Anti-Self-Distillation for Reasoning RL via Pointwise Mutual Information
☆35May 14, 2026Updated 4 months ago
Alternatives and similar repositories for AntiSD
Users that are interested in AntiSD are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆37Feb 12, 2026Updated 7 months ago
- The 1st Spiking Transformer Benchmark (NeurIPS 2025)☆18Jul 10, 2026Updated 2 months ago
- Codebase for the work “Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?”☆77Apr 14, 2026Updated 5 months ago
- Repository for the paper "Advancing General-Purpose Reasoning Models with Modular Gradient Surgery"☆22Mar 15, 2026Updated 6 months ago
- Codebase for DeepVision-103K☆22Feb 21, 2026Updated 7 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.
- ☆18Mar 16, 2026Updated 6 months ago
- RewardAnything: Generalizable Principle-Following Reward Models☆47Jun 11, 2025Updated last year
- RedSearcher's framework for deep search agent trajectory synthesis, QA filtering, and model evaluation, supporting ReACT and DeepSeek-sty…☆27Feb 26, 2026Updated 7 months ago
- ☆23Aug 25, 2026Updated last month
- Reasoning Guided Embeddings: Leveraging MLLM Reasoning for Improved Multimodal Retrieval☆16Nov 29, 2025Updated 10 months ago
- Fast Metropolis-Hastings sampler for LLMs.☆25Jan 2, 2026Updated 9 months ago
- ☆11Jan 8, 2025Updated last year
- ☆670Sep 5, 2026Updated last month
- Bert-Chinese-Text-Classification-Pytorch-master☆10Jan 8, 2023Updated 3 years ago
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- Co-evolving policy actors and experience extractors for efficient experience-driven agent RL☆52May 12, 2026Updated 4 months ago
- LoongRL: Reinforcement Learning for Advanced Reasoning over Long Contexts (ICLR 2026 Oral)☆38Feb 20, 2026Updated 7 months ago
- Code for NeurIPS 2026 paper OpenWebRL: Online Multi-Turn Reinforcement Learning for Visual Web Agents☆52Aug 17, 2026Updated last month
- ☆41Aug 2, 2026Updated 2 months ago
- Weak-to-Strong Generalization via Direct On-Policy Distillation☆93Aug 18, 2026Updated last month
- A curated collection of papers, technical reports, frameworks, and tools for on-policy distillation (OPD) of large language models☆866Aug 30, 2026Updated last month
- [COLM 2026] An efficient 3D sampling method for long-CoT LLM.☆16May 25, 2025Updated last year
- On Policy Distillation Build on top of Verl☆101Sep 3, 2026Updated last month
- [ICML'26] Official implementation of paper "Think-at-Hard: Selective Latent Iterations to Improve Reasoning Language Models"☆93Updated this week
- 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.
- The dataset and code for the EMNLP 2022 paper "Hierarchical Multi-Label Classification of Scientific Documents" are released here.☆21Mar 29, 2023Updated 3 years ago
- ☆26Nov 20, 2021Updated 4 years ago
- Official repository for paper Auto-scaling Continuous Memory for GUI Agent☆31Feb 2, 2026Updated 8 months ago
- ☆11Sep 20, 2024Updated 2 years ago
- ☆208Apr 19, 2025Updated last year
- Data and Baselines for AStitchInLanguageModels dataset☆13Oct 31, 2022Updated 3 years ago
- [NeurIPS 2024] Exploring Structured Semantic Priors Underlying Diffusion Score for Test-time Adaptation☆22Mar 15, 2025Updated last year
- ☆12Jan 9, 2025Updated last year
- Implementation of LaViC (KDD 2025)☆13Jun 1, 2025Updated last year
- 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.
- 本项目采用Firefly模型训练框架，使用LLAMA-2模型对多项选择阅读理解任务（Multiple Choice MRC）进行微调，取得了显著的进步。☆11Sep 16, 2023Updated 3 years ago
- RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Models. NeurIPS 2024☆102Sep 30, 2024Updated 2 years ago
- ☆10Apr 20, 2023Updated 3 years ago
- Reinforcement Learning via Self-Distillation (SDPO)☆1,108Jul 1, 2026Updated 3 months ago
- ☆10May 20, 2026Updated 4 months ago
- This repository includes code for our paper: ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning…☆17May 2, 2026Updated 5 months ago
- The official implementation of "LightTransfer: Your Long-Context LLM is Secretly a Hybrid Model with Effortless Adaptation"☆22Apr 22, 2025Updated last year