F2-Song / Weak-to-Strong-DecodingLinks
The official implementation of "Well Begun is Half Done: Low-resource Preference Alignment by Weak-to-Strong Decoding"
☆23Updated 4 months ago
Alternatives and similar repositories for Weak-to-Strong-Decoding
Users that are interested in Weak-to-Strong-Decoding are comparing it to the libraries listed below
Sorting:
- The official implementation of Preference Data Reward-Augmentation.☆18Updated 6 months ago
- [NeurIPS 2025] Official implementation of "Reasoning Path Compression: Compressing Generation Trajectories for Efficient LLM Reasoning"☆24Updated last month
- [COLM 2025] "C3PO: Critical-Layer, Core-Expert, Collaborative Pathway Optimization for Test-Time Expert Re-Mixing"☆18Updated 7 months ago
- Ruler: A Model-Agnostic Method to Control Generated Length for Large Language Models☆39Updated last year
- [EMNLP 2025] Distill Visual Chart Reasoning Ability from LLMs to MLLMs☆57Updated 2 months ago
- This repo contains code for the paper "Both Text and Images Leaked! A Systematic Analysis of Data Contamination in Multimodal LLM"☆16Updated last month
- [NAACL 2025] Source code for MMEvalPro, a more trustworthy and efficient benchmark for evaluating LMMs☆24Updated last year
- [ACL 2025 Findings] Implicit Reasoning in Transformers is Reasoning through Shortcuts☆16Updated 8 months ago
- [ACL 2025] A Generalizable and Purely Unsupervised Self-Training Framework☆70Updated 5 months ago
- A Recipe for Building LLM Reasoners to Solve Complex Instructions☆28Updated last month
- [NeurIPS 2025] Think or Not? Selective Reasoning via Reinforcement Learning for Vision-Language Models☆48Updated last month
- Code for Heima☆58Updated 7 months ago
- ☆17Updated 8 months ago
- ☆32Updated 4 months ago
- RAG-RewardBench: Benchmarking Reward Models in Retrieval Augmented Generation for Preference Alignment☆16Updated 11 months ago
- [NeurIPS 2025] Let LRMs Break Free from Overthinking via Self-Braking Tuning. https://arxiv.org/abs/2505.14604☆51Updated 2 weeks ago
- ☆31Updated last week
- ☆51Updated 9 months ago
- [AAAI 2026] ReCode: Reinforced Code Knowledge Editing for API Updates☆22Updated 4 months ago
- JudgeLRM: Large Reasoning Models as a Judge☆40Updated 2 months ago
- Official Implementation of our paper "THOR: Tool-Integrated Hierarchical Optimization via RL for Mathematical Reasoning".☆27Updated 2 months ago
- Evaluation framework for paper "VisualWebBench: How Far Have Multimodal LLMs Evolved in Web Page Understanding and Grounding?"☆60Updated last year
- HelloBench: Evaluating Long Text Generation Capabilities of Large Language Models☆52Updated 11 months ago
- Code repository for the paper "The Inherent Limits of Pretrained LLMs: The Unexpected Convergence of Instruction Tuning and In-Context Le…☆13Updated 10 months ago
- Emergent Hierarchical Reasoning in LLMs/VLMs through Reinforcement Learning☆48Updated 3 weeks ago
- The official implementation of Cross-Task Experience Sharing (COPS)☆30Updated last year
- The official code repository for the paper "Mirage or Method? How Model–Task Alignment Induces Divergent RL Conclusions".☆15Updated 2 months ago
- Official repository for Montessori-Instruct: Generate Influential Training Data Tailored for Student Learning [ICLR 2025]☆48Updated 10 months ago
- FastCuRL: Curriculum Reinforcement Learning with Stage-wise Context Scaling for Efficient LLM Reasoning☆53Updated last month
- [ICLR 2025] LongPO: Long Context Self-Evolution of Large Language Models through Short-to-Long Preference Optimization☆43Updated 8 months ago