BaohaoLiao / RSDLinks
[ICML 2025] Reward-guided Speculative Decoding (RSD) for efficiency and effectiveness.
☆47Updated 4 months ago
Alternatives and similar repositories for RSD
Users that are interested in RSD are comparing it to the libraries listed below
Sorting:
- Official repository for paper: O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning☆88Updated 7 months ago
- ☆131Updated 2 weeks ago
- PoC for "SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning" [NeurIPS '25]☆49Updated 2 months ago
- L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning☆254Updated 4 months ago
- Research Code for preprint "Optimizing Test-Time Compute via Meta Reinforcement Finetuning".☆105Updated last month
- [NeurIPS 2025] Simple extension on vLLM to help you speed up reasoning model without training.☆194Updated 3 months ago
- [ICLR 2025] SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration☆55Updated 7 months ago
- Revisiting Mid-training in the Era of Reinforcement Learning Scaling☆176Updated 2 months ago
- ☆332Updated last month
- Official implementation of the NeurIPS 2025 paper "Soft Thinking: Unlocking the Reasoning Potential of LLMs in Continuous Concept Space"☆229Updated 3 weeks ago
- [EMNLP 2025] TokenSkip: Controllable Chain-of-Thought Compression in LLMs☆179Updated 2 months ago
- The official repo of SynLogic: Synthesizing Verifiable Reasoning Data at Scale for Learning Logical Reasoning and Beyond☆166Updated 2 months ago
- ☆119Updated 3 months ago
- [NeurIPS 24 Spotlight] MaskLLM: Learnable Semi-structured Sparsity for Large Language Models☆177Updated 8 months ago
- 📖 This is a repository for organizing papers, codes, and other resources related to Latent Reasoning.☆210Updated 2 weeks ago
- Benchmark and research code for the paper SWEET-RL Training Multi-Turn LLM Agents onCollaborative Reasoning Tasks☆245Updated 4 months ago
- open-source code for paper: Retrieval Head Mechanistically Explains Long-Context Factuality☆210Updated last year
- General Reasoner: Advancing LLM Reasoning Across All Domains [NeurIPS25]☆171Updated 3 months ago
- ☆67Updated 5 months ago
- Chain of Experts (CoE) enables communication between experts within Mixture-of-Experts (MoE) models☆219Updated last week
- ☆86Updated 8 months ago
- Repo for "Z1: Efficient Test-time Scaling with Code"☆64Updated 5 months ago
- [NeurIPS 2025] Reinforcement Learning for Reasoning in Large Language Models with One Training Example☆361Updated this week
- [ICLR‘24 Spotlight] Code for the paper "Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy"☆94Updated 3 months ago
- [COLM 2025] Code for Paper: Learning Adaptive Parallel Reasoning with Language Models☆128Updated last month
- SWE-Swiss: A Multi-Task Fine-Tuning and RL Recipe for High-Performance Issue Resolution☆84Updated last week
- Code for "Critique Fine-Tuning: Learning to Critique is More Effective than Learning to Imitate" [COLM 2025]☆172Updated 2 months ago
- [NeurIPS'24] Official code for *🎯DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving*☆113Updated 9 months ago
- Unofficial implementation for the paper "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"☆171Updated last year
- [ICLR 2025] SuperCorrect: Advancing Small LLM Reasoning with Thought Template Distillation and Self-Correction☆80Updated 6 months ago