Expressive Power of Looped Transformers: Theoretical Analysis and Enhancement via Timestep Encoding (ICML 2025)"☆10Jun 29, 2025Updated last year
- Code for paper "Merging Multi-Task Models via Weight-Ensembling Mixture of Experts"☆35Jun 7, 2024Updated 2 years ago
- Code for the paper Depth Memory☆14Oct 14, 2026Updated 2 weeks ago
- Continual Model Merging without Data: Dual Projections for Balancing Stability and Plasticity. NeurIPS, 2025.☆13Oct 12, 2025Updated last year
- A Paper List for Math Word Problem☆20Oct 25, 2023Updated 3 years ago
- ⚡ Official code for “Massive Activations in Hybrid Linear Attention Large Language Models: Pre-Attention Spikes and Inter-Spike Plateaus”…☆25Aug 13, 2026Updated 2 months ago
- Code for "Gated Recurrent Transformers: Expressive Depth through Recurrent Modulation"☆19Sep 1, 2026Updated last month
- 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.
- ☆14Aug 31, 2026Updated last month
- Official GitHub repo for SCI-Verifier: Scientific Verifier with Thinking (ICLR2026).☆11Jan 26, 2026Updated 9 months ago
- (Nanochat based) Full-bandwidth transformer, feed LLM's own deep hidden states back to itself☆16Oct 3, 2026Updated 3 weeks ago
- [ICML 2024] Code release for "On the Emergence of Cross-Task Linearity in Pretraining-Finetuning Paradigm"☆11Feb 20, 2025Updated last year
- ☆15Sep 29, 2026Updated last month
- [ICML 2023] "Robust Weight Signatures: Gaining Robustness as Easy as Patching Weights?" by Ruisi Cai, Zhenyu Zhang, Zhangyang Wang☆16May 4, 2023Updated 3 years ago
- ☆16Jul 21, 2025Updated last year
- LRT☆20Sep 19, 2026Updated last month
- Official implementation of the paper "Linear Model Merging Unlocks Simple and Scalable Multimodal Data Mixture Optimization".☆14Feb 16, 2026Updated 8 months ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- Pipelined Self-Speculative Decoding for Looped Transformer☆21Sep 24, 2026Updated last month
- SyMerge: From Non-Interference to Synergistic Merging via Single-Layer Adaptation☆12Jul 6, 2026Updated 3 months ago
- [NeurIPS 2026] AsyncOPD: How Stale Can On-Policy Distillation Be?☆39Updated this week
- ☆16Jul 13, 2026Updated 3 months ago
- FlashLoop: Fast and Memory-Efficient Looped Transformers via Lazy Updates☆22Sep 28, 2026Updated last month
- Pytorch code for NeurIPS 2025 paper "Accurate and Efficient Low-Rank Model Merging in Core Space"☆42Feb 2, 2026Updated 8 months ago
- ☆13Sep 29, 2026Updated last month