F2-Song / Weak-to-Strong-DecodingLinks
The official implementation of "Well Begun is Half Done: Low-resource Preference Alignment by Weak-to-Strong Decoding"
☆22Updated last month
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:
- Official repository for Montessori-Instruct: Generate Influential Training Data Tailored for Student Learning [ICLR 2025]☆48Updated 6 months ago
- Code & Dataset for Paper: "Distill Visual Chart Reasoning Ability from LLMs to MLLMs"☆53Updated 9 months ago
- The official implementation of Preference Data Reward-Augmentation.☆17Updated 3 months ago
- A Recipe for Building LLM Reasoners to Solve Complex Instructions☆20Updated last week
- RAG-RewardBench: Benchmarking Reward Models in Retrieval Augmented Generation for Preference Alignment☆16Updated 7 months ago
- HelloBench: Evaluating Long Text Generation Capabilities of Large Language Models☆46Updated 8 months ago
- Code for "C3PO: Critical-Layer, Core-Expert, Collaborative Pathway Optimization for Test-Time Expert Re-Mixing"☆17Updated 4 months ago
- Ruler: A Model-Agnostic Method to Control Generated Length for Large Language Models☆38Updated 10 months ago
- Think or Not? Selective Reasoning via Reinforcement Learning for Vision-Language Models☆40Updated 3 weeks ago
- FastCuRL: Curriculum Reinforcement Learning with Stage-wise Context Scaling for Efficient LLM Reasoning☆52Updated 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 this week
- [NAACL 2025] Source code for MMEvalPro, a more trustworthy and efficient benchmark for evaluating LMMs☆24Updated 10 months ago
- [ACL 2025 Findings] Implicit Reasoning in Transformers is Reasoning through Shortcuts☆16Updated 5 months ago
- JudgeLRM: Large Reasoning Models as a Judge☆32Updated 3 months ago
- Code for Heima☆51Updated 3 months ago
- Official implementation of "Reasoning Path Compression: Compressing Generation Trajectories for Efficient LLM Reasoning"☆22Updated 2 months ago
- ☆52Updated 3 weeks ago
- Code repository for the paper "The Inherent Limits of Pretrained LLMs: The Unexpected Convergence of Instruction Tuning and In-Context Le…☆13Updated 6 months ago
- This repository contains the code for the paper: SirLLM: Streaming Infinite Retentive LLM☆59Updated last year
- Source code for our paper: "ARIA: Training Language Agents with Intention-Driven Reward Aggregation".☆20Updated this week
- [arxiv: 2505.02156] Adaptive Thinking via Mode Policy Optimization for Social Language Agents☆39Updated last month
- OpenVLThinker: An Early Exploration to Vision-Language Reasoning via Iterative Self-Improvement☆104Updated 2 weeks ago
- Codebase for Instruction Following without Instruction Tuning☆35Updated 10 months ago
- The official implementation of Cross-Task Experience Sharing (COPS)☆25Updated 9 months ago
- ☆54Updated 2 months ago
- ☆42Updated 2 weeks ago
- ☆28Updated 3 weeks ago
- ☆29Updated 2 weeks ago
- [ACL 2025] A Generalizable and Purely Unsupervised Self-Training Framework☆68Updated 2 months ago
- [ACL 2025] Are Your LLMs Capable of Stable Reasoning?☆29Updated last week