Codebase for the work “Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?”
☆75Apr 14, 2026Updated 3 months ago
Alternatives and similar repositories for self-distillation-analysis
Users that are interested in self-distillation-analysis are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆62Jul 3, 2026Updated last month
- Reinforcement Learning via Self-Distillation (SDPO)☆1,033Jul 1, 2026Updated last month
- On Policy Distillation Build on top of Verl☆93May 25, 2026Updated 2 months ago
- ☆21May 4, 2026Updated 3 months ago
- ☆666Apr 7, 2026Updated 3 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.
- DuoGuard: A Two-Player RL-Driven Framework for Multilingual LLM Guardrails☆34Feb 26, 2025Updated last year
- ☆533May 10, 2026Updated 2 months ago
- Open-source RL Framework with Online Teacher-Student Distillation☆22Mar 5, 2026Updated 4 months ago
- [ICML 2026] Hybrid Policy Distillation (HPD) is a practical distillation framework for reasoning-oriented language models. This repositor…☆24Apr 24, 2026Updated 3 months ago
- [ICML 2026] An Evaluation Suite for Chain-of-Thought Controllability☆50Mar 10, 2026Updated 4 months ago
- ☆22May 14, 2026Updated 2 months ago
- Official Code Repository for OmniRetrieval☆33Jun 1, 2026Updated 2 months ago
- [ICLR 2025 Oral] Knowledge Entropy Decay during Language Model Pretraining Hinders New Knowledge Acquisition☆17Nov 25, 2024Updated last year
- The open-source code for the NeurIPS 2025 paper, "Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learn…☆64Jan 5, 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.
- ☆16Feb 4, 2026Updated 6 months ago
- Reproducible and flexible LLM evaluations for scientific reasoning.☆29Jul 23, 2025Updated last year
- ☆34Oct 13, 2025Updated 9 months ago
- A package that achieves 95%+ transfer attack success rate against GPT-4☆26Oct 24, 2024Updated last year
- Code of Self-Distilled RLVR - RLSD☆62May 19, 2026Updated 2 months ago
- Self-Hinting Language Models Enhance Reinforcement Learning☆27Mar 28, 2026Updated 4 months ago
- Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe☆878Jun 29, 2026Updated last month
- ☆25Jun 10, 2025Updated last year
- Official implementation of "VideoZeroBench: Probing the Limits of Video MLLMs with Spatio-Temporal Evidence Verification"☆21May 7, 2026Updated 2 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.
- ☆17Jul 17, 2026Updated 2 weeks ago
- [ICML 2026] NITP: Next Implicit Token Prediction for LLM Pre-training☆34May 26, 2026Updated 2 months ago
- Code repository for the ICML 2026 Oral paper "Characterizing, Evaluating, and Optimizing Complex Reasoning".☆17Jun 21, 2026Updated last month
- [COLM 2025] SEAL: Steerable Reasoning Calibration of Large Language Models for Free☆62Apr 6, 2025Updated last year
- Implementation for the paper "Fictitious Synthetic Data Can Improve LLM Factuality via Prerequisite Learning"☆11Jan 10, 2025Updated last year
- ☆28Jan 31, 2026Updated 6 months ago
- GFT: From Imitation to Reward Fine-Tuning with Unbiased Group Advantages and Dynamic Coefficient Rectification☆36Jun 10, 2026Updated last month
- This repository includes code for our paper: ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning…☆15May 2, 2026Updated 3 months ago
- Rethinking the Trust Region in LLM Reinforcement Learning☆66Mar 2, 2026Updated 5 months ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- ☆23Dec 17, 2024Updated last year
- Official code for "Self-Distilled Agentic Reinforcement Learning"☆318Updated this week
- ☆71May 12, 2026Updated 2 months ago
- Repository for the paper: "TiC-LM: A Web-Scale Benchmark for Time-Continual LLM Pretraining" ACL Oral 2025☆24Apr 19, 2026Updated 3 months ago
- ☆76Jun 10, 2025Updated last year
- PARD: Accelerating LLM Inference with Low-Cost PARallel Draft Model Adaptation (ICLR 26)☆34Jun 10, 2026Updated last month
- [ICLR 2026 Blogpost Track Poster] JustRL: Scaling a 1.5B LLM with a Simple RL Recipe☆292Jun 29, 2026Updated last month