VainF / ThinklessLinks
[NeurIPS 2025] Thinkless: LLM Learns When to Think
☆242Updated last month
Alternatives and similar repositories for Thinkless
Users that are interested in Thinkless are comparing it to the libraries listed below
Sorting:
- Official implementation of the NeurIPS 2025 paper "Soft Thinking: Unlocking the Reasoning Potential of LLMs in Continuous Concept Space"☆277Updated last week
- 📖 This is a repository for organizing papers, codes, and other resources related to Latent Reasoning.☆277Updated 2 weeks ago
- repo for paper https://arxiv.org/abs/2504.13837☆254Updated 4 months ago
- ☆341Updated 3 months ago
- [NeurIPS 2025] Reinforcement Learning for Reasoning in Large Language Models with One Training Example☆376Updated last month
- TraceRL & TraDo-8B: Revolutionizing Reinforcement Learning Framework for Diffusion Large Language Models☆317Updated last week
- CPPO: Accelerating the Training of Group Relative Policy Optimization-Based Reasoning Models (NeurIPS 2025)☆167Updated 2 weeks ago
- The official code of "VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning" [NeurIPS25]☆166Updated 5 months ago
- Geometric-Mean Policy Optimization☆92Updated this week
- OpenVLThinker: An Early Exploration to Vision-Language Reasoning via Iterative Self-Improvement☆119Updated 3 months ago
- ☆317Updated 2 weeks ago
- Test-time preferenece optimization (ICML 2025).☆169Updated 6 months ago
- Towards a Unified View of Large Language Model Post-Training☆184Updated 2 months ago
- OpenThinkIMG is an end-to-end open-source framework that empowers LVLMs to think with images.☆327Updated 5 months ago
- [NeurIPS 2025] The official repo of SynLogic: Synthesizing Verifiable Reasoning Data at Scale for Learning Logical Reasoning and Beyond☆186Updated 4 months ago
- ☆222Updated 8 months ago
- The official repo of One RL to See Them All: Visual Triple Unified Reinforcement Learning☆330Updated 5 months ago
- 🚀ReVisual-R1 is a 7B open-source multimodal language model that follows a three-stage curriculum—cold-start pre-training, multimodal rei…☆190Updated last month
- [ACL 2025] A Generalizable and Purely Unsupervised Self-Training Framework☆70Updated 5 months ago
- [EMNLP'25 Industry] Repo for "Z1: Efficient Test-time Scaling with Code"☆66Updated 7 months ago
- General Reasoner: Advancing LLM Reasoning Across All Domains [NeurIPS25]☆202Updated 3 weeks ago
- Benchmark and research code for the paper SWEET-RL Training Multi-Turn LLM Agents onCollaborative Reasoning Tasks☆250Updated 6 months ago
- MMSearch-R1 is an end-to-end RL framework that enables LMMs to perform on-demand, multi-turn search with real-world multimodal search too…☆348Updated 2 months ago
- A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning☆273Updated last month
- One-shot Entropy Minimization☆187Updated 5 months ago
- L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning☆257Updated 6 months ago
- Code for Heima☆58Updated 7 months ago
- ☆105Updated 5 months ago
- Official implementation of paper: SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training☆310Updated 6 months ago
- Codes for Visual Sketchpad: Sketching as a Visual Chain of Thought for Multimodal Language Models☆265Updated 3 months ago