Codebase for the work “Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?”
☆77Apr 14, 2026Updated 4 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:
- ☆67Jul 3, 2026Updated 2 months ago
- Reinforcement Learning via Self-Distillation (SDPO)☆1,094Jul 1, 2026Updated 2 months ago
- On Policy Distillation Build on top of Verl☆98Sep 3, 2026Updated last week
- ☆21May 4, 2026Updated 4 months ago
- ☆694Apr 7, 2026Updated 5 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.
- DuoGuard: A Two-Player RL-Driven Framework for Multilingual LLM Guardrails☆34Feb 26, 2025Updated last year
- ☆631Sep 5, 2026Updated last week
- [ICML 2026] Hybrid Policy Distillation (HPD) is a practical distillation framework for reasoning-oriented language models. This repositor…☆25Apr 24, 2026Updated 4 months ago
- [ICML 2026] An Evaluation Suite for Chain-of-Thought Controllability☆53Mar 10, 2026Updated 6 months ago
- [COLM 2026] Revisiting On-Policy Distillation: Empirical Failure Modes and Simple Fixes☆137May 19, 2026Updated 3 months ago
- ☆25May 14, 2026Updated 3 months ago
- Official Code Repository for OmniRetrieval☆35Jun 1, 2026Updated 3 months ago
- Anti-Self-Distillation for Reasoning RL via Pointwise Mutual Information☆35May 14, 2026Updated 3 months ago
- [ICLR 2025 Oral] Knowledge Entropy Decay during Language Model Pretraining Hinders New Knowledge Acquisition☆17Nov 25, 2024Updated last year
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- The open-source code for the NeurIPS 2025 paper, "Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learn…☆68Jan 5, 2026Updated 8 months ago
- ☆16Feb 4, 2026Updated 7 months ago
- Reproducible and flexible LLM evaluations for scientific reasoning.☆32Jul 23, 2025Updated last year
- ☆34Oct 13, 2025Updated 10 months ago
- A package that achieves 95%+ transfer attack success rate against GPT-4☆26Oct 24, 2024Updated last year
- Self-Hinting Language Models Enhance Reinforcement Learning☆28Mar 28, 2026Updated 5 months ago
- Code of Self-Distilled RLVR - RLSD☆72May 19, 2026Updated 3 months ago
- Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe☆1,003Aug 20, 2026Updated 3 weeks ago
- Official implementation of "VideoZeroBench: Probing the Limits of Video MLLMs with Spatio-Temporal Evidence Verification"☆26May 7, 2026Updated 4 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.
- ☆17Jul 17, 2026Updated last month
- [ICML 2026] NITP: Next Implicit Token Prediction for LLM Pre-training☆35May 26, 2026Updated 3 months ago
- Code repository for the ICML 2026 Oral paper "Characterizing, Evaluating, and Optimizing Complex Reasoning".☆20Jun 21, 2026Updated 2 months ago
- [COLM 2025] SEAL: Steerable Reasoning Calibration of Large Language Models for Free☆65Apr 6, 2025Updated last year
- Implementation for the paper "Fictitious Synthetic Data Can Improve LLM Factuality via Prerequisite Learning"☆11Jan 10, 2025Updated last year
- ☆30Jan 31, 2026Updated 7 months ago
- [ICLR 2025] Language Imbalance Driven Rewarding for Multilingual Self-improving☆25Apr 6, 2026Updated 5 months ago
- GFT: From Imitation to Reward Fine-Tuning with Unbiased Group Advantages and Dynamic Coefficient Rectification☆36Jun 10, 2026Updated 3 months ago
- This repository includes code for our paper: ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning…☆15May 2, 2026Updated 4 months ago
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- Rethinking the Trust Region in LLM Reinforcement Learning☆74Mar 2, 2026Updated 6 months ago
- ☆23Dec 17, 2024Updated last year
- ☆82May 12, 2026Updated 4 months ago
- Repository for the paper: "TiC-LM: A Web-Scale Benchmark for Time-Continual LLM Pretraining" ACL Oral 2025☆24Updated this week
- ☆75Jun 10, 2025Updated last year
- PARD: Accelerating LLM Inference with Low-Cost PARallel Draft Model Adaptation (ICLR 26)☆34Jun 10, 2026Updated 3 months ago
- ☆16Jun 10, 2025Updated last year