Jiaxin-Wen / Unsupervised-ElicitationLinks
☆39Updated 6 months ago
Alternatives and similar repositories for Unsupervised-Elicitation
Users that are interested in Unsupervised-Elicitation are comparing it to the libraries listed below
Sorting:
- Code for "Reasoning to Learn from Latent Thoughts"☆124Updated 9 months ago
- Reinforcing General Reasoning without Verifiers☆93Updated 6 months ago
- Code for ICLR 2025 Paper "What is Wrong with Perplexity for Long-context Language Modeling?"☆109Updated 3 months ago
- [Preprint] RLVE: Scaling Up Reinforcement Learning for Language Models with Adaptive Verifiable Environments☆174Updated last week
- [ICLR 2025] When Attention Sink Emerges in Language Models: An Empirical View (Spotlight)☆152Updated 6 months ago
- Optimizing Anytime Reasoning via Budget Relative Policy Optimization☆51Updated 6 months ago
- Official PyTorch implementation and models for paper "Diffusion Beats Autoregressive in Data-Constrained Settings". We find diffusion mod…☆119Updated last week
- RENT (Reinforcement Learning via Entropy Minimization) is an unsupervised method for training reasoning LLMs.☆41Updated 2 months ago
- [NeurIPS-2024] 📈 Scaling Laws with Vocabulary: Larger Models Deserve Larger Vocabularies https://arxiv.org/abs/2407.13623☆89Updated last year
- ☆111Updated 8 months ago
- ☆33Updated last year
- This is an official implementation of the Reward rAnked Fine-Tuning Algorithm (RAFT), also known as iterative best-of-n fine-tuning or re…☆38Updated last year
- Official implementation of Bootstrapping Language Models via DPO Implicit Rewards☆47Updated 9 months ago
- Code for "Language Models Can Learn from Verbal Feedback Without Scalar Rewards"☆55Updated 2 weeks ago
- ☆91Updated last year
- [NeurIPS 2024] Can LLMs Learn by Teaching for Better Reasoning? A Preliminary Study☆59Updated last year
- [COLM 2025] Code for Paper: Learning Adaptive Parallel Reasoning with Language Models☆137Updated last month
- Official github repo for the paper "Compression Represents Intelligence Linearly" [COLM 2024]☆147Updated last year
- PaCE: Parsimonious Concept Engineering for Large Language Models (NeurIPS 2024)☆41Updated last year
- A Large-Scale, High-Quality Math Dataset for Reinforcement Learning in Language Models☆71Updated 10 months ago
- official implementation of ICLR'2025 paper: Rethinking Bradley-Terry Models in Preference-based Reward Modeling: Foundations, Theory, and…☆70Updated 9 months ago
- [NeurIPS'24 Spotlight] Observational Scaling Laws☆59Updated last year
- Exploration of automated dataset selection approaches at large scales.☆53Updated 10 months ago
- Implementation of 🥥 Coconut, Chain of Continuous Thought, in Pytorch☆181Updated 7 months ago
- ☆202Updated 9 months ago
- The official repository for SkyLadder: Better and Faster Pretraining via Context Window Scheduling☆41Updated 3 weeks ago
- ☆50Updated 11 months ago
- RL Scaling and Test-Time Scaling (ICML'25)☆112Updated 11 months ago
- Ongoing research project for code&math LLMs☆24Updated 6 months ago
- Directional Preference Alignment☆58Updated last year